CA3073589A1 - Detecting location within a network - Google Patents
Detecting location within a network Download PDFInfo
- Publication number
- CA3073589A1 CA3073589A1 CA3073589A CA3073589A CA3073589A1 CA 3073589 A1 CA3073589 A1 CA 3073589A1 CA 3073589 A CA3073589 A CA 3073589A CA 3073589 A CA3073589 A CA 3073589A CA 3073589 A1 CA3073589 A1 CA 3073589A1
- Authority
- CA
- Canada
- Prior art keywords
- transceiver
- detection area
- human
- humans
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/0278—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves involving statistical or probabilistic considerations
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/22—Electrical actuation
- G08B13/24—Electrical actuation by interference with electromagnetic field distribution
- G08B13/2491—Intrusion detection systems, i.e. where the body of an intruder causes the interference with the electromagnetic field
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P13/00—Indicating or recording presence, absence, or direction, of movement
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/04—Systems determining presence of a target
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
- Mobile Radio Communication Systems (AREA)
- Alarm Systems (AREA)
Abstract
Systems and methods for detecting the presence of a body in a network without fiducial elements, using signal absorption, and signal forward and reflected backscatter of radio frequency (RF) waves caused by the presence of a biological mass in a communications network.
Description
DETECTING LOCATION WITHIN A NETWORK
CROSS-REEgRENCE TO RELATED APPLICATION$
[001] This application is a Continuation of United States Utility Patent Application No.
15/713,309 filed September 22, 2017; is a Continuation of United States Utility Patent Application No. 15/713,219 filed September 22, 2017; is a Continuation of United States Utility Patent Application No. 15/674,487, filled on August 10, 2017; and is a Continuation of United States Utility Patent Application No, 15/674,328, flied on August 10, 2017, Application 15/713,219 is a continuation of United States Utility Patent Application No, 15/674,328, filed on August 10, 2017, which is continuation-in-part of United States Utility Patent Application NO,15/600,380; filed May 19, 201T; whichis:Wcontinuation of United States Utilit Patent Application NO. 15/227,717, filed August 3; 2016, Which claims the benefit of United States Provisional Patent Application Number 62/252,954, filed November 9, 2015, and United States Provisional Patent Application Number 62/219,457.
filed September 16,'2015. Application 15/713,309 is a Continuation of United States Utility Patent Application No. 15/674,487, filed on August 10, 2017 which is a continuation of United States Utility Patent Application No. 15/674,328, filed on August 10, 2017, which is continuation-in-part of United States Utility Patent Application No.
15/600,380, filed May 19, 2017, which is a continuation of United States Utility Patent Application No. 15/227,717, filed August 3, 2016, which claims the benefit of United States Provisional Patent Application Number 62/252,954, filed November 9, 2015, and United States Provisional Patent Application Number 62/219,457, filed September 16, 2015. Application 15/227,717 is , continuation of United States Utility Patent Application No. .15/0S4002, filed Mardi 20,, 2016, and iSsttOd On October 18, 201ó.aS United StateS Utility Patent NCi.
9,474,042, Which applications in turn also claim benefit of United States Provisional Patent Application Number 62/252,954, filed November 9, 2W 5, and United States Provisional Patent Application Number 62/219457, filed September 16, 2015. The entire disclosure of all of these documents is herein incorporated by reference..
CROSS-REEgRENCE TO RELATED APPLICATION$
[001] This application is a Continuation of United States Utility Patent Application No.
15/713,309 filed September 22, 2017; is a Continuation of United States Utility Patent Application No. 15/713,219 filed September 22, 2017; is a Continuation of United States Utility Patent Application No. 15/674,487, filled on August 10, 2017; and is a Continuation of United States Utility Patent Application No, 15/674,328, flied on August 10, 2017, Application 15/713,219 is a continuation of United States Utility Patent Application No, 15/674,328, filed on August 10, 2017, which is continuation-in-part of United States Utility Patent Application NO,15/600,380; filed May 19, 201T; whichis:Wcontinuation of United States Utilit Patent Application NO. 15/227,717, filed August 3; 2016, Which claims the benefit of United States Provisional Patent Application Number 62/252,954, filed November 9, 2015, and United States Provisional Patent Application Number 62/219,457.
filed September 16,'2015. Application 15/713,309 is a Continuation of United States Utility Patent Application No. 15/674,487, filed on August 10, 2017 which is a continuation of United States Utility Patent Application No. 15/674,328, filed on August 10, 2017, which is continuation-in-part of United States Utility Patent Application No.
15/600,380, filed May 19, 2017, which is a continuation of United States Utility Patent Application No. 15/227,717, filed August 3, 2016, which claims the benefit of United States Provisional Patent Application Number 62/252,954, filed November 9, 2015, and United States Provisional Patent Application Number 62/219,457, filed September 16, 2015. Application 15/227,717 is , continuation of United States Utility Patent Application No. .15/0S4002, filed Mardi 20,, 2016, and iSsttOd On October 18, 201ó.aS United StateS Utility Patent NCi.
9,474,042, Which applications in turn also claim benefit of United States Provisional Patent Application Number 62/252,954, filed November 9, 2W 5, and United States Provisional Patent Application Number 62/219457, filed September 16, 2015. The entire disclosure of all of these documents is herein incorporated by reference..
2 BACKGROUND
1. Field of the Invention [002] This disclosure is related to the field of object detection, and more particularly to systems and methods for detecting the presence or a biological mass within a wireless comm uni cati on s network.
2. Description of the Related Art [0031 Tracking objects may be done using a number of techniques. For example, a moving transceiver may be attached to the object. Examples of such systems include global positioning location systems such as GPS, which use orbiting satellites to communicate with terrestrial = transceivers. However, Such systems are generally less effective indoors, where satellite signals may be blocked, reducing accuracy. Thus, other technologies are often used indoors, such as BiuetoothTM beacons, which calculate the location of a roaming Or unknown transceiver_ The roaming transceiver acts as a fiducial element.
[004] These systems have several disadvantages, among them that the object tracked must include a transceiver. In certain applications, the object to be tracked will have no such fiducial element, or will actively disable any such element, such as an intruder in a home.
[005) Other technologies exist which can also detect and track objects without the use of a fiducial element. For example, radar is a Venerable object-detection system that uses RF waves to determine the man, angle, or velocity of atiectsõ including aircraft, ships, spacecraft, guided missiles, motor vehicles, weather formations, and terrain. Radar operates by transmitting electromagnetic waves, generally using waves in the radio frequency ("RP") of the electromagnetic spectrum, which reflect from any object in their path. A
receiver, typically part of the same system as the transmitter, receives and processes these reflected waves to determine properties of the objects. Other systems similar to radar, using other parts of the
1. Field of the Invention [002] This disclosure is related to the field of object detection, and more particularly to systems and methods for detecting the presence or a biological mass within a wireless comm uni cati on s network.
2. Description of the Related Art [0031 Tracking objects may be done using a number of techniques. For example, a moving transceiver may be attached to the object. Examples of such systems include global positioning location systems such as GPS, which use orbiting satellites to communicate with terrestrial = transceivers. However, Such systems are generally less effective indoors, where satellite signals may be blocked, reducing accuracy. Thus, other technologies are often used indoors, such as BiuetoothTM beacons, which calculate the location of a roaming Or unknown transceiver_ The roaming transceiver acts as a fiducial element.
[004] These systems have several disadvantages, among them that the object tracked must include a transceiver. In certain applications, the object to be tracked will have no such fiducial element, or will actively disable any such element, such as an intruder in a home.
[005) Other technologies exist which can also detect and track objects without the use of a fiducial element. For example, radar is a Venerable object-detection system that uses RF waves to determine the man, angle, or velocity of atiectsõ including aircraft, ships, spacecraft, guided missiles, motor vehicles, weather formations, and terrain. Radar operates by transmitting electromagnetic waves, generally using waves in the radio frequency ("RP") of the electromagnetic spectrum, which reflect from any object in their path. A
receiver, typically part of the same system as the transmitter, receives and processes these reflected waves to determine properties of the objects. Other systems similar to radar, using other parts of the
3 electromagnetic spectrum, may also be used in similar fashion, such as ultraviolet, visible, or near-infrared light from lasers.
[006] Radar technologies do not require a tiduciai element, but have other shortcomings. For example, radar signals are susceptible to signal noise, or random variations in the signal caused by internal e lee:FA aal components, as -well as noise and interference from external sources, such as the nattu al background radiation. Radar is also vulnerable to external interference sources, such as intervening objects blocking the beam path and can be deceived by objects of particular si;e, shape, and orientation.
[006] Radar technologies do not require a tiduciai element, but have other shortcomings. For example, radar signals are susceptible to signal noise, or random variations in the signal caused by internal e lee:FA aal components, as -well as noise and interference from external sources, such as the nattu al background radiation. Radar is also vulnerable to external interference sources, such as intervening objects blocking the beam path and can be deceived by objects of particular si;e, shape, and orientation.
4 SUMMARY
[007] The following is a summary of the invention in order to provide a basic understanding of some aspects of the invention. This summary is not intended to identify key or critical elements of the invention or to delineate the scope of the invention. The sole purpose Of this section is to present some: concepts of the invention in a simplified form as a prelude to the more detailed description that is presented 'a ter.
[00$1 Because of these and other problems in the art, there is described herein, among other thing* :is a method for detecting the presence of a human comprising:
providing a first transceiver disposed at a first position within a detection area; providing a second transceiver disposed at a: second location within the detection area a computer server commtuneably coupled to the first transceiver; the first transceiver receiving a first set of wireless signals from the second transceiver via the wireless communications network; the computer server receiving a first set of signal data from the first transceiver, the first set of signal data comprising data about the properties of the first set of wireless signals, the property data being generated as part of ordinary operation of the first transceiver on the communication network;
the computer =server creating a baseline signal profile Ito communications from the Second transceiver to the firs tanseeiver, the baseline signal profile being basect at least in part on the witeiess properties thOreceiVed first Set Of Signal data, and :t7epreSenting characteristics of wireless transmissions from the second transceiver ts3 the first rransceiver when no human is present in the detection area; the first transceiver receiving a second set of wireless signals from the second transceiver via the wireless eo.mmunicationa tietWOrlr, the computer server receiving a = second set Of Signal data from the first transceiver, the second set of signal data comprising data about the properties of the second set of wireless signals, the property data being generated as part. of ordinary operation of the first transceiver on the communication network; and the computer server determining whether a human is present within the detection area, the determination based at least in part on a comparison of the wireless signal properties in the received second set of wireless signal data to the baseline signal profile.
[009] In an embodiment of the method, the first set of signal properties comprise wireless /*Mak signal protocol properties determined by the first transddiva.
[0 0] In another embodiment Othe method, the wireless network signal protocol properties are selected from the group consisting of: received signal strength, latency, and bit error rate.<
[0 II In another embodiment of the method, the method further comprises:.
providing a third transceiver disposed at a third location within the detection area; the first transeeiyer receiving a third set of wireless sign* from the third tranSCei*eit Oa the Wireless cemniarticationS
network; the computer server receiving a third set of signal data from the firSt transceiver, the third set of signal data comprising data about the properties of the third set of wireless signals, the property data being generated as part of ordinary operation of the first transceiver on the communication network, the computer server creating a second baseline signal profile for communications from the third transceiver to the first transceiver, the second baseline signal profile being based at least in part on the wireless signal properties in the received third set of Signal data, and representing characteristics of wire less from the third transceiver to the :first transceiver when no human is present in the detection area; the first transceiver receiving a fourth set Of wireless signals from the third transceiver via the wireless :communications network', the computer server receiVing a fourth set of signal data: from the first transce.iver, the fourth sot of signal data comprising data abOut the properties of the fourth set Of wireless Sign*, :the property data being generated as part of ordinary operation of the first transceiver on the communication network; and in the determining step, the computer server determining whether a human is present within the detection area based at least in part on a comparison of the wireless signal properties in the received fourth set of wireless signal data to the second baseline signal profile.
[0121 in another embodiment of the method, the determining step applies statistical methods to the second set of wireless signal data to determine the presence of a human.
[0131 In another embodiment of the method, the method further comprises: the computer server continuously determining the presence or absence of a human within the detection area, the determination based at least in part on a comparison of the baseline signal profile to signal data comprising data about the properties of the first set of wireless signals received continuously at the computer server from the first transceiver; and the computer continuously updating the baseline signal profile based on. the continuously received signal data when the continuously received signal data indicates the absence of a human in the detection area.
[0141 In another embodiment of the method, the method further comprises: the computer server determining the number of humans is present within the detection area, the determination based at least in part on a comparison of the received second set of signal properties to the baseline signal profile.
[015] in another embodiment of the method, the method further comprises: the computer server determining the location of one or more humans within the detection area: the determination based at least in part on a comparison of the received second set of signal properties to the baseline signal profile.
[0161 In another embodiment of the method, the method further comprises: the computer server being operatively coupled to a second system; and:only after the computer server detects the presence of a human in the detection area, the computer operates the second system.
[0171 In another embodiment of the method, the detection network and the second system are configured to communicate using the same communication protocol.
[0181 In another embodiment of the method, the second system is an electrical system.
[0191 In another embodiment of the method, the second system is a lighting system.
[020] i In another embodiment of the method, the second system is .::a heating, venting, and cooling (FIVAC) system, [021] In another embodiment of the method, the second system is a security system.
[021] In another embodiment of the method, the second system is an industrial automation system [023] In another embodiment of the method, the wireless communication protocol is selected from the group consisting of: Bluetoothm, BlnetoothTM Low Energy, ANT, ANTI-, WiFi, Zigbee, Thread, and Z-Wave.
[024] in another embodiment of the method, the wireless communication network has a carrier frequency in the range of 850 MHz and 17,5 Gliz inclusive.
[025] In another embodiment of the method, the determination whether a human is present within the detection area is adjusted based on machine learning comprising:
determining a first sample location of a human having a fiducial element in the detection area, the first sample location being determined based upon detecting the fid.ucial element;
determining a second sample location of the human in the detection area, the second sample location being determined based at least in pan on a comparison of the received second set of signal data to the baseline signal profile not utilizing the fiducial element; comparing the first sample location and the second sample location; and adjusting the determination step based on non-fiducial element location to improve the location calculating capabilities of the System, the adjusting based upon the comparing step.
[026] In another embodiment of the method, the determination whether a human is present within the detection area is adjusted based on machine learning comprising:
determining based on user input or action that a human was present in an area when the sample signal properties correspond at least in part with baseline signal properties of an empty space, modifying, at least In part, the baseline signal properties for an empty space; modifying, at least in part, the signal properties associated with an occupied space; and adjusting the method for comparing sample signal properties to the baseline and other comparative signal properties to improve the accuracy of the system over time.
[0271 In an embodiment of the system, the user input or action which provides presence data is provided directly to the system in some form including, but not limited to, physical switches, smartphone input, or auditory cues.
[028] In an embodiment of the system, the user input or action which provides presence data is provided indirectly to the system in some form, such as deliberately Changing the signal profile to counteract a decision being taken by the system, such as providing such a change during a dimming phase in a lighting system.
[029] In another embodiment of the method, the method further comprises: the computer server storing a plurality of historical data records indicative of whether a human was present in the detection area over a period of time, each of the historical data records comprising an indication of the number of humans detected in the detected area and the date and time of when the number of humans was detected in the detection area; and the computer server making the historical data records available to one or more external computer systems via an interface.
[0301 Also described herein, among other things, is a method for detecting the presence of a human comprising: providing a first transceiver disposed at a first position within a detection area; providing a second transceiver disposed. at a second location within the detection area;
providing a computer server communicably coupled to the first transceiver;
providing a first external system operatively coupled to the computer server; providing a second external system operatively coupled to the computer server; the computer server receiving from the 'first transceiver a set of baseline signal data comprising property data about the signal properties of a first set of wireless signals received by the first transceiver from the second transceiver when no human is present in the detection area, the property data being generated by the first transceiver as part of ordinary operation of the first transceiver on the communication network;
the computer server creating a baseline signal profile for communications from the second transceiver to the first transceiver when no human is present in the detection area, the baseline signal profile being based at least in part on the property data representing characteristics of wireless transmissions from the second transceiver to the first transceiver when no human is present in the detection area; the computer server receiving from the first transceiver a first set of sample baseline signal data comprising property data about the signal properties of a second set a wireless signals received by the first transceiver from. the second transceiver when a human is present in the detection area, the property data being generated by the first transceiver as part of ordinary operation of the first transceiver on the communication network; the computer server creating a first sample baseline signal profile for communications from the second transceiver to the first transceiver when a human is present in the detection area, the first sample baseline signal profile being based at least in part on the property data in the first set of sample baseline signal data, representing characteristics of wireless transmissions from the second transceiver to the first transceiver when a human is present in the detection area; the computer server receiving from the first transceiver a second set of sample baseline signal data comprising property data. about the signal properties of a third set of wireless signals received by the first transceiver from the second transceiver when a human is present in the detection area, the property data being generated by the first transceiver as part of ordinary operation of the first transceiver on the communication network; the computer server creating a second sample baseline signal profile for communications from the second transceiver to the first transceiver when a human is present in the detection area, the second sample baseline signal profile being based at least in part on the property data in the second set of sample baseline signal data, representing characteristics of wireless transmissions from the second transceiver to the first transceiver when a human is present in the detection area; the computer server receiving: from the first transceiver a third set of sample baseline signal data comprising property data about the signal properties of a fourth set of wireless signals received by the first transceiver from the second transceiver when a human is present in the detection area, the property data being generated by the first transceiver AS. part Of ordinary operation of the first trattaceiver Q.11 the 0:n1'110i:0*i netWork; the cot Niter servOdeteonining to Operate the first external system based upon the computer SONO determining that the property data in the third Set of sample baseline Signal data:corresponds to the first sample baseline signal profile; the Computer server determining not to operate the Second external system based upon the computer server determining that the property data in the third set of sample haSeline signal data does not correspond to the secktaid sample baseline signal profile, [031] In an embodiment of the method, the determination to operate the first external system and the determination not to operate the second external system is adjusted based on machine learning comprising: determining a first sample location of a human having a fiducial element in the detection area, the first sample location being determined based upon detecting the fiducial element; determining a second sample location of the human in the detection area, the second sample location being determined based: at least itipatt on a comparison of the received second set of :signal data to the baseline signal profile not utilizing the fiducial element;
COniparing the fit* sample location and the Second Sample lOcation; ,a.ncl adjusting the determination stops based on non-fiducial element location to improve the location calculating capabilitieg of the system: the adjusting based upon the comparing step.
[032} In another embodiment of the method, the determination to operate the Org.: external system and the determination not to operate the second external gS;,Stem is adjusted based on machine learning comprising: determining a first sample location of a human in the detection area using inference, the first sample location being determined based upon detecting the human interacting with the system in some known way; determining a second sample location :of the human in the detection area, the second sample location being determined based at least in part on a comparison of the received second set of signal data to the baseline signal profile not utilizing the inferred location; comparing the first sample location and the second sample location; and adjusting the determination steps based on inferred location to improve: the 10CatiOnealculating, capabilities of the system, the adjusting based upon the comparing step.
[033] In another embodiment of the method, the property data about the wireless signals comprises dam about signal properties selected from the group consisting of:
received signal strength, latency, and bit error rate:, [OA In another embodiment of the method, the computer server creates the:.
first gam*
baseline signal profile by applying statiSticat methods :to the first set of sample baseline signal data, and the computer server creates the second sample baseline signal profile by applying statistical methods to the second set of sample baseline signal data.
[035] in another embodiment of the method, the method further comprises: the computer server receiving from the first transceiver additional sets of baseline signal data comprising property data about the signal properties of a second set of wireless signals received by the first transceiver from the second transeeiVel; the property: data being getterated by the lint ttansceivens part of ordinary operation of the first transceiver on the communication network and the computer Se0er Updating the baseline signal :profile basedon the continuOnslyteccived additional sets of baseline signal data when the continuously received sets of baseline signal data indicate the absence of a human in the detection area, [OM In another embodiment Of the method, the method further comprises: the ootop4tot server receiving from the first tran c6vet a set of signal data comprising property data about the signal properties of a second set of wireless signals received by the first transceiver from the second transceiver when one or more humans are present in the detection area, the property data being generated by the first transceiver as part of ordinary operation of the first transceiver on the communication network; the computer server determining the quantity Of humans present in the detection area based at least in part on a comparison of the set of signal data to the baseline signal profile [037) In another embodiment of the method, the method further comprises: the computer Wye determining, a location Of each of the One or More humans preSent in the detect en at the determination based at least in part on a comparison of the set cf signal data to the baseline signai profile.
.0381 In another enthodiment of the method. When. a human is present in the detection area, the computer server determines that a Inman is present in the detection area and operates the first external system even if the property data in the third set of sample baseline signal data corresponds to the second sample baseline signal profile.
[039] In another embodiment of the method, when a human is present in the detection area, the computer server determines that a human is present in the detection area and operates the second external system only if the property data in the third set of sample baseline signal data corresponds to the second sample baseline signal profile.
[040] hi another embodiment Of the method, the wirelest:communication netWork has a carrier frequency in the range: of 850 MHz and 17.5 014 itic.tusivd:
[04 11 in 4E000:embodiment of the method, the Method further CompriSeS: the :Computer server storing a. plurality of historical data records indicative of whether a human was present in the detection area over 4:period of time, each of the historical data records comprising an indication of the number of humans detected in the detected area and the date and time of when the number of humans WAS detected in the detection area; and the compute Server making the historical data records available to one or more external computer systems via an interface, BRIVEDESCRWTION'OF THE DRAWINGS
[0421 FIG, I is a schematic diagram of an embodiment of a system according to the present disclosure, [0431 FiCk:21gallow chart eat. embodiment otamethod according to the pitstiit di Sciosure.
[044.13 :FIG. 3A depicts:A...$0hOnatic diagram Of.a system for change detection in a deteefi0 network over rinit'according to the present disclosure.
[045] FI:O. 3B deript schematic diagram of a system for detecting changes itt loolions of humans in .,0::de*tion netwodc overtime a(.01:- ding to.: the present*sclosure.
DESCRIPTION OF THE PREFERRED EMBODIMENT
[046] The following detailed description and disclosure illustrates by way of example and not by way of limitation, This description will clearly enable one skilled in the art to make and use the disclosed :system. and methods).. :and describes several embodiments,:
adaptations,i variations, alternatives and uses of the disclosed SyStetnS and methods AS:
various changes could be made in the above ainstructions:without departina from the stope of the disclogureS, it is intended that all matter contained in the description or shown in the accompanying drawings shall be interpreted as illustrative and not in a limiting sense:
[047] Generally speaking, described herein, among other things, are systems and methods for detecting the presence ofa body in a network Without fiducial elements.
Generally speaking, the systems and methods described herein use signal absorption, and signal forward scatter and reflected back.scatter of the RE communication caused by the presence of a biological mass in a communications network, generally a mesh network.
[048] Throughout this disclosure, the term "computer" describes hardware which generally implements functionality provided by digital computing technology, particularly computing functionality associated with microprocessors. The term 'computer" is not intended to be limited to arpy .,,pecifie type 01 4ompt#14 de ice btit it is 'intended to be inclusive of all computational devices includiiig, but not limited to: processing devices, :oticroproceSSor*
personal computers, desktop computers, laptop computersõ:: workstations, terminals, servers,õ
clients, portable computem,: handheld computer*: Smart phones, tablet c omputer.s,, mob 'L
Joie es, sdiNer farms, hardware applianeeS, minicomputers, mainframe computers, video game consoles, handheld video game products, and wearable computing devices including but not limited to eyewear, wrist-wear, pendants, and clip-on devices.
[049] As used herein, a "computer" is necessarily an abstraction of the functionality provided by a single computer device outfitted with the hardware and accessories typical of computers in a particular role. By way of example and not limitation, the term "computer" in reference to a laptop computer would be understood by one of ordinary skill in the art to include the functionality provided by pointer-based input devices, such as a mouse or track pad, whereas the term "computer' used in reference to an enterprise-class server would be understood by one of ordinary ski fin the art to include the functionality provided by redundant systems, such aS RAID (hives and dual power supplies.
[050) It is also well known to those of ordinary skill in the art that the functionality of e single computer may be distributed across a number of individual machines. This distribution may be functional, as where specific machines perform specific tasks; or, balanced, as where each machine is capable of performing most or all functions of any other machine and is assigned tasks based on its available resources at a point in time. Thus, the term "computer" as used herein, can refer to a single, standalone, self-contained device or to a plurality of machines working together or independently, including without limitation: a network server farm, "cloud" computing system, software-as-a-service, Or other distributed or collaborative computer networks, [051] Those of ordinary skill in the art also appreciate that some devices which are not conventionally thought of as "computers" nevertheless exhibit the characteristics of a mfRiter" in certain contexts, Where such a device:is performing the functions of a "computer" as described herein, the term "computer" includes such devices, ..
to that extent.
Devices of this type include but are not limited to: network hardware, print servers, tile servers, N AS and SAN, load balancers, and any other hardware capable of interacting with the systems and methods described herein in the matter of a conventional "computer."
[0521 Throughout this disclosure, the term "software" refers to code objects, program logic, command structures, data structures and definitions, source code, executable and/or binary files, machine code, object code, compiled libraries, implementations, algori thins, libraries, or any instruction or set of instructions capable of being executed by aiicomputer processor, or capable of being converted into a form capable of being executed by a computer processor, including without limitation virtual processors, or by the use of run-time environments, virtual machines, and/or interpreters. Those of ordinaty skill in the art recognize that .ftare can be wired or embedded into hardware, inchiding without limitation onto a microchip, and still be considered "software" within the meaning of this disclosure. For purposes of this disclosure%
software includes. without limitation: instructions Stored or storable in RAM, ROM, flash memory BIOS, CMOS, mother and daughter board circnitry, hardware controllers, USB
controllers or hosts, peripheral devices and controllers, video cards, audio controllers, network cards. BluetoothTM and other wireless communication devices, virtual memory, storage devices and associated controllers, firmware, and device drivers. The systems and methods described here are contemplated to use computers and computer software typically stored in a computer-or machine-readable storage medium or memory, [053] Throughout this disclosure, terms used herein to describe or reference media holding software, including without limitation terms such as ''media,' "storage media," and "memory,"
may include or exclude transitory media such as signals and carrier waves.
[054] Throughout this disclosure, the term 'network" generally refers to a voice, data, or other telecommunications network over which compUterS communicate with each other.
The term "server" generally refers to a computer providing a service over a network, and a "client"
generally refers to a computer =easing or using a service provided by a server over a network.
Those having ordinary skill in the art will appreciate that the terms 'server"
and "client' may refer to hardwate, software, and/or a combination of hardware and software, depending on context, Those having ordinary skill in the art will further appreciate that the terms "server"
and -client" may refer to endpoints of a network communication or network connection, including but not necessarily limited to a network socket connection. Those having ordinary skill in the art will further appreciate that eserver') may comprise a plurality of software and/or:
hardware servers delivering a service or set of services. Those having ordinary skill in the art will further appreciate that the term "host" may, in noun form, refer to an endpoint of a network communication or network. :(co , remote hose), or may: it: verb fdittn,:
refer to SeNtt providing a service over a network ("hosts a website"), or an access point for a Service OVO:11 network, [0551 Throughout this disclosure, the term "real time" refers to Sofware operant* Within operational deadlines for a given Oent to enromenee or complete, or for a:
given module, :Software, or system to teSpond, and generally itivOkes that the ieSpOrtse ot:perforitiance time is, in ordinary user perception and considered the technological Context, effectively generally cotemporaneous with a reference event. Those of ordinary skill in the art understand that "real time" does not literally mean the system processes input and/or responds instantaneously, but rather that the system processes and/or responds rapidly enough that the processing or response time is within the general human perception of the passage of real time in the operational context of the program. Those of ordinary skill in the art understand that, where the operational contextia:tt graphical user interface "real ante normally implies a response time of no more than one second of actual time, with milliseconds or microseconds being preferable However, those Of ordinary skill in the art also understpd that, under otberppOrational contexts a:system operating in 'real nine" may exhibit delays longer than one Second, particularly where network Operations ate involved, [050 Throughout this. disclosure the term "transmitter refers AO equipment:, or a: set Of equipment, having the hardware, circuitry; and/or software to generate and transmit electromagnetic waves carrying messages, signals, data, or other information, A transmitter may also comprise the componentry to receive electric signals containing such messages, signals, data, or other information, and convert them to such electromagnetic waves. The term 1$
"receiver" refers to equipment, or a set of equipment, having the hardware, circuitry, andior software to receive such transmitted electromagnetic waves and convert them into signals, usually electrical, from which the message, signal, data, or other information may be extracted.
The term "transceiver generally refers to a device or system that comptises both a transmitter and receiver, such as, but not necessarily limited to, a two-way radio, or wireless networking router or access point. For purposes of this disclosure, all three terms should be understood as interchangeable unless otherwise indicated; for example, the term "transmitter should be understood to imply the presence of a receiver, and the term "receiver" should be understood to imply the presence of a transmitter.
[057} Throughout this disclosure, the term "detection network" refers to a wireless network used in the systems and methods of the present disclosure to detect the presence of biological mass interposed within the communications area of the network. A detection network may use general networking protocols and standards and may be, but is not necessarily, a special-purpose network. That is, while the nodes in the network could be deployed for the specific purpose of setting up a wireless detection network according to the present invention, they need not be and generally Will not be. Ordinary wireless networks established for other purposes 'nay be used to implement the systems and methods described herein In the preferred embodiment, the detection network uses a pIntality of BluetoothT" Low Energy nodes, but the present disclosure is not limited to such nodes. Each node =acts as a computer with an appropriate. transmitter And receiver for communicating over the network. Eazh of the compilers provides a uniqiie identifier within the network whenever transmitting a message such that a receiving computer is capable of discerning from where the message originated.
Such message origination information will usually be critical to the functioning of the invention as described in this detailed description. The receiving computer then analyzes the incoming signal properties, including but not limited to, signal strength, bit error rate, and message delay.
The detection network may be a mesh network; which means a network topology in which each node relays data from the network.
[058] Throughout this disclosure, the term "node refts. to a start point or endpoint for a network communication, generally a device having, a wireless transceiver and being a part of a detection network. Nodes ate generally:Standalone; :self-contained networking devices, SOO as Wireless routers, wireJess access:. points, short-range beacon, and so forth..
A node may be 0 Amer4l-pulpoS.0 device or la special-purpose device configured for use in a detection network as described herein. By way Ofetattiple and not limitation, a node may be a device having the Wireless transmission capabilities of an off-the-shelf wireless networking device with the addition of specialized hardware, circuit(y, tomponentry, or programming, for implementing the systems and methods described herein; that is, for detecting significant changes to signal properties, including but not limited to, signal strength, bit error rate, and message delay.
Within a detection network, each node can act as both a transmitter of signal to the network, as well as a receiver for other nodes to push information. In the preferred embodiment, the nodes utilize BluetoothTM Low Energy (BILE ) as a wireless networking system.
[059] Throughout this: diSebstittõ, the term ',Omni nods" refers to something happening at an ongoing t,taiS over time, Whether such events are mathematically continuous or discontinuous.
The gene-ray accepted mathematical definition of "continuous function"
describes a:. function which 15 WithOut holes :Or jumps, generally described by tworsided limits. The technology described herein is based upon disturbance* to a telecommunicatiOns system, in Which the transceivers transmit at discrete intervals,: and the received raw data is taken discretely. Lo, at discrete time intervals. The resulting data ik itself may be discrete in that it captures the characteristic of the system during a particular observation window (i.e., the time interval), in a physical or mathematical sense, this mechanism is essentially a set of discrete data points in time, implying a discontinuous function. However, in the context of the technology, one of ordinary skill in the art would understand a system exhibiting this type of behavior to be "continuous" given that such measurements are taken at an ongoing basis over time, [060] The measurable energy density signature of RF signals is impacted by environmental absorbers:and rellettOrs Many biolOgiCal masses suelvas humans, are mostly water and act:as significant energy 0:hsott:ters Other attributes Of people such as clothing, jewelry, internal OrgallS, etc all further impact the measurable RF energy denSity. This is particularly true where RF communication devices are transmitting over relatively short distances less than 50 ineterS), such as I3hietootlim, 892,154 (Zi,04, Thread); 00 Z-WaVe transceivers. A
human who passes through the physical space of the network Will cause signal absorption and disruption. Due to relative uniformity in size, density, and maSs=
composition, human bodies can cause characteristic signal absorption, scattering, and measurable reflection. Changes in signal behavior and/or characteristics are generally referred to herein as "Artifacts." Such phenomena are particularly useful in the Industrial, Scientific, and Medical (ISM) bands of the RF spectrum, but are generally observable in bands beyond these, [061] In an RF communication system comprising! a transmitter and receiver separated in space,: Signals receiVed by the receiver from a given transmitter are made up of energy from the original transmitted message whicti has arrived at the receiVer. Objects generally in the tratigniSsiOn path will affed the ehaototetiSties of ultimatO Op* which arriVesat the receiver.:
[062] Communication ostems are:generally designed to handle such issues and still faithfully reproduce the Message from the transmitter. Since humans generally exist, 0s far as RF
communications are impacted, as: mass of water :4 one such Observable difference between human *Settee and absence in a detection network is signal absorption by' the human_ Generally, the closer to the transmitter or receiver, the more significant the absorption is likely to be.
[063] Generally, it is envisioned that humans will produce artifacts in a detection network in.
a somewhat predictable manner, which can be detected or identified programmatically by detection algorithms. Further, artifacts may be cross correlated across the network to determine an estimated position of the object cansing the. artifaCt. The accuracy of this estimation may vary with the algorithms Otosenlconttincted, and with the equipment ttsed in the individnal system.
[064.1 For: each given algorithm which is. Choteniconstructed, the system May build such detections as a combination of a baseline signal profile with no human present in the detection area and *triple baseline signal data with a human present in the detection area NOW itie0itiOg sample baseline signal data may be compared against both the known sample baseline signal data and the baseline signal profile to determine the presence or absence of humans in a space.
[065] Short-range low power communication networks typically operate using signals in the 2.4G11z, frequency band, which is notable for being well-within the energy frequencies humans have been observed to absorbõks indicated, a human body physically interposed in a detection network absorbs and/or reflects at least some of the signals transmitted between and among nodes. However, other effects may :also take place, such As forward and backward scattering_ Utilizing the collection of data in a detection network without a human present to establish A:
baseline, futtne elements pf dat4 for statistically :OignificOOt differences typically exhibited by the physical presence of one or more humans, whether or not the one or more humans is moving, the detection network makes the determination as to the pretence or absence of humans within the network [066] Depending on the communication network itself hardware used, and the human, those changes may register within the network in different ways and produce different results;
however, such changes are detectable. This differs from radar technologies in that detection of the object does not necessarily rely or depend upon only signal reflection, but often rather the opposite principle signal absorption which is detected via measurable changes in signal characteristics between a transmitter and receiver in different physical locations.
[0671 By analyzing the change in signal characteristics between nodes within the network, the position of a disruptor and e.g., a human body can be calculated relative to the network.
Because the mere presence of the body is sufficient, this system does not necessarily include a fiducial element, and it need not rely on motion or movement. Because no fiducial element is required, the systems and methods described herein may provide an anonymous location data reporting service, allowing for the collection of data concerning traffic, travel routes, and occupancy without requiring additional components or devices to be associated with the bodies being tracked. Generally speaking, the systems and methods described herein operate in real time.
[0613] FIG. 1 is a schematic diagram of a system and method according to the present disclosure. In the depicted embodiment (101) of FIG. 1, a detection network (103) comprising a plurality of nodes (107) is disposed within a physical space (102), such as a room, corridor, hallway, or doorway. In the depicted embodiment of FIG. 1, an indoor space (102) is used, but the systems and methods described herein are operable in external environments as well. In the depicted embodiment, a node (107A) is communicably coupled (111) to a telecommunications network (115), such as an intranet, an internet, or the Internet. A server computer (109) may also be communicably coupled (113) to the telecommunications network (115) and thereby with the connected node (107A). The depicted server (109) comprises programming instructions for implemenfing the systems described herein, and carrying out the method steps described herein. However, in an embodiment, the functions performed by the server may be performed by one or more nodes (107) having, the appropriate software/programming instructions, or being appropriately modified.
[069] hi the depicted embodiment ofIFIG. T., each of the nodes (107) is communicably connected with at least one other node (107) in the detection network (103)3 and may be communicably connected to two or more, or all of the other nodes (107) in the detection network (103):: Fotekanapie,, hi a typical wireless network deployment strategy, :a plurality of **less access points is placed througliout the physical space (102), generally to ensure that high-quality signal is available everywhere. These nodes (107) Collectively form a detect*
network (103) and may transmit data to One another, or may transmit only to a router or set of touters. In the depicted embodiment of FIG. 1., node (107A):is wireless router, And the other nodes (107B), (107C) ati.d (1(i71)) are wireless acceSs pOints. However, this isjust: one possible configuration. Further, it is not necessary that any given node (107) be a particular type of wireless device. Any number of nodes (107) may comprise a router, access point, beacon, or other type of wireless transceiver. Further, any number of nodes (107) may be present in an embodiment, though a minimum of two is preferred. More nodes (107) in a space (102) increases the amount of data collected (as described elsewhere herein), thus improving the chance that a human is generally interposed between at least two nodes (107), improving the lOtAtion resolution_ [070] In the ordinary eddrse:Of operation, the nodes (107) frequently Send and receive wireleSS
tratigniSSiOns. For ocample, when aWit*Ss router (I 07A) reteives a data packet; the wireleSS
router (107A) typically broadcasts a witeless transmission containing the packet. This means that any receivers! Within the broadcaSt radius Of the w ter ,(107A): can receive the sig,nal, *better Or not:intended for them LjkeviiSei: wben an access point receives local data, such data is likeWiae broadcast and can be detected by other access points, and the router. Even4hen no user data is actively transmitted on the network, other data is frequently transmitted. These other transmissions may include status data, service scans, and data exchange for functions of the low-level layers of the network stack.
[071.] Thus, each node (107) in a typical detection network (103) receives transmissions on a consistent basis and, in a busy network, this effectively may be a continuous basis. The detection network (103) may thus be used to calculate the existence and/or position of a biological rums (104) or (105) physically interposed within the transmission :
range of the network (03). Because the presence of a human body impacts the Characteristics of signals transmitted between or among nodes (107) within the network (103), such presence Can be detected by mom tot Mg for changes in Well characteristiea, This detection May tilSo be performed while the data in the data packets being transmitted and received is still being transmitted and received; that is, the detection is incident to ordinary data exchange: be(Ween or among two or more nodes, which continues regardless of the detection.
Specifically, the wireless network may operate to transfer data between nodes, while simultaneously using characteristics of how the data packets incorporating that data have been impacted by the presence of an object in the transmission path, to detect and locate the object [072] In the depicted embodiment of F1G. 1, at least one node (107) monitors the communication signatures between itself (107) and at least one other node (107) for statistically significant changes in signal characteristics nven while it awaits, receive*, and/or transmits communications between itself and other nodes (107) The particular geometry of the physical space, (02), including the pt*.4e.tve and 1OCation of fixtures in the physical enyirotitnerit, generally does not impact the :system because the monitoring is for statistically significant c/hinge in signal characteristics indicating or iciencim; the character *s of a human. That a change in signal characteristics is attributable to a:Change in absorbers or reflectors, like human bodies, in the physical environment Of Communication space covered by the detection network (103). The detection of the presence of a human within the detection network (103) may be done using statistical analysis methods on the signal, such as using sensing algorithms, as described elsewhere herein. Again, this does not require the human to be associated with a :Uncial element, or in motion. Instead, the detection network (103) deteets tbat Characteristics of the network communication have changed because a new object (which is generally a human object) has been introduced in the communication space and the presence of that object has caused a change to the characteristics of the network:: communications, typically data packets,i between nodes (107).
[073] To detect a :change, generally a baseline of signal characteristics is developed =againat :Whichirecent ly transmitted si griala ar ompm-ed. These characteristiCa:are derived from typical WireleS$ COMM LirtiOatiOJI netWor k diagnostic inforrnati On .............
This baseline of si gn I charac.eTiStics:
between nodes (107) is generally established prior to the use of the detection network (103) 04 deteetbr, This may be done by operating the. detection network (103) under typical or normal circumstances, that is with the detection network (103) communicating data packets, with no significant biological mass interposed in the physical broadcast space of the detection network (103)_ For an amount of time during such operation, signal characteristics between and/or among nodes (107) are monitored and collected and stored in a database. In an embodiment, the server (109) will receive and store such data, but in an embodiment, one or more nodes (107) may comprise hardware systems configured to receive and/or store such data.
[074) for ekample,*here 4hode (1W) contains special purpose hardware and prOg,ramming for Use according to the ptoaot disclosure, such node 0071 may 4:Grp its Own signal characteristic data. Such. lai characteristic data may be data relating to the received energy characteristic of signals received by a particular node (107) from one or more other nodes (107.).:
The baseline data establishes for each node (107) a signature characteristic profile, Which is essentially a :collection of data defining the typical and/or general characteristics Of signals received by the node (107) under ordinary operating circumstances where there is no significant biological mass interposed in the detection network (103). The node (107) may have one or more of such profiles for each other node (107) from which it receives data.
[075] In an embodiment, after the baseline signatures have been detected and collected, the detection network (103) will generally continue to operate in the same or similar fashion, but is now able to detect the presence of a biological mass. This is done by detecting and collecting additional signal. characteristics, generally in real-time, as the detection network (103) operates in a normal mode of transmitting and receiving data packets. These newly generated real-time signal characteristic profiles are also generally characteristics of signals between two particular nodes (107) in the detection network (103), and thus can be compared to a corresponding baseline signal characteristic profile for the same two particular nodes (107). A statistically significant difference in certain characteristics between the two profiles may then be interpreted as being caused. by the presence of a significant biological mass, such as a human.
[076] The comparison operations may be performed by appropriate hardware in a given node (107), or the real-time signal characteristic profiles may be transmitted to a server (109) for processing and comparison. In a further embodiment, both are done so that a copy of the real-time data is also stored and accessible via the server, effectively providing a history of signal characteristic profiles.
[077] This is because, as described herein, a biological mass interposed within the network will generally cause at least some signal characteristics between at least two nodes to change when a data. packet is transmitted which intercepts and/or generally interacts with the biological mass. The degree and nature of the change generally will be related to the nature of the particular biological mass interposed (e.g., the size, shape, and composition), and its location in the network (1.03). For example, where a housefly flies through the detection network (103), the amount of signal change may be so minor as to be indistinguishable from natural fluctuations in signal characteristics. However, a larger mass, such as a human, may cause more substantial and statistically significant changes in sham! characteristics.
[078] Such changes may not necessarily manifest in all signal. characteristic profiles for the detection network (103). For example, where the mass is interposed at the edge of the detection network (103), the nodes (107) nearest that edge are likely to experience statistically significant signal characteristic changes, whereas nodes on the opposing side of the detection network (103) (*hose signals to each other do not pass through. or around the biological mass), are likely to experience few or no statistically significant changes. Thus, if the physical locations of the nodes (107) are also known, the system can determine not only that a biological mass is present in the detection network (103), but calculate an estimate of where it is located, by determining which nodes (107) are experiencing changes and calculating the magnitude of those changes.
[0791 This can he seen in the depicted embodiment of FIG. 1, In FIG. 1, assuming the presence of only one human ¨ either A (104) or B (105) ¨ is present at a time for simplicity, A
(104) would generally have a greater impact on the signal characteristics between nodes (107C) and (107A) than between nodes (107A) and (107C). FurtherõA (104) would also generally have a small bidirectional effect on the signal characteristics between nodes (107B) and (10713). By contrast, 8 (105) would have a bidirectional impact on the signal characteristics between nodes (107A) and (107C), as well as on the signal characteristics between nodes (1079) and (1071)).
[0801 While all nodes may be communicating with one another, the effects of A
(104) and B
(105) will generally be more negligible on communications where A (104) and/or B:(105) are not generally in line with the communications path between nodes. For example, neither person (104) or (105) is likely to seriously impact transmission between nodes (107A) and (1079) because neither person (104) or (105) is in the transmission path between those nodes.
However, A (104) may have an impact on transmissions between nodes (107C) and (10713).
[081] It should be noted that the presence or absence of a biological mass within the communication area of the detection network (103) will not necessarily result in any change in data communication. It is expected that the detection network (103) will utilize its standard :existing protocols, means, and methods (including all forms of retransmission and error checking) to make sure that the data in the data packets being transmitted is correctly received, processed and acted upon. In effect, the detection process of the detection network (103) is performed in addition to the standard data communication of the detection:
network [082] it should he recognized from this that the data in the data packets being pOmmunicated by the nodes (107)in the detection network (103) generally Will not be directly used to detect the biological mass within the communicatiOn area of the detection network (I03). Instead, the data will simply be data being communicated via the detection network (103) for any reason and will Wien have nothing to do with detection of the biological mass.
Further, while this disclosure generally contemplates packetized communication in the form of data packets, in an alternative embodiment, the data may be continuously communicated in a non-packetized form, [083] In an embodiment,,,iitt Order W. allow the detection network (103) to detect the presence or absence of a particular biological nut0.., the system includes a training ..:aspect or step This aspect may comprise, after the baseline is established, one or more humans are deliberately interposed in the network at one or more kvations in the network, and one or more additional ,tets of baselim data ate eollected and stored. This second baseline may be used for comparison purposes to improve accuracy in detecting the Size, Shape, andlOt other characteristics of 11 biological mass interposed in the network, and/or for improving the accuracy of location determination. Such training may use supervised or unsupervised learning, andlor may utilize techniques known to one skilled in the art of machine learning, [0841 hi an embodiment; adetection oetwork (103) may useaispecialized protocol comprising a controlled messaging structure andlor format, which can be controlled from one node (107) to another (107), making it simpler and easier to determine from which node (107) a message originated; and allowing for control of aspects Such as the composition of the Signal sent, transmitted signal strength, and signal do,ation. Such control !flother facilitates certain improvements in prOc es s n& and facilitates receivers i den t fyi lig and using certain signal finalities and/or characte,ristios particular to the detection:aspects of the network: 0931 which may differ from general networking aspects sharing the same network (103).
With control of the message sent and received on the opposing sides Of the mass being located, it is not necessary to send a signal as .à scan, nor to sweep a region in space, :as such functions tend to require significantly more expensive equipment than is needed for typical broadcast or directional transmission between nodes (107). Messages are generally constructed in such a way as to best produce usable data for detection algorithms which would be constructed to function best with the communication network they are being used within, Generally, such constructions still avoid the need for waveform level analysis of the signals sent by the network.
[085] In the depicted:embodiment, each node (107) generally is. able to determine the Origin 040 (197) :of packets received by such node (1107). Such message :Origination information: is:
:typically encoded within the *Osage =itself,: as would be ltnewn to one skilled in :communications networks. Byway of example and not limitation, this may be done by eXamining data embedded in established protocols M the nettm?orking stack, or by eXmnining data transmitted by the sending not* (ton for:* specific purpose of implementing the Systems and methods described herein. Typically; :each node (107) haS
appropriate hardware and processing capability for analyzing the messages received, While many different topologies and messaging protocols would allow for the functionality described herein, generally mesh networking topologies and communication methods will produce usable results.
[086] FIG. 2 depicts an embodiment (201) of a method according to the present disclosure and should be understood in conjunction with the system of FIG. I. In the depicted embodiment, the method begins t 203) with the establishment 1.203) of a detection network (103) comprising a plurality of communication nodes (107) according to the present disclosure As would be known to one skilled in the art of setting, up communication systems, there are many different approaches to the setup of such a network (103) and many different network (103) topologies may prove viable within this framework.
[087} Next, a digital map in memory may be generated (205) indicating the detection network's (103) physical node (107) geometry, The detection algorithms described herein generally use information about where in the physical environment (102) the nodes (107) are deployed. Data about such physical location of the nodes (107) may be supplied manually to an accurate diagram of the physical network environment (102), and/or software could be used to automatically generate a relational position map of one or more nodes (107) within the detection network (103), facilitating eager placement of the nodes (107) into such an environment map or diagram.
[088] Altermtively, nodes (107) may be placed on a blank or empty map or diagram using relational (as opposed to absolute) distances for detection. In such a dimensionless system, messages could still be generated from the algorithms related to the detection of humans in the system (1.01), and additional manual processing may be included, such as user input concerning which messages are sent related to the presence and/or movement of humans within the network (103).
[089] In an embodiment with automatic node (107) location detection, node (107) locations are detected algorithmically and/or programmatically by one or more nodes (107) and/or a computer server (109), based upon fattors such as, but not necessarily limited to: detection network (103) setup and configuration, including physical location of specific hardware components such as nodes (107) and each node's (107) location relative to one or more other nodes (107); signal strength indicators; and, transmission delay. In the depicted embodiment, this step (205) further comprises overlaying the generated map on a digital map of the physica1 space (102) or em ronment (referred to helvin as an "en v ro n men t map") the dewetion network (103) occupies, such as floor plan of a building. This step (205) may further and optionally comprise a sealing element to align the scales of the generated map to the environment map, as well as user-manipulated and/or modifiable input elements for making adjustments to fine rune the generated map so that it more doSely conforms to the actual node (107) deployment geometry, as would be understood by one of ordinary skill in the art. In an alternative embodiment, each node (107) may be manually placed in its appropriate location on the environment map without using a relative location algorithm.
[090] Either way, this step (205) establishes the physical locations of the nodes (107) in the detection network (103), which will facilitate determination of the location of interposed biological masses attributable to the presence of humans within the detection network (103).
By placing the nodes (107) on a map (either through manual or automatic means), the nodes (107) trad the presence of a human in thenetwork (103) based on how the baseline signal affects communication between various nodes (107). The system (101) then utilizes information collected about the signals which arrive at the receivers, given a transmitted set of information known to the data processing algorithm. The data processing algorithm is what ultimately determines whether a human is present within the network (103) and/or where within the network (103) that human is located.
[091] Next, messages are constructed and exchanged (207) in a lomat, and according to a protocol, determined to be suitable for detecting the presence of a biological mass within the network (103). While this may be done using general purpose networking protocols known in the art, such as protocols in the OSi network model, or special-purpose protocols which replace, or supplement, such general-purpose protocols.
[092] Generally, it preferred that this step further comprise controlling and/or modifying (207) messages passed within the detection network (103) for the specific purpose Of detecting human presence and facilitating simplified statistical analysis. By controlling (207) message exchange, the system (101) can adjust for a. common content being sent through the detection network (1.03) while also facilitating adjustment of parameters including, but not necessarily limited to: transmission intervals; transmission power; message length and/or content; and, intended message recipient(s). Again, the system does not necessarily rely on waveform level analysis, allowing operation within the confines of wireless communication standards.
[093] Controlling (207) such parameters facilitates the development of statistics and/or analytics, which may be based at least in part on pre-defined or anticipated message content or characteristics. Such content and/or characteristics may include, without limitation, transmission timestamp and/or transmission power level. By controlling and modifying (207) these aspects, one may overcome hardware limitations, including hardware features which cause unwanted consequences when used in a detection 'network (103) according to the presence disclosure, such as but not necessarily limited to automatic gain control (AGC) circuits, which may be integrated into certain receiver hardware in a node (107).
[094] Next in the depicted embodiment (201), the space (102) is cleared (209) of significant biological mass - notably humans (205); Then, a statistical baseline -of signal strength is developed (211) locally by each node (107). Again, by placing-the nodes (107) on a map in step (205), whether through manual and/or automatic means, the nodes (107) can track the presence of a human in the network (103) based on how the baseline signal is affected for communication between nodes (107).
[095) Next, a biological mass enters (213) the detection network (l03), causing signal absorption and other distortions, which manifest in changes in signal characteristics between nodes (107). These changes are detected (215) and analyzed (217) to determine whether the changes are indicative of the :presence of a human, or of another type of biological mass the detection network (103) is configured to detect. Such detections are further localized at least to an area between nodes, such as within an interior area between three nodes on the network, but possibly with greater accuracy depending on the algorithms and hardware being in use at the time.
[096] Generally, this is done using detection algorithms executed either hone or more nodes (107) or by a server computer (109). The nodes (107) and/or server (109) use software to estimate the location of the detected biological mass in the detection network (103) using one or more detection algorithms. Such algorithms generally compare the baseline profile to newly detected signals, and may also use or be based upon various data and other aspects, such as, without limitation: detection network (103) setup and configuration, including physical location of specific hardware components such as nodes (107) and each node's (107) location relative to one or more other nodes (107); signal strength indicators; and, transmission delay.
[097] Generally speaking, as described elsewhere herein, these algorithms include comparing newly gathered signal characteristic profiles (215) to baseline signal characteristic profiles (211) to identify a change and determine whether, based on the nature of the change, the change is indicative of the presence of a human. This determination may be done at least in part using training data developed through machine learning As described elsewhere herein.
[098] In an embodiment, the detection algorithms may further comprise the use of observed signal characteristic change(s) between one or more pairs of nodes (107) in the detection network (103), correlated in time and relative effect. These factors facilitate the identification of a physical location in the detection network (103) where such a signal change took place, allowing for an estimate of the ph vsical location o f the human causing such signal characteristic change(s), which in turn may be used to estimate a physical location in the detection network (103) environment where the biological mass is interposed. Such physical location may be provided as simple x, y, z coordinates according to a coordinate system, or may be vistuilly indicated, sad) as on the map_ [099] Where multiple humans are present in the detection network (103), separating out the impact of the various individuals from one another is more difficult, and accuracy will generally improve with the addition Of more nodes (1071. In an embodiment, techniques such as advanced filtering and predictive path algorithms may be used to separately detemiine location of individuals within the network (103). Although movement of the.
human in the network (103) is not required for the systems and methods to operate properly, movement, or lack of movement, may be used to improve detection accuracy, such as by predicting the path of a single individual. This can help identify instances where an individual has, statistically, "disappeared" from the detection network (103) but the system has sufficient data to estimate that the individual is still present in the network (103).
[0100] For example, where an individual's movement path has been predicted, and terminates next to another detected individual, the system (101) may determine that the two individuals are loo close together for signal characteristic profile changes to separately identify them, but since the individual's movement path was not determined to have taken the individual out of the network's (103) detection range, the algorithm detemilnes that the individual is present, and not moving, in dose proximity to another detected human. Thus, when one of the two proximate, stationary humans moves, the algorithms may again separately identify each one, and resume predicting path based on observed signal characteristic profile changes.
[0101] in this way, the systems and methods according to the present disclosure can track one or more individual humans within a network (103), whether or not moving, and whether or not any $1.1Ch humans are associated with a fiducial element.
ldentifying::specifie individuals may further be done using other path prediction and sensing algorithms, such as but not necessarily limited to those used in the robotics industry for human-following technology, in order to estimate which human was which. It:should be noted that individuals may impart specific and unique effects on y0.6(10 signal characteristics, :allowing for the identification of a Specific individual, and further allowing for one specific individual to be distinguished from others.
Such effects may be used. to further determine the location of specific individuals within the detection network.
[0102] The detection: algorithm(s) are generally :constructed to take advantage Of the characteristics of communication signals; Considering factors such as, but not necessarily:
limited to, frequency of the signal(s) and the transmitted power levels of the signal(s). in an embodiment, the algorithms detect human presence using data-driven methods for determining the effect of the presence of a human on signal characteristics in the RI' environment within the communication network, and then identifying when that effect is later observed.
[0103] For example, in an embodiment, a signal characteristic which varies with the presence of a human body is:the:..Signal strength registered between nodes (107). This is particularly the :case Within a BLE network, and the statistics related to signal Strength over time May indicate the presence of a human within the network, These artifatts may. be used by the Oetectio0 algorithm(s) to provide information about the physical location of the object causing the artifact. The is. by combining various statistics about artifacts captured across the network (104 the system determines 'N'here in physical space (102) the artifact is located, and thus.
Where a human is the network (103).
[0104] In the simplest use case, the algorithms may simply identify 011.000$
in signal characteristics which are similar to changes known (e.g.õ from training) to be caused by the presence of a human, and simply trigger a detection event (219) whenever such changes relative to a baseline are detected_ This may appear like an adjustment of mean, standard deviation, skewness, or variance in the signal strength depending on the system (i01) used, When the detected signal characteristic profile returns to a profile similar to the baseline, it can be inferred that the physical environment 0,02) hag :returned to an empty state with respect to whether a human is present [0105] Elaborating on the simplest use case, the baseline profile in this case Comprises some or all baseline profiles which exist when a space doeS not contain any humatiSaod may vary depending on physical adjustments to that space: Simpler algorithms, Which may account for the changes associated with a newly detected human :Change relative to :a recent baseline, can be used to address such situations; however, in the event that the baseline has changed, it is preferred that the system accurately determine whether one or more current signal profiles matches an empty baseline profile, or matches a profile one that represents some degree of occupancy. Such determinations may be made in response to movement, but it is preferred that they be not made in response to movement, but rather based on whether the characteristics of such a signal can be correlated with one or more of the empty baselines or one or more of the presence:Signal profiles;
[0106] Compared to Other technologies used for,sucii. determinations (typically the Passive:
Infrared (PIR) :SOO:SOO,: Which require rnotion to function, the Systems and inethodS described herein are capable of detecting the presence of a static human within a space (102), whether or not in motion, and more precisely, detecting when a human is no longer in the space (102). For applications wen. aS security and OceOpanOy sensing, this System would be more difficult to trick. Some examples of tricks that may fool PER and other similar motion based technologies' include holding a sheet in front of a person while they enter a space, moving very slowly; or remaining generally motionless in an area after entering. Another benefit is that the system does not necessarily require additional hardware beyond that used in ordinary network communications. This is because the additional software and processing capability may be provided via external components or modifications to existing hardware, such as by implementing the appropriate software as a System On a Chip (SOC) attached to off-the-shelf communications modules.. It additional processing power is required, additional processing node(s) may be added to analyze the signals propagated between nodes (107). or the workload may be transmitted to and handled by a dedicated server machine (109)õ
[0107] Making determinations of human presence andfor location may be related to the particulars of the signal type being analyzed, and controlling the signal sent between nodes (107) on the network (103) to best achieve those detections. By sending controlled communication pulses through the network (103) where the original signal is known and the transmitted power can be modulated, it is possible to develop exemplary data related to signal absorption, reflection, backscatter, etc. due to additional humans between the nodes (107).
Since it is generally assumed that a baseline system can be configured without the presence of a human and that such a baseline would look statistically different than with a human present, it can further be assumed that signal characteristic changes would be due to the presence of a human in the network. By allowing for the input of timers and generally configuring. the system to refine the baseline definition \ then a space (102) is empty, the system may tcalibrate itself periodically to achieve improved accuracy. Generally speaking, tracking algorithms make use of the best available triangulation calculations combined with statistical methods, as would be known to one skilled in the art of location technologies, coupled with the detection algorithms fOr detecting humans within the network (1 03)_ [0108] The present disclosure does not require a fiducial element associated with the human detected, nor does it require that the human be carrying any device capable of communicating with the network; however, such technology would take advantage of such elements should they be deployed within the system. The addition of such elements may ease the calculation burden on the system and allow for increased accuracy_ The systems and methods described herein do not preclude such additional functionality, and could be enhanced by it. Augmenting detection with an inference engine adds to the ability of the sensing hardware to recover from a false alarm situation or other edge case, thereby making the system more robust. Such an.
inference engine may further feed information into a machine teaming system, which may further modify the one or more baseline signal profiles or the one or more presence signal profiles to improve the performance of the system.
[0109] in an embodiment. a detection network (103) implementing the systems and methods described herein may further comprise elements for taking action (219) based on the detected presence and/or location of a human. This may be done, for example, by sending control signals over the network using the computers to first determine the presence and/or location of a human on the network, and then to determine an action to take based on the presence and/or location of a human on the network, and to send a message over that network to take that action. Since the communication network and the network performing the detection may be the same network, the invention described herein extends the traditional functionality of a communication network to include human detection andlot location sens i w th out requiring additional sensing hardware.
[0110] The computer elements on the network necessarily perform additional calculations and may craft communication signals. This may ease the calculation burden on the computers;
however, the network may still function IS a command and control network, independently of the network. as a detection network.
[0111] The system as a whole can be used for a wide variety of applications, ranging from occupancy sensing, as might be used thr lighting control and/or security, to counting the number of people in a space as might be needed for a heat and/or traffic map, to a system that tracks individual humans moving through a space_ The technology may be integrated into the network nodes themselves, or may be a combination of nodes transmitting information, to a processing element (either directly on the network Of in the cloud) to perform the calculations to determine the desired information. The final integrated product suite may be customized for an application, and could be used in a variety of different ways.
[0112] No additional sensor is required t though, in an embodiment, one may be present), and the detections are effectively made through calculating statistics from the traditional RF
communication stack Such a system prevents the collection of personal data from the people walking through the space as the system only knows that an approximately human-sized mass of water, organs, clothing, etc, has passed through, and does not require any separate device to act as a fiducial element. As such, the technology represents a significant departure from traditional methods for tracking humans moving through a space.
[0113] A logical extension of the systems and methods described herein comprises dynamically handling functional network messages within the statistical analysis so as to avoid Of reduce additional messaging overhead for the system, It is also contemplated that, in an embodiment, the systems and methods described herein are extended to comprise dynamic adjustments to network and/or message structure, configuration, and/or operating parameters based at least in part on functional messages transmitted within the network.
[0114] Further, because the tracking is based on signals being affected by what is generally a human mass, the system. is not reliant on the human moving around for detections. By not relying on movement, many of the shortfalls with traditional presence sensing technologies, such as passive infrared and ultrasonic sensing technology, are overcome, [0115] The utilization of a communication network's signals between nodes to detect the presence of humans in the network where the human does not carry a fiducial element is a radical departure from current non-fiducial element detection methods and makes use of communication networks to perform presence sensing in an entirely new way. The combination of detection techniques and utilization of network nodes as transmitter receiver combinations for the purposes of performing human presence detection presented herein constitute a new type of human presence detection system which does not require additional equipment beyond that which is required to form the communication network itself.
[01 16] The systems and methods described herein may be implemented in a communication network without influencing the operation of the network itself for purposes of ordinary communication. The network continues to operate as a communications network as its primary function, but some of the communications are used in this case to calculate the position of a human existing in the network, Because the systems and methods described herein utilize basic operations of a network, a human within the network additionally carrying a transceiver device known to the network may be detected and located with increased accuracy. Such a transceiver device, which may comprise, for example, a mobile computing device having a wireless transceiver, such as a cell phone, mobile phone, smart phone, tablet computer, wearable computer technology, and so forth, may connect to the network and be locatable by the network using traditional triangulation methods known to one skilled in the an.
Machine learning algorithms may also be applied when a person carries such a transceiver, which may in turn further improve performance.
[0117] The location calculation of a known transceiver device. may be compared with the location of the person as determined by the non-transceiver aspects described herein. With the = communications network teponing both the location of the fiduciii.
dl'tlierit as well as the human within the net the locations of those two can be compared, Since it is generally the case that the detected location of a fidncial element has a higher degree of fidelity than the estimated location of the human based on network communications alone, the location calculations for the position of the human within the network can be adjusted using machine learning algorithms so as to improve the location calculation capabilities:Of the system 'for the next human entering the network.
[0118] Using machine learning algorithms, the system can: improve the accuracy of location predicting Algorithms based on the kribUlt: location from the ttangetiver.
This May allow for -verification of prior determinatiOns, and refining of fungai:d0terminationa.
For etamp e, if it i$
found that prior determinations are consistently off by about the same amount, that amount may be applied to future determinationS RS an adjustment In this Way, the system can continue to improve and train itself to better locate the humans within the network.
Similarly, machine learning can continue toin-iptoVO the detection and false guilt: rate. By toy of *ample and not limitation, data concerning prior traffic patterns at a facility can be used to establish defaults, presumptions, or expectations concerning the range of times or days during which a particular facility is generally occupied or generally empty. Such data can be used by the system to improve its performance.
[0119] Additionally, the system is configured to make or draw inferences, such as based upon physical interactions with network elements; that is, devices or components attached to or communicating with the network:that ate :operable by Or operate based upon the presence Ofa butp.00, such as net*ork,operable elettrioal switches, doors notion settkitS., infrared senors, and the like. Such p4y*al interactions may beetinsidere0 fidueial elements at the paint in time that they Are interacted with for the purposes of the system. ,As an example, if a light ,switch that is part of the network is actuated, the system may infer that a human was present at or near the physical location Of the switch at the time the s-witCh was actuated AS suck the:
system could use that information as a known data point examining signal characteristics of the various network devices at that point of time with the inferred knowledge that those characteristics reflect a human at a particular location near the switch) to which it could apply machine learning to better make predictions of human presence in the future, Additionally, such events could serve as -presence triggers for other purposes such as security alerts. As an example, say that the system is in a security mode and someone has found a way to mask their presence but still interacts with a switch, then the system would be able to determine that someone was present and send an alert: based on the interaction with the switch. Generally speaking, interaction ith the system wOuld be defined both physically and logically Where logical interaction 'Would. !tkie typical lisage patterns based on time, ontsidt. inputs et Such a System servesais backup to the RE' presence Sensing and provides additional machine learning Capabilities, to the syStem.
[01201 Additionally, the system can estimate whether :a Mobile transceiver in the network is actually being carried by a human or nOt; Such as where a human leaves :a device in a location in the network. Because the system can detect the human as a biomass through changes in signal characteristics, the system can detect whether a transceiver is present in the network while a human biomass is not. This inhibits false training of the system and facilitates the avoidance of baseline and presence signal profiles being corrupted by data not correlated with such profiles, [0121] In an embodiment,IS Iftither input to the inference engine., &Wine indication of the System changes states and a human Within the detection area behaves in such a manner as To torrealhe :sy0ettl state, the ay$teith may infer that it *mid adjust its baseline and presence profiles to better reflect:user preferences. Byway of example, if the lights in a space AVere to turn off with a human in the spat*, Said human may engage in behavior to reflect presence,:
SOO as physically movmg way* arms, and so fortkotgimpiy .looking for:or:walking tolkartts a wall switch. This movement may be detected Within some reaSonable amount of time, and the system may determine that it incorrectly determined that the space was absent, and adjust its baseline and presence profiles accordingly. Such activities may be referred to as inferring the presence of one or more humans in a space.
[0122] As a side effect of collecting various signal characteristics and being capable of running them through various algorithms, the system is capable of running multiple detection calculations simultaneously to achieve different performance criteria with the same system. As an example, the same communication network can be used for detections associated with lighting and security; however, the gathered statistics can be processed differently, but simultaneously, for the two applications. In this way, the lighting application can still provide for a shorter time to detect, but with a potentially higher &Ise alarm. rate, while a security application, can trade a slightly longer time to detect while reducing the false alarm rate. The signal characteristics to be processed by the system may vary by application, but all are captured from the communication network and can be processed in multiple ways simultaneously. Such processing methods may be encapsulated in multiple sets of different sample baseline signal data for determining detections relative to a baseline signal profile.
[0123] In an embodiment of a system according to the present disclosure, the system comprises a communication system which is capable of determining the presence of one or more humans from information about the wireless signals between two or more computers on the network where each computer consists of a transceiver thr communication; and a computing element for performing calculations, where each computer sends signals to one or more other computers on the network where the signal includes a unique identifier of the computer sending the signal;
where each computer processes the signals received for the purposes of determining the presence of one or more humans; and where the one or more humans are not required to have on their person any device capable of communicating with the network..
[0124] In an embodiment of such a system, the algorithms use statistical methods to determine the presence of one or more humans. In a further embodiment of such a system, the statistical methods determine the number of people present. In another further embodiment of such a system, the system is capable of determining the physical location of the one or more humans on the network In a still further embodiment of such a system, the system is capable of tracking the physical location of the one or more humans over time. In another further embodiment of such a system, the system uses information about the presence of one or more humans to control devices on the network. hi an embodiment, the network is a mesh network.
[0 125] In an embodiment, the computers determine their relative physical locations and further determine the relative physical location of the one or more humans on the network, In a further embodiment, statistical methods are applied to a measure of signal strength to determine the presence of a human. In a further embodiment, the transmitted signal is controlled for making detecting human presence easier, in a fluffier embodiment, the power level of the transmitted signal is controlled for making human presence easier. In a further embodiment, the system functions as an occupancy sensing system. In a further embodiment, the occupancy sensing;
system controls a lighting system. In a further embodiment, the network for controlling the lighting system and the network used for occupancy sensing utilize the same communications technology and hardware. In a further embodiment, the communications technology employed by the computers is chosen from the list of BiuetoothTM SLow Energy, WiFi, Zigbee, Thread, and ZAN' ave.
[0126] In a further embodiment, the system functions as a sensing system Ibr a security application. In a further embodiment, thesecurity sensing system controls the Security System.
In a further embodiment, the network thr.controlling the security system and the network used for security sensing udlize the same communications technology and hardware.
In a further embodiment, the system functions as a human detector for robotic systems. In a further embodiment, the robotic systems have computers which locate various elements of the robotic system relative to one another dynamically. In a further embodiment, the network for controlling the robotic systems and the network for functioning as the human detector for the system utilize the same communications technology and hardware.
[0127] In a further embodiment, the system functions as a sensing system for a HVAC
application. In a further embodiment, the HVAC sensing system controls the HVAC system.
In a further embodiment, the network for controlling the HVAC system and the network used for HVAC sensing utilize the same communications technology and hardware.
[0128] In another embodiment, the system uses machine learning to improve its detection capabilities where humans which have a tiducial element on their person train the system through: (1) using known location techniques to determine the location of the fiducial element;
(2) using the system described above to locate the person; (3) comparing the location calculated by the method of (1) of this paragraph to the method 01 (2) of this paragraph;
(4) adjusting the location determining methods using machine learning algorithms to improve the location calculating capabilities of the system.
[01.29] In another embodiment, the system may infer the presence of humans in the network based on those humans interacting in some way with one or more of the computers on the network. In a further embodiment, the system may use the inferred presence of a human as an.
input for machine learning to improve its detection capabilities.
[01301 In an embodiment of a system according to the present disclosure, the system comprises a communication system which is capable of determining the presence, both static and moving, of one or more humans from information about the signals between two or more computers on the network where each computer consists of: a transceiver for communication;
and a computing element for performing calculations, where each computer sends signals to one or more other computers on the network where the signal includes a unique identifier of the computer sending the signal; where each computer processes the signals received for the purposes of determining the presence of one or more humans; where the one or more humans are not required to have on their person any device capable of communicating with the network.
[0131] In an embodiment, the algorithms use statistical methods to:determine the presence:of one or more humans. In another embodiment, the statistical methods determine the number of people present. In another embodiment, the system is capable of determining the physical location Of the one or more humans On the network. In another embodiment,: the System:: is opable of tracking the physical location Of the One or more humans over time.
En another embodiment, the system uses information about the presence of one or more humans to control devices on the network. in another embodiment, the information about the presence of one or more humans is made available to one: or More Systems not directly :inyOlved in the determination Of presente. In another: embodiment the system haS the abiki to per** self., optimization to achieve a given perfOrmance :according to one or more preset criteria.
[0132] In another embodiment, the communications protocols or network is generally defined by a standards committee including bin not limited to protocols such as Bluetoothml LOW
Energy, Win, Zigbee, Thread, and Z-Wave. In another embodiment, statistical methods are applied to a measure of received signal strength to determine the presence of a human. In another embodiment, the transmitting and receiving devices on the network may be selected and actnated by the system for the purpose of making human detection easier In another embodiment, the power levet of the tranSmitted signal May be controlled for making human presence egOer. In another embodiment, the::s-sisterrt: functions 0: an Neupancysensing system for a lighting system. In another embodiment, the occupancy sensing system controls a lighting system. In another embodiment, the network for controlling the lighting system and the network used for occupancy Sensing utilize the same communication technology and hardware.
[0133] In another embodiment, the system functions as a Oii.Otig system for a security application. In another embodiment, the security sensing system controls the security system.
In another embodiment, the network for controlling the security system and the network used for security ::sensing utilize the same communications technology and hardware. In another embodiment, the system functions as an occupancy sensor for a Heating.
Venting, and Cooling (HVAC) system. In another embodiment, the occupancy sensing system controls the HVAC
system. In another embodiment, the network for controlling the HVAC System and the netWork used. tbt occupancy sensing: utilize the same communications teem-3010g and hardware.
[0134] In another embodiment, the Systent iiks machine learning to improve its detection capabilitieS *here humans which have, a fiducial element on their person train the system through:. (1) using known location techniques to determine the lOcati on of the fiducial element;
(2) using the system :to *ate the 1)et's0ii.; (3) comparing the location calculated by (1) Of this paragraph to (2) of this paragraph; (4) adjusting the location determining methods using machine learning, algorithms to improve the location calculating, capabilities of the system.
[0135] In another embodiment, the system may infer the presence of humans in the network based on those humans interacting in some way with one of the computers on the network. Said interactions may be direct physical interactions or indirect interaction in response to some change of state in the system (e.g., waving arms in response to lights turning off). In another embodiment, the Osten" MO use the inferred presence Of a human as an inptit:for machine learning to improve its detection [0136] Also described herein is communication system which is apable Of determining the presence, both static and moving, of one or more humans in a detection network based on information about the Signals between two or more computers on the network where each Computer -e0risiStS Of 4 transceiver for communication; and, a coinputiq element for performing calculations, Where each computer sends Avid to one or: more :Other computers on the network where the signal includes a unique identifier of the computer sending the signal;
where each computer will process the signals received for the purposes of determining the presence of one or more humans in two or more ways to achieve different performance criteria as required to function for two or more purposes simultaneously; where the one or rnore humans are not required to have on their person any device capable of cornmunicating with the network, [01371 In an embodiment, the algorithms use two or more statistical methods to determine the presence of one or more humans according to two or more sets of performance criteria. In another embodiment, the system has the ability to perform self-optimization to achieve a set of two or more performances according to two or more preset criteria. In another embodiment, the conimunications protocols or network is generally defined by a. standards committee including but not limited to protocols such as luetornhTM Low Energy, WiFi, Zigbee, Thread, and Z-Wave. in another embodiment, two or more statistical methods are applied to a measure of received signal strength to determine the presence of a human according to two or more sets of performance criteria. In another embodiment, the system uses machine learning to improve the detection capabilities of the two or more methods for determining presence where humans which have a fiducial element on their person train the system through: ( I) using known location techniques to determine the location of the fiducial element; (2) using the system to locate the person; (3) comparing the location calculated by (1) of this paragraph to (2) of this paragraph; (4) adjusting the location deteimining methods using machine learning algo[ it hms to improvd.thd location.calculating capabilities Of the syStetn, [0138] n an embodiment, the systems and methods described herein include change detection.
By way of example and not limitation, chat= detection may use or utilize a rolling baseline approach. In such an embodiment, a first baseline is established and compared with a second baseline, and any. differences between the first and second baselines caused by the presence of a human in the detection network may be recognized by the system. This may be done by programming software to receive sets of wireless signal characteristic data from one or more nodes in the detection network and, based on such data, detecting changes in the RI' environment caused by a human being present in a different position when thefirstbaseline is established as compared to the second baseline. Such methods may be utilized when a system is first setup in a location to establish a minimal performance level without requiring a space be empty upon startup:: Such Vaal-lg. With Change detection may improve Overtime to a State between change and presence where limited aspects Of presence :detection may be present in such a system.
[0 139] An exemplary illustration of change detection is depicted in FIG 3A, In the depicted embodiment of :FIG:. 3A, the RIF' enViromni.nit Of FIG. 1 is shown with, a human (301) present in the erivirontnent (103) at a discreet position 303'l M.:(iesCribed elsewhere in this disclosure, the charadteristics of Wireless Signal transmissions among the nodes (107A)16 (107D) is influenced by the presence of the human (301). In this particular example, transmissions between node A (107A) and node D (107D) are influenced by the presence of the human (301 ).
Thus, when the baseline is established (211) as shown in the method of FIG. 2, the baseline represents the wireless signal characteristics while the human (301) is present at the discreet position (303). If the human (301) moves to a new position (305), as can be seen if FIG, 3A, the. characteristics OfWireless signals among the nodes (1 07A) to (107D):Will change.
[0140] In this particular exemplary ern bod merit: therev:Vill be little interference between nodes:
A:(L07A) and D (107D) when the human is at position (305). HoWever, there will be greater interference between nodes B (107B) and C (107c),: because the position:(305) is disposed between those two nodes. Thus, when the differences are detected (205) as shown in FIG. 2, the change in position:of the latitilan can be detected.
[0141] nit is I.eSS difficult to implement than presence sensing because the heed to establish baselines in the detection network (103) without a human present is reduced.
Such a system may detect changes within the detection network (103) based primarily on when a human changes positions, and updating the operative baseline profile on a rolling basis. That is, the baseline:(211)is updated in this embodiment to be equal to the baseline when the human (301) is at position (305). Thus, when the human (301) moves to a third position (307), the differences detected (215) are as between the second baseline taken at position (305) and the wireless sigma characteristics of detection network : (103) when the human is at position (307) Likewise; the baseline (21 1) has been updated to be equal to the baseline in position (307),: Which can then be used to detect further tbanges M the position of a human (201). This detection method uses changes in the wireleSii$Ipial baselines (*wed by changes in the position of a human (01) in the. detectiOn (103). This system has many advantage. over prior art motion detection technologies, such as passive infrared, in that this system is not obscured by objects 0.0t4i#
detect Slow Of gradual changes in position, which may be overlooked by prior ail Systems. in an embodiment using this methodology, the baselines may be continuously updated.
[01412] In another embodiment, the system or method comprises making a confidence determination. This aspect may determine a degree of confidence that a third baseline corresponds to either a first or second set of baselines, The confidence determination may use any number of techniques, including techniques known in the art, such as supervised training or the use of statistical methods to determine a degree of similarity or difference. between data sets. The confident* May increase Or decrease esVer.: ,time, allowing for decisions to be auton*ticoUy:olade, *th reSpectle baseline differences that are minimally different, but may still indicate the presence of a human in the detection network 003):
Confidence in a determMation of presence or abscmce of a human in the detection network (103):
may be determined based on how similar a third baseline is to a first or second baseline. For example, if a third baseline is known to: indicate the *Sent of a mass whose impact on signal characteristics is known, comparing the first or second baseline to the third may improve (or decrease) the confidence level that the identified mass is the same as the mass identified in the third baseline. Based on confidence, the system can be configured to use different confidence thteShORIS in different operational contexts (e.g:, HVAC, security, lighting, .safety, etc), A
system or method including a confidence determination may operate across a plurality of systems using a common communication system, wherein the systems can include disparate nodes in communication with one another. A given node May operate in a plurality of detection networks (103), allowing for better system scaling when deploying. the systents and methods to multiple adjacent detection networks (103).
[0143] In another embodiment, baseline diMrences may be used to count or estimate the number of humans present in the detection network. In an embodiment, this may be done by estimating the amount of human mass in the detection network, and dividing by an average mass per person. This may be done by establishing a first, empty baseline when there are no humans in the detection network (103), and establishing a second, occupied baseline when some known number of humans are present in the detection network (103). Next, a third baseline is taken and compared to the first empty baseline and the second occupied baseline_ The system software then interprets where the third baseline wireless signal characteristics fit on a spectrum of profiles between the first empty baseline and the second occupied baseline, and from that determination estimate the total amount of human mass in the detection network This estimation may be based upon the total mats of humans in the detection network when the second occupied baseline was established.
[0144] By way of example and not limitation, if the signal distortion in the third baseline is moderate as compared to the first empty baseline, the system may estimate that the amount of human mass present is relatively low. However, if the amount of signal distortion is closer to that shown in the second occupied baseline, the system may determine that the estimated amount of human mass present in the detection network (103) is closer to the amount that was present when the second baseline was taken. Similarly, if the amount of distortion is determined to be even more extreme than that reflected in the second baseline, the system may determine that the total amount of human mass present when the third baseline was taken exceeds the amount present when the second baseline was taken. The estimation of human mass may be based broadly upon the algorithms and methods described herein, and adjusted to estimate a number of humans in a space as generally described above.
[0145] In another embodiment, a system uses entrance and exit signatures in network diapostic information to estimate the number of humans present in a space based upon such signatures.
[0146] In such a method, an entrance profile is established by a human entering a space, an exit profile is established by a human leaving the same space, and another later-captured profile is compared to the entrance and exit profiles to determine whether a human has entered or exited the space. Entrance and exit profiles are learned through normal system operation, based upon estimation from the presence detection technology and its determination following a state change. By way of example and not limitation, if a system detects a change and presence goes from not being detected to being detected, such an event may be classified as an entrance.
Similarly, by way of example and not limitation, if the system detects a change and determines that a space has gone from occupied to unoccupied, such an event may be classified as an exit.
The difference between entrance count and exit count may be used to estimate the number of humans present in the space.
[0147] In another embodiment, a. system uses entrance and exit signatures in network diagnostic information in combination with people count estimates derived from comparing a sample profile against presence profiles of varying people counts.
[0148] Each of these methods may be used in anti unction with one or more counting methods to enhance the accuracy.
[0149] In an embodiment, the count or estimate of humans present in the detection network::
(103) may be used to operate another system, such as, hut not necessarily limited to, a HVAC, system, [0150] In an embodiment, the location or poSitiOn a a human in the detection netWOrk, IS:
estimated. This may be done by estimating the range between various devices to determine the location of a human,: examining subset detection areas Constructed from higher numbers of nod*: using various location baselines,: and further extending the fiinction of a location system to analyze locations Over time to estimate speed and direction. of a human in the detection network. In one embodiment: Of such a method, the system .to4y: use VatiOns :node pairs, estimating the, position of a human between those pairs based on baseline information, Wine overlapping estimates within the node pairs, then determining a highest probability position for a human in the detection network based on those overlapping estimates to determine the actual location of the human.
[0151] In another embodiment, systems with larger number of nodes can use more subset detection areas, generally each with three or more nodes, to determine the presence or absence of a human in each space, and estimate location based. on overlapping occupied areas wherein the common occupied space might be assumed to be the most Specific WOO .o.r a human in the deteetiOn netwOrk. By way: Of example and not limitations Set of fOttr nodes may be subdivided into four sets of three nodes, where location maybe determined based upon which :subsets of three nodes presence is detected within. This sub-area creation allows for detections within subareas where Such sub-shapes are defined by overlapping:. areaS
(treated With sets of three Or more nodes. Alternatively, a plurality Of baselines for humans in different locations within a detection network may be established, with subsequent baselines compared against said baselines to determine the location within the detection network of a human. By way of example and not limitation, a detection profile play be created for various locations within a detection area where a given detection profile corresponds with a human in a given position within the network, a sample profile is compared against a set of detection profiles corresponding to different positions, the system determines which detection profiles correlate most with the sample profile, and the system makes a determination of the location of the human based on the location of the detection profiles deemed most similar to the sample profile.
[0152] Additionally, based on detected changes in locations of humans in the detection network over time, a human's travel speed and dirtvtion in the detection network may be estimated. This may be done, for exampleõ through the use of interpolation and dead reckoning, or direct reconnaissance. An exemplary embodiment of such a system and method is depicted in FIG, 3B, In the depicted embodiment, a human is located in a detection network (103) at position (401) at Timeo. At a subsequent point in Timei, the Human is detected at a different position (403). Because position (401) and position (403) are known, a Distance' between them can be calculated. Additionally, the amount of time elapsed from Time to Time can be determined or is known. Given that distance equals rate times time, the rate of movement of the human from position (401) to position (403) can be determined.
Additionally, a Vector could be determined representing the movement of the human, embodying both direction and magnitude (speed).
[0153] Having oily twc, sample points,. however, faise,s the possibility of a high error rate, and more than two sample points is desired. For example, in the depicted embodiment, a third profile taken at Time, places the human at position (405). Again, the Distance2 from position (403) to position (405) can be determined, and arate of speed between these positions may also be determined. In the depicted embodiment, these positions are generally linear, suggesting that the human is rfloviriR in a more or less straight line in a given direction, defined by Vector.
The system may thus further estimate the future or expected position of the human based on this data, That is, at Times an estimated position (407) of the human may be determined based on the prior detected locatiorm This estimate may place the human outside of the detection network (103), and may be further used to estimate the arrival or departure of a human in or from the detection network (103). Additionally, this information may be used to alert another segment of the detection network, or another detection network entirely, of a:potentially soon to be arriving human, This may be done, tir example by communications using the computer server (109) via the network (115).
[0154] Continuing the Owmplary embodiment above, in the depicted embodiment, the human's detected change in position from Timer to Timei Js 0. meters %eters it one secoti,i. for a speed :of .8 meters per second. 'fhe detected change in distance fitoti Timei to Tim 02 is meters, with one additional elapsed second, or, 2.0 total meters Over twO
total elapsed seconds, for an average speed of one meter per second. Thus, at Times, one second later, an additional one meter of movement may be anticipated, making the estimated future position (407) one meter further along Vector than position (405).
[0155] In an embodiment, the systems and methods use machine learning to further train the system over time. By way of example and not limitation, a system may accumulate data from one or more of the above.-described Change detection techniques using a combination of knOwt feedback and/or feedhatkfrOm third pattySystenis:sOch as hut nOt limited to interactions With:
other Smart deviceS:(thermostatSõ: yoke recognitiol:sy#00$; 00. andlor ttse inference icer time to improve operation based on expected or anticipated system behavior.
Such inferences may be based upon ordinary behavior in a space: direct human interaction with elements of the system, :Or Sample:profile changes from human reactions to system decisions.
By Way of example and not limitation, in a ,s,Stem implementing change detection to operate lighting or HVAC systems, user feedback may be provided to the system as supervised training data, indicating whether a given operation was correct (i.e., whether a change in the lighting or I-1VAC system should have been made or not).
[0156] Similarly, hi a system implementing presence detection; a ,t1Ser may force change detection to trigger while within a detection network, providing the system an automated means to establish a baseline practice for the occupied space based upon the time that change riggerinlevenis occur and, faCilitating times far removed from change triggering events to be detected ag generally otopty When cOnibined with infecting OcCupancy based on roOtn: type,, such a I nethod may facilitate he system training itself, improving fortetibmdiiy over time from change detection to presence detection level functionality. Effectively, by using the system based on change detection, the system may infer presence and absence, allowing it to establish baseline profiles for when no tOiltn is present and detection: profiles based on When there is a human present. In such a way, the system would be capable of training hell to move from operating as a change detection system into one operating as a true presence detection system, [0157] In an embodiment implementing counting, combinations of change detection and presence detection may determine an estimated count of humans within a detection network, estimating such counting baseline profiles and improving them over time. Such a system may thcilitate the system training itself over time to count the number of humans within the detection network [0158] In an embodiment implementing, locating people, Combinations Of Change detection, prOsen(e detection, and counting people may be utilized to determine eStnnateS
Of location based on overlapping areas and occupancy counts eventually establishing more accurate baseline !eatirnateS, ollowing the system over time to improve Tocatina humanS
Within lA
detection netµVork. Such a sy!nem may comprise an inference :
Such as computer = Software running on the serVet; and/or build an estimation of expected system operation from normal operations, and may adjust operational parameters in accordance with expected behavior. For example, if a detection area is typically empty from I 0:00am until 3:00pm, and occupied from 3:00pm until 6:00pm, parameters may be adjusted to expect emptiness from 10:00aim3:00pm and to expect presence from 3:00pm until 6:00pr4 Such inferences may be:
developed over time and may improve performance at those times, while maintaining overall flex [01591 Nodes may be disposed in. various location combinations to improve system operation:
A system may Operate with nodes located on walls, ceilings, 'liked nodes, mobile nodes, and/or in mixed configurations. Because spaces are three-dimensional, detection areas may be defined by nodes on ditierent floors of a building. Nodes may be placed on wails in POsitiOns such as:
Switches and outlets. The broadcast range generally defines the perimeter :Of a detection areas and the system May be configured to exaMinenettyork. diagnostics aSstttning humans are within said perimeter.
[0160] In an embodiment, one or more nodes may be placed on a:ceiling. By way ofeXample and not limitation, this might occur when nodes are integrated into fixtures and/or lighting systems. in such an embodiment, nodes may radiate generally downward into the detection area, and a system may be configured to examine network diagnostics based on different radiation and multi-path patterns than might be seen from a switch and outlet based system. In such an embodiment, nodes generate communications:in:A generally dOgniWard direction where reflections from *ati$, objeot , and fit** generally ensure that the RI energy reaches other nodes yialmiltipath The multipath also generally provides for cOverage of the detection area, Such coverage due to multipath means that ceiling mounted nodes function similarly to wAli mounted nodes with regards to the impact Of a human on network diagnostic information.
[0161] Other fixed nodes are also contemplated, such as, Ottibilt televisions;
monitot*atid; smart home !nibs. Such nodes May be installed on A wall, ceiling, or at a fixed location. Still other nodes, such as smartphones, tablets, and laptop computers, may be used in a detection network as a mobile node. However, in such an embodiment, a mobile node may first locate itself relative to fixed nodes in the system_ Having its location established within the network may further enhance the accuracy of the system.
[0162] In an embodiment, combinations of nodes may be used in a detection area. When combining larger number of nodes, the system may determine the optimal nodes for operation.
Optimal nodes may be determined by, among other things, determining the most efficient nodes for a chosen level of functionality. As node count increases, accuracy of cletennimaion gem rally increases, as does level of functionality, [0.16:3] in an enibodi merit one. or more nodes may operate in a plurality of detection areas. This facilitates improved system scali ng, particularly for adjacent detection areas.. Such scaling may additionally result in inference within a larger network of nodes including the plurality of detection areas, further facilitating the tracking of human detections front one detection area to the next. For example, nodes may be shared between detection areas_ A given node in a first detection network may have network diagnostic information based on communications within said first detection area, and may also be part of a second detection network and have network diagnostic information based on communications within said second detection network, The system can make independent decisions on how to operate third party systems in each of the two detection areas. Examining inference across detection areas can improve the determination of the presote or absence of humans within the detection areas, particularly when. a person leaves one detection area and enters another. Detected changes in signal characteristics can be used to determine the presence or absence of a human in the individual areas, based on information shared between the first and second detection area [0164] In an embodiment, the systems and methods may operate through the use of a mass identification technique. In such an embodiment, a "mass" is identified and tracked. A unique identity may be assigned to the mass by the computer systems, and tracked based on changes to wire:less signal characteristics. By way of example, and not limitation, if a mass is first detected near the center of a room, and next detected at a location several feet away from the:
center of the room, but the system has not detected any other masses as entering the room, the system may infer that the second detected mass is the same mass as the first detected mass, but has relocated to a new position. Based on the difference in signal characteristics caused by the interference of the mass in the network, the system may infer, for example, that other Masse*
exhibiting similar movement would have similar effects on the signal characteristics. In this :way, the system can "leart" hp* to identify a mass, and track. it.
[01.45] Although each human mass in the system Causes different interference characteristics when disposed at any locatiOk for most indoor locations, the total set of humans likely to be present in a room is generally finite. That is most indoor spaeeSate, for any appreciable length of time, occupied by the same basic set of people most of the time, with only minor and infrequent variations. For example, the same set of people generally show up each day to a workplace, or a school, or even a public location such as a restaurant.
Because most indoor spaces can only be entered from a limited number of points of entry, such as doorways, the system can detect a person entering at the point of ingress, and determine the specific interference :pattern caused by: the presence of that particular human upon entering the spate.
Based on the signal characteristics (interference ) and the vvay that those characteristics Change = totripare4 to other hunlansin the *ee,it On be determined where and hoW
each human trfass:
moves through the room.
[0166] It is c.ontemplated that a system may automate varions aspectS Of setup, particularly:
with regards to grouping nodes: into detection areas and building levels of functionality nominally based on the machine learning methods described herein. A system Which determines nearest nodes and estimates detection areas through inference requires no setup by a user. Based upon best estimates, a user may simply place nodes throughout a building, and the nodes automatically group into detection areas using unsupervised machine learning, ultimately resulting in a building system learning, how to detect occupants, Occupancy can then be related to actions taken by occupants, developing an automation system which reduces or eliminates the need for human input for normal system operation, [01.67] In an embodiment, the method is a method for detecting the presence of a human comprising: providing a first transceiver disposed at a first location within a= detection area;
providing a second transceiver disposed at a second location within said detection area; a computer server communicably coupled to said firs t.nanseeiver; said first transceiver receiving a first set of wireless signals from said second transceiver; said computer ser,, er: receiving a first set of signal data from said first tmnsceiver, said first set of signal data.comprising data about properties of said first set of wireless signals; inferring that said first Set of signal data is indicative of the presence of a human in said detection area; creating a detection signal profile .fir wireless communications from said second transceiver to said first transceiver based at least in part on said properties of said first set of wireless signals in said first set of signal data when a human is inferred present in said detection area: said first transceiver receiving a second set of wireless signals from said second transceiver; said computer server:
receiving a second set of signal data from said first transceiver, said second set of signal data comprising data about properties of said second set of wireless signals; infening that said second set of signal data is indicative of the absence of any humans in said deteetion area; creating a baseline signal profile for wireless communications from said second transceiver to said first transceiver based at least in part on said properties of said second set of v,eireless signals in said second set of signal data when the absence of any humans in in said detection area is infermd; said rust transceiver receiving a third set of wireless signals from said second transceiver; said computer server receiving a third set of signal data from said first transceiver, said third set of signal data comprising data about properties of said third set of wireless signals;
determining whether said third set of signal data is indicative of the presence of a human, or absence of any humans, in said detection area, said determining based at least in part a comparison of said third set of signal data to said detection signal profile and said baseline signal profile, [0168] In a further embodiment, the method comprises: in said inferring that said first set of signal data it indicative of the presence of a human in said detection area, said inferring is based at leaStin part on additional Signal data Sets for signals received by said first transceiver from other transceivers in the detection area; and in said inferring that said second set of signal data is indicative Of the absekeof any humans in said detection area, said inferring is based at least in part on additional Signal data sets for signals received by said first:
transceiver from other transceivers in the detection area.
[0169] In a further embodiment, the method comprise: Said Computer Server;
Storing aplurality of historical data records indicative of whether a human was determined to be present in said detection area over a period of time, each of said historical data records comprising an indication of a number of humans determined to be present in said detection area and a date and time when each of said number of humans was determined to be present in said detection area; and said computer server making at least some of said plurality of historical data records available to One Or more edema] computer systems Via an interface, [0170] In a Anther embodimeOt:The method cotnpriSek Said computer s'erver IS
operatively COUPled to a:SecOnd system; and otflyafterSaid computer seryer:determinesa homan is present in said detection area, said computer server: operates said second system.
[0171] In a further embodiment, the method comprises: said tirst transceiver and said second system are configured to communicate using an identical eommunicationprotbea [0172] In a further embodiment, the method comprises: Said second sySteM is Selected from the group consisting of: an electrical system; a lighting system; a heating, venting, and cooling (11VAC) system; a security system; and, an industrial automation system.an electrical system.
[0173] In a further embodiment, the method comprises: said wireless communication utilizes a protocol selected from the group consisting of: BluetoothTM. BluetoothTm Low Energy, ANT, ANT+, WiFi, Zigbee, Thread, and Z-Wave, [0174] In a further embodiment, the method comprises: said wireless communications from said second transceiver to said first transceiver have a carrier frequency in the range of 850 MHz and 17,5 G Hz inclusive.
[0175] In a further embodiment, the method comprises: said computer server determining whether said third set Of signal data is indicative of the presence of a human includes a confidence metric.
[0176] In a further embodiment, the method comprises: said first transceiver and said second transceiver are configured to calculate their relative positions within said detection area automatically.
[0 177] In, another embodiment, the method comprises a method for estimating the number of humans present in an area comprising: providing a first transceiver disposed at a first location within a detection area; providing a second transceiver disposed at a second location within said detection area; a computer server communicably coupled to said first transceiver., said first transceiver receiving a first set of wireless signals from said second transceiver when no humans are present within said detection area; said computer server receiving It first set of signal data from said first transceiver, said first set of signal data comprising data about properties of saki first set of v,eireless signals; said computer server creating a baseline signal profile for wireless communications from said second transceiver to said first transceiver, said baseline signal profile being based at least in part on said properties of said first set of wireless signals in said first set of signal data when no humans are present in said detection area; said first transceiver receiving a second set of wireless signals from said second transceiver when a first plurality of humans is present in said detection area, said first plurality of humans having a total mass; said computer server receiving a second set of signal data from said lint transceiver, said second set of signal data comprising data about properties of said second set of wireless signals; said computer server creating a second baseline signal profile for wireless communications from said second transceiver to said first transceiver, said second 'baseline signal profile being based at least in part on said properties of said second set of wireless signals in said second set of signal data. when said first plurality of humans is present in said detection area; said first. transceiver receiving a third set of wireless signals from said second transceiver when a second plurality of humans is present within said detection area; said computer server receiving a third set of signal data from said first transceiver, said third set of signal data comprising data about properties of said third. set of wireless signals; said computer server estimating the total mass of said second plurality of humans, said estimating based at least in.
part on a comparison of said properties of said third set of wireless signals in said third set of wireless signal data to said baseline signal profile and to said baseline signal profile; said computer server estimating the total number of humans in said plurality of humans based at least in part on dividing said estimated total mass of said plurality of humans by an average mass per human.
[0178] In a further embodiment, the method comprises: said computer server estimating the total mass of said second plurality of humans is further based at least in part on a comparison of said properties of said third set of wireless signals in said third set of wireless signal data to said properties of said second set of wireless signals in said second set of wireless signal data.
[0179] :In a further embodiment, the method comprises: said properties of said first set of wireless signals, said second set of wireless signals, and said third set of wireless signals comprise wireless network signal protocol properties determined by said first transceiver.
[0180] In a further embodiment, the method comprises: each or said wireless network signal protocol properties is selected from the group consisting of: received signal strength, latency, and bit error rate, [0181] In a father embodiment, the method comprises: said 'computer server :estimating Comprises interpolating the total T1 14$ S of humans in said 'second plurality Of hair!**
[0182] in a further embodiment, the method comprises: said interpolating uses an assumed nias :of zero for said baseline signal profile and said total mass of humans in said first plurality of humans for said second baseline signal profile.
[0183] In a further embodiment, the method comprises: Said total MOS is a discrete user, supplied quantity.
[0184] T In a further embodiment, the method comprises: said average mass per human is 0 discrete user-supplied quantity.
[0185] In a further embodiment, the method comprises: said computer server storing a plurality of historical data records indicative of whether a human was present in the detection area over a period of time, each of said historical data records comprising an indication of a number of humans deeded in said detection area and a date and time when each Of said number of humans was detected in Said detection area, and said computer !.-lerVer Making at least some Of said plurality of historical data:records:n*1We to one Orrnore external cOmputet7systeois yin an interface:
[0186] In a further embodiment, the method comprises: said computer server estimating the total mass of said second plurality of humans is adjusted based on machine learning comprises:
determining a first sample total mass Of a plurality of humans having a fiducial element in Said detection area, said first sample mass being determined based upon detecting said fiducial element; determining a second sample total mass of said plurality of humans in said detection area, said second sample mass being determined based at least in part on a comparison of said received second set of signal data to said baseline signal profile; comparing said first sample mass and said second sample mass; and adjusting said estimation of said total mass of said second plurality of humans based upon said comparing.
[0187] In a further embodiment, the method comprises: said computer server estimating the total mass of said second plurality of humans is adjusted based on machine learning comprises:
determining a first sample total mass of a plurality of humans based on inferences in said detection area; determining a second sample total mass of a plurality of humans in said detection area, said second sample mass being determined based at least in part on a comparison of said received second set of signal data to said baseline signal profile;
comparing said first sample mass and. said second sample mass; and adjusting said determination of said second sample mass based upon said comparing.
[0188] In a further embodiment, the method comprises: said determining a .first sample location of a human based on inference in said detection area comprises said computer server inferring from a detected operation of a network element in said detection area that a human is present in said detection area near said network element.
[0189] In a further embodiment, the method comprises: said network component is a component of an electrical system, a lighting system, a heating, venting, and cooling (FIVAC) system, a security system, or an industrial automation systent [0190] In a further embodiment, the method comprises: n said estimating the total number of humans in said plurality of humans includes a confidence metric.
[0191] :In a further embodiment, the method comprises: said first transceiver and said second transceiver are configured to calculate their relative positions within said detection area automatically.
[0192] In a further embodiment, the method comprises: said Vvireless:communication utilizes a protocol selected from the group consisting of: BluetoothTm, BluetoodiTm Low Energy, ANT, ANT+, Wi Fi, Zigbee, Thread, and Z-Wave, [01931 In afather embodiment, the method comprises: said wireless cOmmunications from said second transceiver to Said firStlranscei vet have a carrier frequency in the range of 850 MHz and 1'7,5 Gliz inclusive.
[0194] While the invention has been disclosed in conjunction with a description of certain embodimentS; including those that are currently t*iieed to be preferred embodiments, the demi ied deseription is intended to be illustrative :add Siithild not be utWerStobd tOttit the scope of the present &Closure. As would be understood by one of ordinary skill in the art, embodiments other than those described in detail herein are encompassed by the present invention. Modifications and variations of the described embodiments may be made without departing from the spirit and scope of the invention.
[007] The following is a summary of the invention in order to provide a basic understanding of some aspects of the invention. This summary is not intended to identify key or critical elements of the invention or to delineate the scope of the invention. The sole purpose Of this section is to present some: concepts of the invention in a simplified form as a prelude to the more detailed description that is presented 'a ter.
[00$1 Because of these and other problems in the art, there is described herein, among other thing* :is a method for detecting the presence of a human comprising:
providing a first transceiver disposed at a first position within a detection area; providing a second transceiver disposed at a: second location within the detection area a computer server commtuneably coupled to the first transceiver; the first transceiver receiving a first set of wireless signals from the second transceiver via the wireless communications network; the computer server receiving a first set of signal data from the first transceiver, the first set of signal data comprising data about the properties of the first set of wireless signals, the property data being generated as part of ordinary operation of the first transceiver on the communication network;
the computer =server creating a baseline signal profile Ito communications from the Second transceiver to the firs tanseeiver, the baseline signal profile being basect at least in part on the witeiess properties thOreceiVed first Set Of Signal data, and :t7epreSenting characteristics of wireless transmissions from the second transceiver ts3 the first rransceiver when no human is present in the detection area; the first transceiver receiving a second set of wireless signals from the second transceiver via the wireless eo.mmunicationa tietWOrlr, the computer server receiving a = second set Of Signal data from the first transceiver, the second set of signal data comprising data about the properties of the second set of wireless signals, the property data being generated as part. of ordinary operation of the first transceiver on the communication network; and the computer server determining whether a human is present within the detection area, the determination based at least in part on a comparison of the wireless signal properties in the received second set of wireless signal data to the baseline signal profile.
[009] In an embodiment of the method, the first set of signal properties comprise wireless /*Mak signal protocol properties determined by the first transddiva.
[0 0] In another embodiment Othe method, the wireless network signal protocol properties are selected from the group consisting of: received signal strength, latency, and bit error rate.<
[0 II In another embodiment of the method, the method further comprises:.
providing a third transceiver disposed at a third location within the detection area; the first transeeiyer receiving a third set of wireless sign* from the third tranSCei*eit Oa the Wireless cemniarticationS
network; the computer server receiving a third set of signal data from the firSt transceiver, the third set of signal data comprising data about the properties of the third set of wireless signals, the property data being generated as part of ordinary operation of the first transceiver on the communication network, the computer server creating a second baseline signal profile for communications from the third transceiver to the first transceiver, the second baseline signal profile being based at least in part on the wireless signal properties in the received third set of Signal data, and representing characteristics of wire less from the third transceiver to the :first transceiver when no human is present in the detection area; the first transceiver receiving a fourth set Of wireless signals from the third transceiver via the wireless :communications network', the computer server receiVing a fourth set of signal data: from the first transce.iver, the fourth sot of signal data comprising data abOut the properties of the fourth set Of wireless Sign*, :the property data being generated as part of ordinary operation of the first transceiver on the communication network; and in the determining step, the computer server determining whether a human is present within the detection area based at least in part on a comparison of the wireless signal properties in the received fourth set of wireless signal data to the second baseline signal profile.
[0121 in another embodiment of the method, the determining step applies statistical methods to the second set of wireless signal data to determine the presence of a human.
[0131 In another embodiment of the method, the method further comprises: the computer server continuously determining the presence or absence of a human within the detection area, the determination based at least in part on a comparison of the baseline signal profile to signal data comprising data about the properties of the first set of wireless signals received continuously at the computer server from the first transceiver; and the computer continuously updating the baseline signal profile based on. the continuously received signal data when the continuously received signal data indicates the absence of a human in the detection area.
[0141 In another embodiment of the method, the method further comprises: the computer server determining the number of humans is present within the detection area, the determination based at least in part on a comparison of the received second set of signal properties to the baseline signal profile.
[015] in another embodiment of the method, the method further comprises: the computer server determining the location of one or more humans within the detection area: the determination based at least in part on a comparison of the received second set of signal properties to the baseline signal profile.
[0161 In another embodiment of the method, the method further comprises: the computer server being operatively coupled to a second system; and:only after the computer server detects the presence of a human in the detection area, the computer operates the second system.
[0171 In another embodiment of the method, the detection network and the second system are configured to communicate using the same communication protocol.
[0181 In another embodiment of the method, the second system is an electrical system.
[0191 In another embodiment of the method, the second system is a lighting system.
[020] i In another embodiment of the method, the second system is .::a heating, venting, and cooling (FIVAC) system, [021] In another embodiment of the method, the second system is a security system.
[021] In another embodiment of the method, the second system is an industrial automation system [023] In another embodiment of the method, the wireless communication protocol is selected from the group consisting of: Bluetoothm, BlnetoothTM Low Energy, ANT, ANTI-, WiFi, Zigbee, Thread, and Z-Wave.
[024] in another embodiment of the method, the wireless communication network has a carrier frequency in the range of 850 MHz and 17,5 Gliz inclusive.
[025] In another embodiment of the method, the determination whether a human is present within the detection area is adjusted based on machine learning comprising:
determining a first sample location of a human having a fiducial element in the detection area, the first sample location being determined based upon detecting the fid.ucial element;
determining a second sample location of the human in the detection area, the second sample location being determined based at least in pan on a comparison of the received second set of signal data to the baseline signal profile not utilizing the fiducial element; comparing the first sample location and the second sample location; and adjusting the determination step based on non-fiducial element location to improve the location calculating capabilities of the System, the adjusting based upon the comparing step.
[026] In another embodiment of the method, the determination whether a human is present within the detection area is adjusted based on machine learning comprising:
determining based on user input or action that a human was present in an area when the sample signal properties correspond at least in part with baseline signal properties of an empty space, modifying, at least In part, the baseline signal properties for an empty space; modifying, at least in part, the signal properties associated with an occupied space; and adjusting the method for comparing sample signal properties to the baseline and other comparative signal properties to improve the accuracy of the system over time.
[0271 In an embodiment of the system, the user input or action which provides presence data is provided directly to the system in some form including, but not limited to, physical switches, smartphone input, or auditory cues.
[028] In an embodiment of the system, the user input or action which provides presence data is provided indirectly to the system in some form, such as deliberately Changing the signal profile to counteract a decision being taken by the system, such as providing such a change during a dimming phase in a lighting system.
[029] In another embodiment of the method, the method further comprises: the computer server storing a plurality of historical data records indicative of whether a human was present in the detection area over a period of time, each of the historical data records comprising an indication of the number of humans detected in the detected area and the date and time of when the number of humans was detected in the detection area; and the computer server making the historical data records available to one or more external computer systems via an interface.
[0301 Also described herein, among other things, is a method for detecting the presence of a human comprising: providing a first transceiver disposed at a first position within a detection area; providing a second transceiver disposed. at a second location within the detection area;
providing a computer server communicably coupled to the first transceiver;
providing a first external system operatively coupled to the computer server; providing a second external system operatively coupled to the computer server; the computer server receiving from the 'first transceiver a set of baseline signal data comprising property data about the signal properties of a first set of wireless signals received by the first transceiver from the second transceiver when no human is present in the detection area, the property data being generated by the first transceiver as part of ordinary operation of the first transceiver on the communication network;
the computer server creating a baseline signal profile for communications from the second transceiver to the first transceiver when no human is present in the detection area, the baseline signal profile being based at least in part on the property data representing characteristics of wireless transmissions from the second transceiver to the first transceiver when no human is present in the detection area; the computer server receiving from the first transceiver a first set of sample baseline signal data comprising property data about the signal properties of a second set a wireless signals received by the first transceiver from. the second transceiver when a human is present in the detection area, the property data being generated by the first transceiver as part of ordinary operation of the first transceiver on the communication network; the computer server creating a first sample baseline signal profile for communications from the second transceiver to the first transceiver when a human is present in the detection area, the first sample baseline signal profile being based at least in part on the property data in the first set of sample baseline signal data, representing characteristics of wireless transmissions from the second transceiver to the first transceiver when a human is present in the detection area; the computer server receiving from the first transceiver a second set of sample baseline signal data comprising property data. about the signal properties of a third set of wireless signals received by the first transceiver from the second transceiver when a human is present in the detection area, the property data being generated by the first transceiver as part of ordinary operation of the first transceiver on the communication network; the computer server creating a second sample baseline signal profile for communications from the second transceiver to the first transceiver when a human is present in the detection area, the second sample baseline signal profile being based at least in part on the property data in the second set of sample baseline signal data, representing characteristics of wireless transmissions from the second transceiver to the first transceiver when a human is present in the detection area; the computer server receiving: from the first transceiver a third set of sample baseline signal data comprising property data about the signal properties of a fourth set of wireless signals received by the first transceiver from the second transceiver when a human is present in the detection area, the property data being generated by the first transceiver AS. part Of ordinary operation of the first trattaceiver Q.11 the 0:n1'110i:0*i netWork; the cot Niter servOdeteonining to Operate the first external system based upon the computer SONO determining that the property data in the third Set of sample baseline Signal data:corresponds to the first sample baseline signal profile; the Computer server determining not to operate the Second external system based upon the computer server determining that the property data in the third set of sample haSeline signal data does not correspond to the secktaid sample baseline signal profile, [031] In an embodiment of the method, the determination to operate the first external system and the determination not to operate the second external system is adjusted based on machine learning comprising: determining a first sample location of a human having a fiducial element in the detection area, the first sample location being determined based upon detecting the fiducial element; determining a second sample location of the human in the detection area, the second sample location being determined based: at least itipatt on a comparison of the received second set of :signal data to the baseline signal profile not utilizing the fiducial element;
COniparing the fit* sample location and the Second Sample lOcation; ,a.ncl adjusting the determination stops based on non-fiducial element location to improve the location calculating capabilitieg of the system: the adjusting based upon the comparing step.
[032} In another embodiment of the method, the determination to operate the Org.: external system and the determination not to operate the second external gS;,Stem is adjusted based on machine learning comprising: determining a first sample location of a human in the detection area using inference, the first sample location being determined based upon detecting the human interacting with the system in some known way; determining a second sample location :of the human in the detection area, the second sample location being determined based at least in part on a comparison of the received second set of signal data to the baseline signal profile not utilizing the inferred location; comparing the first sample location and the second sample location; and adjusting the determination steps based on inferred location to improve: the 10CatiOnealculating, capabilities of the system, the adjusting based upon the comparing step.
[033] In another embodiment of the method, the property data about the wireless signals comprises dam about signal properties selected from the group consisting of:
received signal strength, latency, and bit error rate:, [OA In another embodiment of the method, the computer server creates the:.
first gam*
baseline signal profile by applying statiSticat methods :to the first set of sample baseline signal data, and the computer server creates the second sample baseline signal profile by applying statistical methods to the second set of sample baseline signal data.
[035] in another embodiment of the method, the method further comprises: the computer server receiving from the first transceiver additional sets of baseline signal data comprising property data about the signal properties of a second set of wireless signals received by the first transceiver from the second transeeiVel; the property: data being getterated by the lint ttansceivens part of ordinary operation of the first transceiver on the communication network and the computer Se0er Updating the baseline signal :profile basedon the continuOnslyteccived additional sets of baseline signal data when the continuously received sets of baseline signal data indicate the absence of a human in the detection area, [OM In another embodiment Of the method, the method further comprises: the ootop4tot server receiving from the first tran c6vet a set of signal data comprising property data about the signal properties of a second set of wireless signals received by the first transceiver from the second transceiver when one or more humans are present in the detection area, the property data being generated by the first transceiver as part of ordinary operation of the first transceiver on the communication network; the computer server determining the quantity Of humans present in the detection area based at least in part on a comparison of the set of signal data to the baseline signal profile [037) In another embodiment of the method, the method further comprises: the computer Wye determining, a location Of each of the One or More humans preSent in the detect en at the determination based at least in part on a comparison of the set cf signal data to the baseline signai profile.
.0381 In another enthodiment of the method. When. a human is present in the detection area, the computer server determines that a Inman is present in the detection area and operates the first external system even if the property data in the third set of sample baseline signal data corresponds to the second sample baseline signal profile.
[039] In another embodiment of the method, when a human is present in the detection area, the computer server determines that a human is present in the detection area and operates the second external system only if the property data in the third set of sample baseline signal data corresponds to the second sample baseline signal profile.
[040] hi another embodiment Of the method, the wirelest:communication netWork has a carrier frequency in the range: of 850 MHz and 17.5 014 itic.tusivd:
[04 11 in 4E000:embodiment of the method, the Method further CompriSeS: the :Computer server storing a. plurality of historical data records indicative of whether a human was present in the detection area over 4:period of time, each of the historical data records comprising an indication of the number of humans detected in the detected area and the date and time of when the number of humans WAS detected in the detection area; and the compute Server making the historical data records available to one or more external computer systems via an interface, BRIVEDESCRWTION'OF THE DRAWINGS
[0421 FIG, I is a schematic diagram of an embodiment of a system according to the present disclosure, [0431 FiCk:21gallow chart eat. embodiment otamethod according to the pitstiit di Sciosure.
[044.13 :FIG. 3A depicts:A...$0hOnatic diagram Of.a system for change detection in a deteefi0 network over rinit'according to the present disclosure.
[045] FI:O. 3B deript schematic diagram of a system for detecting changes itt loolions of humans in .,0::de*tion netwodc overtime a(.01:- ding to.: the present*sclosure.
DESCRIPTION OF THE PREFERRED EMBODIMENT
[046] The following detailed description and disclosure illustrates by way of example and not by way of limitation, This description will clearly enable one skilled in the art to make and use the disclosed :system. and methods).. :and describes several embodiments,:
adaptations,i variations, alternatives and uses of the disclosed SyStetnS and methods AS:
various changes could be made in the above ainstructions:without departina from the stope of the disclogureS, it is intended that all matter contained in the description or shown in the accompanying drawings shall be interpreted as illustrative and not in a limiting sense:
[047] Generally speaking, described herein, among other things, are systems and methods for detecting the presence ofa body in a network Without fiducial elements.
Generally speaking, the systems and methods described herein use signal absorption, and signal forward scatter and reflected back.scatter of the RE communication caused by the presence of a biological mass in a communications network, generally a mesh network.
[048] Throughout this disclosure, the term "computer" describes hardware which generally implements functionality provided by digital computing technology, particularly computing functionality associated with microprocessors. The term 'computer" is not intended to be limited to arpy .,,pecifie type 01 4ompt#14 de ice btit it is 'intended to be inclusive of all computational devices includiiig, but not limited to: processing devices, :oticroproceSSor*
personal computers, desktop computers, laptop computersõ:: workstations, terminals, servers,õ
clients, portable computem,: handheld computer*: Smart phones, tablet c omputer.s,, mob 'L
Joie es, sdiNer farms, hardware applianeeS, minicomputers, mainframe computers, video game consoles, handheld video game products, and wearable computing devices including but not limited to eyewear, wrist-wear, pendants, and clip-on devices.
[049] As used herein, a "computer" is necessarily an abstraction of the functionality provided by a single computer device outfitted with the hardware and accessories typical of computers in a particular role. By way of example and not limitation, the term "computer" in reference to a laptop computer would be understood by one of ordinary skill in the art to include the functionality provided by pointer-based input devices, such as a mouse or track pad, whereas the term "computer' used in reference to an enterprise-class server would be understood by one of ordinary ski fin the art to include the functionality provided by redundant systems, such aS RAID (hives and dual power supplies.
[050) It is also well known to those of ordinary skill in the art that the functionality of e single computer may be distributed across a number of individual machines. This distribution may be functional, as where specific machines perform specific tasks; or, balanced, as where each machine is capable of performing most or all functions of any other machine and is assigned tasks based on its available resources at a point in time. Thus, the term "computer" as used herein, can refer to a single, standalone, self-contained device or to a plurality of machines working together or independently, including without limitation: a network server farm, "cloud" computing system, software-as-a-service, Or other distributed or collaborative computer networks, [051] Those of ordinary skill in the art also appreciate that some devices which are not conventionally thought of as "computers" nevertheless exhibit the characteristics of a mfRiter" in certain contexts, Where such a device:is performing the functions of a "computer" as described herein, the term "computer" includes such devices, ..
to that extent.
Devices of this type include but are not limited to: network hardware, print servers, tile servers, N AS and SAN, load balancers, and any other hardware capable of interacting with the systems and methods described herein in the matter of a conventional "computer."
[0521 Throughout this disclosure, the term "software" refers to code objects, program logic, command structures, data structures and definitions, source code, executable and/or binary files, machine code, object code, compiled libraries, implementations, algori thins, libraries, or any instruction or set of instructions capable of being executed by aiicomputer processor, or capable of being converted into a form capable of being executed by a computer processor, including without limitation virtual processors, or by the use of run-time environments, virtual machines, and/or interpreters. Those of ordinaty skill in the art recognize that .ftare can be wired or embedded into hardware, inchiding without limitation onto a microchip, and still be considered "software" within the meaning of this disclosure. For purposes of this disclosure%
software includes. without limitation: instructions Stored or storable in RAM, ROM, flash memory BIOS, CMOS, mother and daughter board circnitry, hardware controllers, USB
controllers or hosts, peripheral devices and controllers, video cards, audio controllers, network cards. BluetoothTM and other wireless communication devices, virtual memory, storage devices and associated controllers, firmware, and device drivers. The systems and methods described here are contemplated to use computers and computer software typically stored in a computer-or machine-readable storage medium or memory, [053] Throughout this disclosure, terms used herein to describe or reference media holding software, including without limitation terms such as ''media,' "storage media," and "memory,"
may include or exclude transitory media such as signals and carrier waves.
[054] Throughout this disclosure, the term 'network" generally refers to a voice, data, or other telecommunications network over which compUterS communicate with each other.
The term "server" generally refers to a computer providing a service over a network, and a "client"
generally refers to a computer =easing or using a service provided by a server over a network.
Those having ordinary skill in the art will appreciate that the terms 'server"
and "client' may refer to hardwate, software, and/or a combination of hardware and software, depending on context, Those having ordinary skill in the art will further appreciate that the terms "server"
and -client" may refer to endpoints of a network communication or network connection, including but not necessarily limited to a network socket connection. Those having ordinary skill in the art will further appreciate that eserver') may comprise a plurality of software and/or:
hardware servers delivering a service or set of services. Those having ordinary skill in the art will further appreciate that the term "host" may, in noun form, refer to an endpoint of a network communication or network. :(co , remote hose), or may: it: verb fdittn,:
refer to SeNtt providing a service over a network ("hosts a website"), or an access point for a Service OVO:11 network, [0551 Throughout this disclosure, the term "real time" refers to Sofware operant* Within operational deadlines for a given Oent to enromenee or complete, or for a:
given module, :Software, or system to teSpond, and generally itivOkes that the ieSpOrtse ot:perforitiance time is, in ordinary user perception and considered the technological Context, effectively generally cotemporaneous with a reference event. Those of ordinary skill in the art understand that "real time" does not literally mean the system processes input and/or responds instantaneously, but rather that the system processes and/or responds rapidly enough that the processing or response time is within the general human perception of the passage of real time in the operational context of the program. Those of ordinary skill in the art understand that, where the operational contextia:tt graphical user interface "real ante normally implies a response time of no more than one second of actual time, with milliseconds or microseconds being preferable However, those Of ordinary skill in the art also understpd that, under otberppOrational contexts a:system operating in 'real nine" may exhibit delays longer than one Second, particularly where network Operations ate involved, [050 Throughout this. disclosure the term "transmitter refers AO equipment:, or a: set Of equipment, having the hardware, circuitry; and/or software to generate and transmit electromagnetic waves carrying messages, signals, data, or other information, A transmitter may also comprise the componentry to receive electric signals containing such messages, signals, data, or other information, and convert them to such electromagnetic waves. The term 1$
"receiver" refers to equipment, or a set of equipment, having the hardware, circuitry, andior software to receive such transmitted electromagnetic waves and convert them into signals, usually electrical, from which the message, signal, data, or other information may be extracted.
The term "transceiver generally refers to a device or system that comptises both a transmitter and receiver, such as, but not necessarily limited to, a two-way radio, or wireless networking router or access point. For purposes of this disclosure, all three terms should be understood as interchangeable unless otherwise indicated; for example, the term "transmitter should be understood to imply the presence of a receiver, and the term "receiver" should be understood to imply the presence of a transmitter.
[057} Throughout this disclosure, the term "detection network" refers to a wireless network used in the systems and methods of the present disclosure to detect the presence of biological mass interposed within the communications area of the network. A detection network may use general networking protocols and standards and may be, but is not necessarily, a special-purpose network. That is, while the nodes in the network could be deployed for the specific purpose of setting up a wireless detection network according to the present invention, they need not be and generally Will not be. Ordinary wireless networks established for other purposes 'nay be used to implement the systems and methods described herein In the preferred embodiment, the detection network uses a pIntality of BluetoothT" Low Energy nodes, but the present disclosure is not limited to such nodes. Each node =acts as a computer with an appropriate. transmitter And receiver for communicating over the network. Eazh of the compilers provides a uniqiie identifier within the network whenever transmitting a message such that a receiving computer is capable of discerning from where the message originated.
Such message origination information will usually be critical to the functioning of the invention as described in this detailed description. The receiving computer then analyzes the incoming signal properties, including but not limited to, signal strength, bit error rate, and message delay.
The detection network may be a mesh network; which means a network topology in which each node relays data from the network.
[058] Throughout this disclosure, the term "node refts. to a start point or endpoint for a network communication, generally a device having, a wireless transceiver and being a part of a detection network. Nodes ate generally:Standalone; :self-contained networking devices, SOO as Wireless routers, wireJess access:. points, short-range beacon, and so forth..
A node may be 0 Amer4l-pulpoS.0 device or la special-purpose device configured for use in a detection network as described herein. By way Ofetattiple and not limitation, a node may be a device having the Wireless transmission capabilities of an off-the-shelf wireless networking device with the addition of specialized hardware, circuit(y, tomponentry, or programming, for implementing the systems and methods described herein; that is, for detecting significant changes to signal properties, including but not limited to, signal strength, bit error rate, and message delay.
Within a detection network, each node can act as both a transmitter of signal to the network, as well as a receiver for other nodes to push information. In the preferred embodiment, the nodes utilize BluetoothTM Low Energy (BILE ) as a wireless networking system.
[059] Throughout this: diSebstittõ, the term ',Omni nods" refers to something happening at an ongoing t,taiS over time, Whether such events are mathematically continuous or discontinuous.
The gene-ray accepted mathematical definition of "continuous function"
describes a:. function which 15 WithOut holes :Or jumps, generally described by tworsided limits. The technology described herein is based upon disturbance* to a telecommunicatiOns system, in Which the transceivers transmit at discrete intervals,: and the received raw data is taken discretely. Lo, at discrete time intervals. The resulting data ik itself may be discrete in that it captures the characteristic of the system during a particular observation window (i.e., the time interval), in a physical or mathematical sense, this mechanism is essentially a set of discrete data points in time, implying a discontinuous function. However, in the context of the technology, one of ordinary skill in the art would understand a system exhibiting this type of behavior to be "continuous" given that such measurements are taken at an ongoing basis over time, [060] The measurable energy density signature of RF signals is impacted by environmental absorbers:and rellettOrs Many biolOgiCal masses suelvas humans, are mostly water and act:as significant energy 0:hsott:ters Other attributes Of people such as clothing, jewelry, internal OrgallS, etc all further impact the measurable RF energy denSity. This is particularly true where RF communication devices are transmitting over relatively short distances less than 50 ineterS), such as I3hietootlim, 892,154 (Zi,04, Thread); 00 Z-WaVe transceivers. A
human who passes through the physical space of the network Will cause signal absorption and disruption. Due to relative uniformity in size, density, and maSs=
composition, human bodies can cause characteristic signal absorption, scattering, and measurable reflection. Changes in signal behavior and/or characteristics are generally referred to herein as "Artifacts." Such phenomena are particularly useful in the Industrial, Scientific, and Medical (ISM) bands of the RF spectrum, but are generally observable in bands beyond these, [061] In an RF communication system comprising! a transmitter and receiver separated in space,: Signals receiVed by the receiver from a given transmitter are made up of energy from the original transmitted message whicti has arrived at the receiVer. Objects generally in the tratigniSsiOn path will affed the ehaototetiSties of ultimatO Op* which arriVesat the receiver.:
[062] Communication ostems are:generally designed to handle such issues and still faithfully reproduce the Message from the transmitter. Since humans generally exist, 0s far as RF
communications are impacted, as: mass of water :4 one such Observable difference between human *Settee and absence in a detection network is signal absorption by' the human_ Generally, the closer to the transmitter or receiver, the more significant the absorption is likely to be.
[063] Generally, it is envisioned that humans will produce artifacts in a detection network in.
a somewhat predictable manner, which can be detected or identified programmatically by detection algorithms. Further, artifacts may be cross correlated across the network to determine an estimated position of the object cansing the. artifaCt. The accuracy of this estimation may vary with the algorithms Otosenlconttincted, and with the equipment ttsed in the individnal system.
[064.1 For: each given algorithm which is. Choteniconstructed, the system May build such detections as a combination of a baseline signal profile with no human present in the detection area and *triple baseline signal data with a human present in the detection area NOW itie0itiOg sample baseline signal data may be compared against both the known sample baseline signal data and the baseline signal profile to determine the presence or absence of humans in a space.
[065] Short-range low power communication networks typically operate using signals in the 2.4G11z, frequency band, which is notable for being well-within the energy frequencies humans have been observed to absorbõks indicated, a human body physically interposed in a detection network absorbs and/or reflects at least some of the signals transmitted between and among nodes. However, other effects may :also take place, such As forward and backward scattering_ Utilizing the collection of data in a detection network without a human present to establish A:
baseline, futtne elements pf dat4 for statistically :OignificOOt differences typically exhibited by the physical presence of one or more humans, whether or not the one or more humans is moving, the detection network makes the determination as to the pretence or absence of humans within the network [066] Depending on the communication network itself hardware used, and the human, those changes may register within the network in different ways and produce different results;
however, such changes are detectable. This differs from radar technologies in that detection of the object does not necessarily rely or depend upon only signal reflection, but often rather the opposite principle signal absorption which is detected via measurable changes in signal characteristics between a transmitter and receiver in different physical locations.
[0671 By analyzing the change in signal characteristics between nodes within the network, the position of a disruptor and e.g., a human body can be calculated relative to the network.
Because the mere presence of the body is sufficient, this system does not necessarily include a fiducial element, and it need not rely on motion or movement. Because no fiducial element is required, the systems and methods described herein may provide an anonymous location data reporting service, allowing for the collection of data concerning traffic, travel routes, and occupancy without requiring additional components or devices to be associated with the bodies being tracked. Generally speaking, the systems and methods described herein operate in real time.
[0613] FIG. 1 is a schematic diagram of a system and method according to the present disclosure. In the depicted embodiment (101) of FIG. 1, a detection network (103) comprising a plurality of nodes (107) is disposed within a physical space (102), such as a room, corridor, hallway, or doorway. In the depicted embodiment of FIG. 1, an indoor space (102) is used, but the systems and methods described herein are operable in external environments as well. In the depicted embodiment, a node (107A) is communicably coupled (111) to a telecommunications network (115), such as an intranet, an internet, or the Internet. A server computer (109) may also be communicably coupled (113) to the telecommunications network (115) and thereby with the connected node (107A). The depicted server (109) comprises programming instructions for implemenfing the systems described herein, and carrying out the method steps described herein. However, in an embodiment, the functions performed by the server may be performed by one or more nodes (107) having, the appropriate software/programming instructions, or being appropriately modified.
[069] hi the depicted embodiment ofIFIG. T., each of the nodes (107) is communicably connected with at least one other node (107) in the detection network (103)3 and may be communicably connected to two or more, or all of the other nodes (107) in the detection network (103):: Fotekanapie,, hi a typical wireless network deployment strategy, :a plurality of **less access points is placed througliout the physical space (102), generally to ensure that high-quality signal is available everywhere. These nodes (107) Collectively form a detect*
network (103) and may transmit data to One another, or may transmit only to a router or set of touters. In the depicted embodiment of FIG. 1., node (107A):is wireless router, And the other nodes (107B), (107C) ati.d (1(i71)) are wireless acceSs pOints. However, this isjust: one possible configuration. Further, it is not necessary that any given node (107) be a particular type of wireless device. Any number of nodes (107) may comprise a router, access point, beacon, or other type of wireless transceiver. Further, any number of nodes (107) may be present in an embodiment, though a minimum of two is preferred. More nodes (107) in a space (102) increases the amount of data collected (as described elsewhere herein), thus improving the chance that a human is generally interposed between at least two nodes (107), improving the lOtAtion resolution_ [070] In the ordinary eddrse:Of operation, the nodes (107) frequently Send and receive wireleSS
tratigniSSiOns. For ocample, when aWit*Ss router (I 07A) reteives a data packet; the wireleSS
router (107A) typically broadcasts a witeless transmission containing the packet. This means that any receivers! Within the broadcaSt radius Of the w ter ,(107A): can receive the sig,nal, *better Or not:intended for them LjkeviiSei: wben an access point receives local data, such data is likeWiae broadcast and can be detected by other access points, and the router. Even4hen no user data is actively transmitted on the network, other data is frequently transmitted. These other transmissions may include status data, service scans, and data exchange for functions of the low-level layers of the network stack.
[071.] Thus, each node (107) in a typical detection network (103) receives transmissions on a consistent basis and, in a busy network, this effectively may be a continuous basis. The detection network (103) may thus be used to calculate the existence and/or position of a biological rums (104) or (105) physically interposed within the transmission :
range of the network (03). Because the presence of a human body impacts the Characteristics of signals transmitted between or among nodes (107) within the network (103), such presence Can be detected by mom tot Mg for changes in Well characteristiea, This detection May tilSo be performed while the data in the data packets being transmitted and received is still being transmitted and received; that is, the detection is incident to ordinary data exchange: be(Ween or among two or more nodes, which continues regardless of the detection.
Specifically, the wireless network may operate to transfer data between nodes, while simultaneously using characteristics of how the data packets incorporating that data have been impacted by the presence of an object in the transmission path, to detect and locate the object [072] In the depicted embodiment of F1G. 1, at least one node (107) monitors the communication signatures between itself (107) and at least one other node (107) for statistically significant changes in signal characteristics nven while it awaits, receive*, and/or transmits communications between itself and other nodes (107) The particular geometry of the physical space, (02), including the pt*.4e.tve and 1OCation of fixtures in the physical enyirotitnerit, generally does not impact the :system because the monitoring is for statistically significant c/hinge in signal characteristics indicating or iciencim; the character *s of a human. That a change in signal characteristics is attributable to a:Change in absorbers or reflectors, like human bodies, in the physical environment Of Communication space covered by the detection network (103). The detection of the presence of a human within the detection network (103) may be done using statistical analysis methods on the signal, such as using sensing algorithms, as described elsewhere herein. Again, this does not require the human to be associated with a :Uncial element, or in motion. Instead, the detection network (103) deteets tbat Characteristics of the network communication have changed because a new object (which is generally a human object) has been introduced in the communication space and the presence of that object has caused a change to the characteristics of the network:: communications, typically data packets,i between nodes (107).
[073] To detect a :change, generally a baseline of signal characteristics is developed =againat :Whichirecent ly transmitted si griala ar ompm-ed. These characteristiCa:are derived from typical WireleS$ COMM LirtiOatiOJI netWor k diagnostic inforrnati On .............
This baseline of si gn I charac.eTiStics:
between nodes (107) is generally established prior to the use of the detection network (103) 04 deteetbr, This may be done by operating the. detection network (103) under typical or normal circumstances, that is with the detection network (103) communicating data packets, with no significant biological mass interposed in the physical broadcast space of the detection network (103)_ For an amount of time during such operation, signal characteristics between and/or among nodes (107) are monitored and collected and stored in a database. In an embodiment, the server (109) will receive and store such data, but in an embodiment, one or more nodes (107) may comprise hardware systems configured to receive and/or store such data.
[074) for ekample,*here 4hode (1W) contains special purpose hardware and prOg,ramming for Use according to the ptoaot disclosure, such node 0071 may 4:Grp its Own signal characteristic data. Such. lai characteristic data may be data relating to the received energy characteristic of signals received by a particular node (107) from one or more other nodes (107.).:
The baseline data establishes for each node (107) a signature characteristic profile, Which is essentially a :collection of data defining the typical and/or general characteristics Of signals received by the node (107) under ordinary operating circumstances where there is no significant biological mass interposed in the detection network (103). The node (107) may have one or more of such profiles for each other node (107) from which it receives data.
[075] In an embodiment, after the baseline signatures have been detected and collected, the detection network (103) will generally continue to operate in the same or similar fashion, but is now able to detect the presence of a biological mass. This is done by detecting and collecting additional signal. characteristics, generally in real-time, as the detection network (103) operates in a normal mode of transmitting and receiving data packets. These newly generated real-time signal characteristic profiles are also generally characteristics of signals between two particular nodes (107) in the detection network (103), and thus can be compared to a corresponding baseline signal characteristic profile for the same two particular nodes (107). A statistically significant difference in certain characteristics between the two profiles may then be interpreted as being caused. by the presence of a significant biological mass, such as a human.
[076] The comparison operations may be performed by appropriate hardware in a given node (107), or the real-time signal characteristic profiles may be transmitted to a server (109) for processing and comparison. In a further embodiment, both are done so that a copy of the real-time data is also stored and accessible via the server, effectively providing a history of signal characteristic profiles.
[077] This is because, as described herein, a biological mass interposed within the network will generally cause at least some signal characteristics between at least two nodes to change when a data. packet is transmitted which intercepts and/or generally interacts with the biological mass. The degree and nature of the change generally will be related to the nature of the particular biological mass interposed (e.g., the size, shape, and composition), and its location in the network (1.03). For example, where a housefly flies through the detection network (103), the amount of signal change may be so minor as to be indistinguishable from natural fluctuations in signal characteristics. However, a larger mass, such as a human, may cause more substantial and statistically significant changes in sham! characteristics.
[078] Such changes may not necessarily manifest in all signal. characteristic profiles for the detection network (103). For example, where the mass is interposed at the edge of the detection network (103), the nodes (107) nearest that edge are likely to experience statistically significant signal characteristic changes, whereas nodes on the opposing side of the detection network (103) (*hose signals to each other do not pass through. or around the biological mass), are likely to experience few or no statistically significant changes. Thus, if the physical locations of the nodes (107) are also known, the system can determine not only that a biological mass is present in the detection network (103), but calculate an estimate of where it is located, by determining which nodes (107) are experiencing changes and calculating the magnitude of those changes.
[0791 This can he seen in the depicted embodiment of FIG. 1, In FIG. 1, assuming the presence of only one human ¨ either A (104) or B (105) ¨ is present at a time for simplicity, A
(104) would generally have a greater impact on the signal characteristics between nodes (107C) and (107A) than between nodes (107A) and (107C). FurtherõA (104) would also generally have a small bidirectional effect on the signal characteristics between nodes (107B) and (10713). By contrast, 8 (105) would have a bidirectional impact on the signal characteristics between nodes (107A) and (107C), as well as on the signal characteristics between nodes (1079) and (1071)).
[0801 While all nodes may be communicating with one another, the effects of A
(104) and B
(105) will generally be more negligible on communications where A (104) and/or B:(105) are not generally in line with the communications path between nodes. For example, neither person (104) or (105) is likely to seriously impact transmission between nodes (107A) and (1079) because neither person (104) or (105) is in the transmission path between those nodes.
However, A (104) may have an impact on transmissions between nodes (107C) and (10713).
[081] It should be noted that the presence or absence of a biological mass within the communication area of the detection network (103) will not necessarily result in any change in data communication. It is expected that the detection network (103) will utilize its standard :existing protocols, means, and methods (including all forms of retransmission and error checking) to make sure that the data in the data packets being transmitted is correctly received, processed and acted upon. In effect, the detection process of the detection network (103) is performed in addition to the standard data communication of the detection:
network [082] it should he recognized from this that the data in the data packets being pOmmunicated by the nodes (107)in the detection network (103) generally Will not be directly used to detect the biological mass within the communicatiOn area of the detection network (I03). Instead, the data will simply be data being communicated via the detection network (103) for any reason and will Wien have nothing to do with detection of the biological mass.
Further, while this disclosure generally contemplates packetized communication in the form of data packets, in an alternative embodiment, the data may be continuously communicated in a non-packetized form, [083] In an embodiment,,,iitt Order W. allow the detection network (103) to detect the presence or absence of a particular biological nut0.., the system includes a training ..:aspect or step This aspect may comprise, after the baseline is established, one or more humans are deliberately interposed in the network at one or more kvations in the network, and one or more additional ,tets of baselim data ate eollected and stored. This second baseline may be used for comparison purposes to improve accuracy in detecting the Size, Shape, andlOt other characteristics of 11 biological mass interposed in the network, and/or for improving the accuracy of location determination. Such training may use supervised or unsupervised learning, andlor may utilize techniques known to one skilled in the art of machine learning, [0841 hi an embodiment; adetection oetwork (103) may useaispecialized protocol comprising a controlled messaging structure andlor format, which can be controlled from one node (107) to another (107), making it simpler and easier to determine from which node (107) a message originated; and allowing for control of aspects Such as the composition of the Signal sent, transmitted signal strength, and signal do,ation. Such control !flother facilitates certain improvements in prOc es s n& and facilitates receivers i den t fyi lig and using certain signal finalities and/or characte,ristios particular to the detection:aspects of the network: 0931 which may differ from general networking aspects sharing the same network (103).
With control of the message sent and received on the opposing sides Of the mass being located, it is not necessary to send a signal as .à scan, nor to sweep a region in space, :as such functions tend to require significantly more expensive equipment than is needed for typical broadcast or directional transmission between nodes (107). Messages are generally constructed in such a way as to best produce usable data for detection algorithms which would be constructed to function best with the communication network they are being used within, Generally, such constructions still avoid the need for waveform level analysis of the signals sent by the network.
[085] In the depicted:embodiment, each node (107) generally is. able to determine the Origin 040 (197) :of packets received by such node (1107). Such message :Origination information: is:
:typically encoded within the *Osage =itself,: as would be ltnewn to one skilled in :communications networks. Byway of example and not limitation, this may be done by eXamining data embedded in established protocols M the nettm?orking stack, or by eXmnining data transmitted by the sending not* (ton for:* specific purpose of implementing the Systems and methods described herein. Typically; :each node (107) haS
appropriate hardware and processing capability for analyzing the messages received, While many different topologies and messaging protocols would allow for the functionality described herein, generally mesh networking topologies and communication methods will produce usable results.
[086] FIG. 2 depicts an embodiment (201) of a method according to the present disclosure and should be understood in conjunction with the system of FIG. I. In the depicted embodiment, the method begins t 203) with the establishment 1.203) of a detection network (103) comprising a plurality of communication nodes (107) according to the present disclosure As would be known to one skilled in the art of setting, up communication systems, there are many different approaches to the setup of such a network (103) and many different network (103) topologies may prove viable within this framework.
[087} Next, a digital map in memory may be generated (205) indicating the detection network's (103) physical node (107) geometry, The detection algorithms described herein generally use information about where in the physical environment (102) the nodes (107) are deployed. Data about such physical location of the nodes (107) may be supplied manually to an accurate diagram of the physical network environment (102), and/or software could be used to automatically generate a relational position map of one or more nodes (107) within the detection network (103), facilitating eager placement of the nodes (107) into such an environment map or diagram.
[088] Altermtively, nodes (107) may be placed on a blank or empty map or diagram using relational (as opposed to absolute) distances for detection. In such a dimensionless system, messages could still be generated from the algorithms related to the detection of humans in the system (1.01), and additional manual processing may be included, such as user input concerning which messages are sent related to the presence and/or movement of humans within the network (103).
[089] In an embodiment with automatic node (107) location detection, node (107) locations are detected algorithmically and/or programmatically by one or more nodes (107) and/or a computer server (109), based upon fattors such as, but not necessarily limited to: detection network (103) setup and configuration, including physical location of specific hardware components such as nodes (107) and each node's (107) location relative to one or more other nodes (107); signal strength indicators; and, transmission delay. In the depicted embodiment, this step (205) further comprises overlaying the generated map on a digital map of the physica1 space (102) or em ronment (referred to helvin as an "en v ro n men t map") the dewetion network (103) occupies, such as floor plan of a building. This step (205) may further and optionally comprise a sealing element to align the scales of the generated map to the environment map, as well as user-manipulated and/or modifiable input elements for making adjustments to fine rune the generated map so that it more doSely conforms to the actual node (107) deployment geometry, as would be understood by one of ordinary skill in the art. In an alternative embodiment, each node (107) may be manually placed in its appropriate location on the environment map without using a relative location algorithm.
[090] Either way, this step (205) establishes the physical locations of the nodes (107) in the detection network (103), which will facilitate determination of the location of interposed biological masses attributable to the presence of humans within the detection network (103).
By placing the nodes (107) on a map (either through manual or automatic means), the nodes (107) trad the presence of a human in thenetwork (103) based on how the baseline signal affects communication between various nodes (107). The system (101) then utilizes information collected about the signals which arrive at the receivers, given a transmitted set of information known to the data processing algorithm. The data processing algorithm is what ultimately determines whether a human is present within the network (103) and/or where within the network (103) that human is located.
[091] Next, messages are constructed and exchanged (207) in a lomat, and according to a protocol, determined to be suitable for detecting the presence of a biological mass within the network (103). While this may be done using general purpose networking protocols known in the art, such as protocols in the OSi network model, or special-purpose protocols which replace, or supplement, such general-purpose protocols.
[092] Generally, it preferred that this step further comprise controlling and/or modifying (207) messages passed within the detection network (103) for the specific purpose Of detecting human presence and facilitating simplified statistical analysis. By controlling (207) message exchange, the system (101) can adjust for a. common content being sent through the detection network (1.03) while also facilitating adjustment of parameters including, but not necessarily limited to: transmission intervals; transmission power; message length and/or content; and, intended message recipient(s). Again, the system does not necessarily rely on waveform level analysis, allowing operation within the confines of wireless communication standards.
[093] Controlling (207) such parameters facilitates the development of statistics and/or analytics, which may be based at least in part on pre-defined or anticipated message content or characteristics. Such content and/or characteristics may include, without limitation, transmission timestamp and/or transmission power level. By controlling and modifying (207) these aspects, one may overcome hardware limitations, including hardware features which cause unwanted consequences when used in a detection 'network (103) according to the presence disclosure, such as but not necessarily limited to automatic gain control (AGC) circuits, which may be integrated into certain receiver hardware in a node (107).
[094] Next in the depicted embodiment (201), the space (102) is cleared (209) of significant biological mass - notably humans (205); Then, a statistical baseline -of signal strength is developed (211) locally by each node (107). Again, by placing-the nodes (107) on a map in step (205), whether through manual and/or automatic means, the nodes (107) can track the presence of a human in the network (103) based on how the baseline signal is affected for communication between nodes (107).
[095) Next, a biological mass enters (213) the detection network (l03), causing signal absorption and other distortions, which manifest in changes in signal characteristics between nodes (107). These changes are detected (215) and analyzed (217) to determine whether the changes are indicative of the :presence of a human, or of another type of biological mass the detection network (103) is configured to detect. Such detections are further localized at least to an area between nodes, such as within an interior area between three nodes on the network, but possibly with greater accuracy depending on the algorithms and hardware being in use at the time.
[096] Generally, this is done using detection algorithms executed either hone or more nodes (107) or by a server computer (109). The nodes (107) and/or server (109) use software to estimate the location of the detected biological mass in the detection network (103) using one or more detection algorithms. Such algorithms generally compare the baseline profile to newly detected signals, and may also use or be based upon various data and other aspects, such as, without limitation: detection network (103) setup and configuration, including physical location of specific hardware components such as nodes (107) and each node's (107) location relative to one or more other nodes (107); signal strength indicators; and, transmission delay.
[097] Generally speaking, as described elsewhere herein, these algorithms include comparing newly gathered signal characteristic profiles (215) to baseline signal characteristic profiles (211) to identify a change and determine whether, based on the nature of the change, the change is indicative of the presence of a human. This determination may be done at least in part using training data developed through machine learning As described elsewhere herein.
[098] In an embodiment, the detection algorithms may further comprise the use of observed signal characteristic change(s) between one or more pairs of nodes (107) in the detection network (103), correlated in time and relative effect. These factors facilitate the identification of a physical location in the detection network (103) where such a signal change took place, allowing for an estimate of the ph vsical location o f the human causing such signal characteristic change(s), which in turn may be used to estimate a physical location in the detection network (103) environment where the biological mass is interposed. Such physical location may be provided as simple x, y, z coordinates according to a coordinate system, or may be vistuilly indicated, sad) as on the map_ [099] Where multiple humans are present in the detection network (103), separating out the impact of the various individuals from one another is more difficult, and accuracy will generally improve with the addition Of more nodes (1071. In an embodiment, techniques such as advanced filtering and predictive path algorithms may be used to separately detemiine location of individuals within the network (103). Although movement of the.
human in the network (103) is not required for the systems and methods to operate properly, movement, or lack of movement, may be used to improve detection accuracy, such as by predicting the path of a single individual. This can help identify instances where an individual has, statistically, "disappeared" from the detection network (103) but the system has sufficient data to estimate that the individual is still present in the network (103).
[0100] For example, where an individual's movement path has been predicted, and terminates next to another detected individual, the system (101) may determine that the two individuals are loo close together for signal characteristic profile changes to separately identify them, but since the individual's movement path was not determined to have taken the individual out of the network's (103) detection range, the algorithm detemilnes that the individual is present, and not moving, in dose proximity to another detected human. Thus, when one of the two proximate, stationary humans moves, the algorithms may again separately identify each one, and resume predicting path based on observed signal characteristic profile changes.
[0101] in this way, the systems and methods according to the present disclosure can track one or more individual humans within a network (103), whether or not moving, and whether or not any $1.1Ch humans are associated with a fiducial element.
ldentifying::specifie individuals may further be done using other path prediction and sensing algorithms, such as but not necessarily limited to those used in the robotics industry for human-following technology, in order to estimate which human was which. It:should be noted that individuals may impart specific and unique effects on y0.6(10 signal characteristics, :allowing for the identification of a Specific individual, and further allowing for one specific individual to be distinguished from others.
Such effects may be used. to further determine the location of specific individuals within the detection network.
[0102] The detection: algorithm(s) are generally :constructed to take advantage Of the characteristics of communication signals; Considering factors such as, but not necessarily:
limited to, frequency of the signal(s) and the transmitted power levels of the signal(s). in an embodiment, the algorithms detect human presence using data-driven methods for determining the effect of the presence of a human on signal characteristics in the RI' environment within the communication network, and then identifying when that effect is later observed.
[0103] For example, in an embodiment, a signal characteristic which varies with the presence of a human body is:the:..Signal strength registered between nodes (107). This is particularly the :case Within a BLE network, and the statistics related to signal Strength over time May indicate the presence of a human within the network, These artifatts may. be used by the Oetectio0 algorithm(s) to provide information about the physical location of the object causing the artifact. The is. by combining various statistics about artifacts captured across the network (104 the system determines 'N'here in physical space (102) the artifact is located, and thus.
Where a human is the network (103).
[0104] In the simplest use case, the algorithms may simply identify 011.000$
in signal characteristics which are similar to changes known (e.g.õ from training) to be caused by the presence of a human, and simply trigger a detection event (219) whenever such changes relative to a baseline are detected_ This may appear like an adjustment of mean, standard deviation, skewness, or variance in the signal strength depending on the system (i01) used, When the detected signal characteristic profile returns to a profile similar to the baseline, it can be inferred that the physical environment 0,02) hag :returned to an empty state with respect to whether a human is present [0105] Elaborating on the simplest use case, the baseline profile in this case Comprises some or all baseline profiles which exist when a space doeS not contain any humatiSaod may vary depending on physical adjustments to that space: Simpler algorithms, Which may account for the changes associated with a newly detected human :Change relative to :a recent baseline, can be used to address such situations; however, in the event that the baseline has changed, it is preferred that the system accurately determine whether one or more current signal profiles matches an empty baseline profile, or matches a profile one that represents some degree of occupancy. Such determinations may be made in response to movement, but it is preferred that they be not made in response to movement, but rather based on whether the characteristics of such a signal can be correlated with one or more of the empty baselines or one or more of the presence:Signal profiles;
[0106] Compared to Other technologies used for,sucii. determinations (typically the Passive:
Infrared (PIR) :SOO:SOO,: Which require rnotion to function, the Systems and inethodS described herein are capable of detecting the presence of a static human within a space (102), whether or not in motion, and more precisely, detecting when a human is no longer in the space (102). For applications wen. aS security and OceOpanOy sensing, this System would be more difficult to trick. Some examples of tricks that may fool PER and other similar motion based technologies' include holding a sheet in front of a person while they enter a space, moving very slowly; or remaining generally motionless in an area after entering. Another benefit is that the system does not necessarily require additional hardware beyond that used in ordinary network communications. This is because the additional software and processing capability may be provided via external components or modifications to existing hardware, such as by implementing the appropriate software as a System On a Chip (SOC) attached to off-the-shelf communications modules.. It additional processing power is required, additional processing node(s) may be added to analyze the signals propagated between nodes (107). or the workload may be transmitted to and handled by a dedicated server machine (109)õ
[0107] Making determinations of human presence andfor location may be related to the particulars of the signal type being analyzed, and controlling the signal sent between nodes (107) on the network (103) to best achieve those detections. By sending controlled communication pulses through the network (103) where the original signal is known and the transmitted power can be modulated, it is possible to develop exemplary data related to signal absorption, reflection, backscatter, etc. due to additional humans between the nodes (107).
Since it is generally assumed that a baseline system can be configured without the presence of a human and that such a baseline would look statistically different than with a human present, it can further be assumed that signal characteristic changes would be due to the presence of a human in the network. By allowing for the input of timers and generally configuring. the system to refine the baseline definition \ then a space (102) is empty, the system may tcalibrate itself periodically to achieve improved accuracy. Generally speaking, tracking algorithms make use of the best available triangulation calculations combined with statistical methods, as would be known to one skilled in the art of location technologies, coupled with the detection algorithms fOr detecting humans within the network (1 03)_ [0108] The present disclosure does not require a fiducial element associated with the human detected, nor does it require that the human be carrying any device capable of communicating with the network; however, such technology would take advantage of such elements should they be deployed within the system. The addition of such elements may ease the calculation burden on the system and allow for increased accuracy_ The systems and methods described herein do not preclude such additional functionality, and could be enhanced by it. Augmenting detection with an inference engine adds to the ability of the sensing hardware to recover from a false alarm situation or other edge case, thereby making the system more robust. Such an.
inference engine may further feed information into a machine teaming system, which may further modify the one or more baseline signal profiles or the one or more presence signal profiles to improve the performance of the system.
[0109] in an embodiment. a detection network (103) implementing the systems and methods described herein may further comprise elements for taking action (219) based on the detected presence and/or location of a human. This may be done, for example, by sending control signals over the network using the computers to first determine the presence and/or location of a human on the network, and then to determine an action to take based on the presence and/or location of a human on the network, and to send a message over that network to take that action. Since the communication network and the network performing the detection may be the same network, the invention described herein extends the traditional functionality of a communication network to include human detection andlot location sens i w th out requiring additional sensing hardware.
[0110] The computer elements on the network necessarily perform additional calculations and may craft communication signals. This may ease the calculation burden on the computers;
however, the network may still function IS a command and control network, independently of the network. as a detection network.
[0111] The system as a whole can be used for a wide variety of applications, ranging from occupancy sensing, as might be used thr lighting control and/or security, to counting the number of people in a space as might be needed for a heat and/or traffic map, to a system that tracks individual humans moving through a space_ The technology may be integrated into the network nodes themselves, or may be a combination of nodes transmitting information, to a processing element (either directly on the network Of in the cloud) to perform the calculations to determine the desired information. The final integrated product suite may be customized for an application, and could be used in a variety of different ways.
[0112] No additional sensor is required t though, in an embodiment, one may be present), and the detections are effectively made through calculating statistics from the traditional RF
communication stack Such a system prevents the collection of personal data from the people walking through the space as the system only knows that an approximately human-sized mass of water, organs, clothing, etc, has passed through, and does not require any separate device to act as a fiducial element. As such, the technology represents a significant departure from traditional methods for tracking humans moving through a space.
[0113] A logical extension of the systems and methods described herein comprises dynamically handling functional network messages within the statistical analysis so as to avoid Of reduce additional messaging overhead for the system, It is also contemplated that, in an embodiment, the systems and methods described herein are extended to comprise dynamic adjustments to network and/or message structure, configuration, and/or operating parameters based at least in part on functional messages transmitted within the network.
[0114] Further, because the tracking is based on signals being affected by what is generally a human mass, the system. is not reliant on the human moving around for detections. By not relying on movement, many of the shortfalls with traditional presence sensing technologies, such as passive infrared and ultrasonic sensing technology, are overcome, [0115] The utilization of a communication network's signals between nodes to detect the presence of humans in the network where the human does not carry a fiducial element is a radical departure from current non-fiducial element detection methods and makes use of communication networks to perform presence sensing in an entirely new way. The combination of detection techniques and utilization of network nodes as transmitter receiver combinations for the purposes of performing human presence detection presented herein constitute a new type of human presence detection system which does not require additional equipment beyond that which is required to form the communication network itself.
[01 16] The systems and methods described herein may be implemented in a communication network without influencing the operation of the network itself for purposes of ordinary communication. The network continues to operate as a communications network as its primary function, but some of the communications are used in this case to calculate the position of a human existing in the network, Because the systems and methods described herein utilize basic operations of a network, a human within the network additionally carrying a transceiver device known to the network may be detected and located with increased accuracy. Such a transceiver device, which may comprise, for example, a mobile computing device having a wireless transceiver, such as a cell phone, mobile phone, smart phone, tablet computer, wearable computer technology, and so forth, may connect to the network and be locatable by the network using traditional triangulation methods known to one skilled in the an.
Machine learning algorithms may also be applied when a person carries such a transceiver, which may in turn further improve performance.
[0117] The location calculation of a known transceiver device. may be compared with the location of the person as determined by the non-transceiver aspects described herein. With the = communications network teponing both the location of the fiduciii.
dl'tlierit as well as the human within the net the locations of those two can be compared, Since it is generally the case that the detected location of a fidncial element has a higher degree of fidelity than the estimated location of the human based on network communications alone, the location calculations for the position of the human within the network can be adjusted using machine learning algorithms so as to improve the location calculation capabilities:Of the system 'for the next human entering the network.
[0118] Using machine learning algorithms, the system can: improve the accuracy of location predicting Algorithms based on the kribUlt: location from the ttangetiver.
This May allow for -verification of prior determinatiOns, and refining of fungai:d0terminationa.
For etamp e, if it i$
found that prior determinations are consistently off by about the same amount, that amount may be applied to future determinationS RS an adjustment In this Way, the system can continue to improve and train itself to better locate the humans within the network.
Similarly, machine learning can continue toin-iptoVO the detection and false guilt: rate. By toy of *ample and not limitation, data concerning prior traffic patterns at a facility can be used to establish defaults, presumptions, or expectations concerning the range of times or days during which a particular facility is generally occupied or generally empty. Such data can be used by the system to improve its performance.
[0119] Additionally, the system is configured to make or draw inferences, such as based upon physical interactions with network elements; that is, devices or components attached to or communicating with the network:that ate :operable by Or operate based upon the presence Ofa butp.00, such as net*ork,operable elettrioal switches, doors notion settkitS., infrared senors, and the like. Such p4y*al interactions may beetinsidere0 fidueial elements at the paint in time that they Are interacted with for the purposes of the system. ,As an example, if a light ,switch that is part of the network is actuated, the system may infer that a human was present at or near the physical location Of the switch at the time the s-witCh was actuated AS suck the:
system could use that information as a known data point examining signal characteristics of the various network devices at that point of time with the inferred knowledge that those characteristics reflect a human at a particular location near the switch) to which it could apply machine learning to better make predictions of human presence in the future, Additionally, such events could serve as -presence triggers for other purposes such as security alerts. As an example, say that the system is in a security mode and someone has found a way to mask their presence but still interacts with a switch, then the system would be able to determine that someone was present and send an alert: based on the interaction with the switch. Generally speaking, interaction ith the system wOuld be defined both physically and logically Where logical interaction 'Would. !tkie typical lisage patterns based on time, ontsidt. inputs et Such a System servesais backup to the RE' presence Sensing and provides additional machine learning Capabilities, to the syStem.
[01201 Additionally, the system can estimate whether :a Mobile transceiver in the network is actually being carried by a human or nOt; Such as where a human leaves :a device in a location in the network. Because the system can detect the human as a biomass through changes in signal characteristics, the system can detect whether a transceiver is present in the network while a human biomass is not. This inhibits false training of the system and facilitates the avoidance of baseline and presence signal profiles being corrupted by data not correlated with such profiles, [0121] In an embodiment,IS Iftither input to the inference engine., &Wine indication of the System changes states and a human Within the detection area behaves in such a manner as To torrealhe :sy0ettl state, the ay$teith may infer that it *mid adjust its baseline and presence profiles to better reflect:user preferences. Byway of example, if the lights in a space AVere to turn off with a human in the spat*, Said human may engage in behavior to reflect presence,:
SOO as physically movmg way* arms, and so fortkotgimpiy .looking for:or:walking tolkartts a wall switch. This movement may be detected Within some reaSonable amount of time, and the system may determine that it incorrectly determined that the space was absent, and adjust its baseline and presence profiles accordingly. Such activities may be referred to as inferring the presence of one or more humans in a space.
[0122] As a side effect of collecting various signal characteristics and being capable of running them through various algorithms, the system is capable of running multiple detection calculations simultaneously to achieve different performance criteria with the same system. As an example, the same communication network can be used for detections associated with lighting and security; however, the gathered statistics can be processed differently, but simultaneously, for the two applications. In this way, the lighting application can still provide for a shorter time to detect, but with a potentially higher &Ise alarm. rate, while a security application, can trade a slightly longer time to detect while reducing the false alarm rate. The signal characteristics to be processed by the system may vary by application, but all are captured from the communication network and can be processed in multiple ways simultaneously. Such processing methods may be encapsulated in multiple sets of different sample baseline signal data for determining detections relative to a baseline signal profile.
[0123] In an embodiment of a system according to the present disclosure, the system comprises a communication system which is capable of determining the presence of one or more humans from information about the wireless signals between two or more computers on the network where each computer consists of a transceiver thr communication; and a computing element for performing calculations, where each computer sends signals to one or more other computers on the network where the signal includes a unique identifier of the computer sending the signal;
where each computer processes the signals received for the purposes of determining the presence of one or more humans; and where the one or more humans are not required to have on their person any device capable of communicating with the network..
[0124] In an embodiment of such a system, the algorithms use statistical methods to determine the presence of one or more humans. In a further embodiment of such a system, the statistical methods determine the number of people present. In another further embodiment of such a system, the system is capable of determining the physical location of the one or more humans on the network In a still further embodiment of such a system, the system is capable of tracking the physical location of the one or more humans over time. In another further embodiment of such a system, the system uses information about the presence of one or more humans to control devices on the network. hi an embodiment, the network is a mesh network.
[0 125] In an embodiment, the computers determine their relative physical locations and further determine the relative physical location of the one or more humans on the network, In a further embodiment, statistical methods are applied to a measure of signal strength to determine the presence of a human. In a further embodiment, the transmitted signal is controlled for making detecting human presence easier, in a fluffier embodiment, the power level of the transmitted signal is controlled for making human presence easier. In a further embodiment, the system functions as an occupancy sensing system. In a further embodiment, the occupancy sensing;
system controls a lighting system. In a further embodiment, the network for controlling the lighting system and the network used for occupancy sensing utilize the same communications technology and hardware. In a further embodiment, the communications technology employed by the computers is chosen from the list of BiuetoothTM SLow Energy, WiFi, Zigbee, Thread, and ZAN' ave.
[0126] In a further embodiment, the system functions as a sensing system Ibr a security application. In a further embodiment, thesecurity sensing system controls the Security System.
In a further embodiment, the network thr.controlling the security system and the network used for security sensing udlize the same communications technology and hardware.
In a further embodiment, the system functions as a human detector for robotic systems. In a further embodiment, the robotic systems have computers which locate various elements of the robotic system relative to one another dynamically. In a further embodiment, the network for controlling the robotic systems and the network for functioning as the human detector for the system utilize the same communications technology and hardware.
[0127] In a further embodiment, the system functions as a sensing system for a HVAC
application. In a further embodiment, the HVAC sensing system controls the HVAC system.
In a further embodiment, the network for controlling the HVAC system and the network used for HVAC sensing utilize the same communications technology and hardware.
[0128] In another embodiment, the system uses machine learning to improve its detection capabilities where humans which have a tiducial element on their person train the system through: (1) using known location techniques to determine the location of the fiducial element;
(2) using the system described above to locate the person; (3) comparing the location calculated by the method of (1) of this paragraph to the method 01 (2) of this paragraph;
(4) adjusting the location determining methods using machine learning algorithms to improve the location calculating capabilities of the system.
[01.29] In another embodiment, the system may infer the presence of humans in the network based on those humans interacting in some way with one or more of the computers on the network. In a further embodiment, the system may use the inferred presence of a human as an.
input for machine learning to improve its detection capabilities.
[01301 In an embodiment of a system according to the present disclosure, the system comprises a communication system which is capable of determining the presence, both static and moving, of one or more humans from information about the signals between two or more computers on the network where each computer consists of: a transceiver for communication;
and a computing element for performing calculations, where each computer sends signals to one or more other computers on the network where the signal includes a unique identifier of the computer sending the signal; where each computer processes the signals received for the purposes of determining the presence of one or more humans; where the one or more humans are not required to have on their person any device capable of communicating with the network.
[0131] In an embodiment, the algorithms use statistical methods to:determine the presence:of one or more humans. In another embodiment, the statistical methods determine the number of people present. In another embodiment, the system is capable of determining the physical location Of the one or more humans On the network. In another embodiment,: the System:: is opable of tracking the physical location Of the One or more humans over time.
En another embodiment, the system uses information about the presence of one or more humans to control devices on the network. in another embodiment, the information about the presence of one or more humans is made available to one: or More Systems not directly :inyOlved in the determination Of presente. In another: embodiment the system haS the abiki to per** self., optimization to achieve a given perfOrmance :according to one or more preset criteria.
[0132] In another embodiment, the communications protocols or network is generally defined by a standards committee including bin not limited to protocols such as Bluetoothml LOW
Energy, Win, Zigbee, Thread, and Z-Wave. In another embodiment, statistical methods are applied to a measure of received signal strength to determine the presence of a human. In another embodiment, the transmitting and receiving devices on the network may be selected and actnated by the system for the purpose of making human detection easier In another embodiment, the power levet of the tranSmitted signal May be controlled for making human presence egOer. In another embodiment, the::s-sisterrt: functions 0: an Neupancysensing system for a lighting system. In another embodiment, the occupancy sensing system controls a lighting system. In another embodiment, the network for controlling the lighting system and the network used for occupancy Sensing utilize the same communication technology and hardware.
[0133] In another embodiment, the system functions as a Oii.Otig system for a security application. In another embodiment, the security sensing system controls the security system.
In another embodiment, the network for controlling the security system and the network used for security ::sensing utilize the same communications technology and hardware. In another embodiment, the system functions as an occupancy sensor for a Heating.
Venting, and Cooling (HVAC) system. In another embodiment, the occupancy sensing system controls the HVAC
system. In another embodiment, the network for controlling the HVAC System and the netWork used. tbt occupancy sensing: utilize the same communications teem-3010g and hardware.
[0134] In another embodiment, the Systent iiks machine learning to improve its detection capabilitieS *here humans which have, a fiducial element on their person train the system through:. (1) using known location techniques to determine the lOcati on of the fiducial element;
(2) using the system :to *ate the 1)et's0ii.; (3) comparing the location calculated by (1) Of this paragraph to (2) of this paragraph; (4) adjusting the location determining methods using machine learning, algorithms to improve the location calculating, capabilities of the system.
[0135] In another embodiment, the system may infer the presence of humans in the network based on those humans interacting in some way with one of the computers on the network. Said interactions may be direct physical interactions or indirect interaction in response to some change of state in the system (e.g., waving arms in response to lights turning off). In another embodiment, the Osten" MO use the inferred presence Of a human as an inptit:for machine learning to improve its detection [0136] Also described herein is communication system which is apable Of determining the presence, both static and moving, of one or more humans in a detection network based on information about the Signals between two or more computers on the network where each Computer -e0risiStS Of 4 transceiver for communication; and, a coinputiq element for performing calculations, Where each computer sends Avid to one or: more :Other computers on the network where the signal includes a unique identifier of the computer sending the signal;
where each computer will process the signals received for the purposes of determining the presence of one or more humans in two or more ways to achieve different performance criteria as required to function for two or more purposes simultaneously; where the one or rnore humans are not required to have on their person any device capable of cornmunicating with the network, [01371 In an embodiment, the algorithms use two or more statistical methods to determine the presence of one or more humans according to two or more sets of performance criteria. In another embodiment, the system has the ability to perform self-optimization to achieve a set of two or more performances according to two or more preset criteria. In another embodiment, the conimunications protocols or network is generally defined by a. standards committee including but not limited to protocols such as luetornhTM Low Energy, WiFi, Zigbee, Thread, and Z-Wave. in another embodiment, two or more statistical methods are applied to a measure of received signal strength to determine the presence of a human according to two or more sets of performance criteria. In another embodiment, the system uses machine learning to improve the detection capabilities of the two or more methods for determining presence where humans which have a fiducial element on their person train the system through: ( I) using known location techniques to determine the location of the fiducial element; (2) using the system to locate the person; (3) comparing the location calculated by (1) of this paragraph to (2) of this paragraph; (4) adjusting the location deteimining methods using machine learning algo[ it hms to improvd.thd location.calculating capabilities Of the syStetn, [0138] n an embodiment, the systems and methods described herein include change detection.
By way of example and not limitation, chat= detection may use or utilize a rolling baseline approach. In such an embodiment, a first baseline is established and compared with a second baseline, and any. differences between the first and second baselines caused by the presence of a human in the detection network may be recognized by the system. This may be done by programming software to receive sets of wireless signal characteristic data from one or more nodes in the detection network and, based on such data, detecting changes in the RI' environment caused by a human being present in a different position when thefirstbaseline is established as compared to the second baseline. Such methods may be utilized when a system is first setup in a location to establish a minimal performance level without requiring a space be empty upon startup:: Such Vaal-lg. With Change detection may improve Overtime to a State between change and presence where limited aspects Of presence :detection may be present in such a system.
[0 139] An exemplary illustration of change detection is depicted in FIG 3A, In the depicted embodiment of :FIG:. 3A, the RIF' enViromni.nit Of FIG. 1 is shown with, a human (301) present in the erivirontnent (103) at a discreet position 303'l M.:(iesCribed elsewhere in this disclosure, the charadteristics of Wireless Signal transmissions among the nodes (107A)16 (107D) is influenced by the presence of the human (301). In this particular example, transmissions between node A (107A) and node D (107D) are influenced by the presence of the human (301 ).
Thus, when the baseline is established (211) as shown in the method of FIG. 2, the baseline represents the wireless signal characteristics while the human (301) is present at the discreet position (303). If the human (301) moves to a new position (305), as can be seen if FIG, 3A, the. characteristics OfWireless signals among the nodes (1 07A) to (107D):Will change.
[0140] In this particular exemplary ern bod merit: therev:Vill be little interference between nodes:
A:(L07A) and D (107D) when the human is at position (305). HoWever, there will be greater interference between nodes B (107B) and C (107c),: because the position:(305) is disposed between those two nodes. Thus, when the differences are detected (205) as shown in FIG. 2, the change in position:of the latitilan can be detected.
[0141] nit is I.eSS difficult to implement than presence sensing because the heed to establish baselines in the detection network (103) without a human present is reduced.
Such a system may detect changes within the detection network (103) based primarily on when a human changes positions, and updating the operative baseline profile on a rolling basis. That is, the baseline:(211)is updated in this embodiment to be equal to the baseline when the human (301) is at position (305). Thus, when the human (301) moves to a third position (307), the differences detected (215) are as between the second baseline taken at position (305) and the wireless sigma characteristics of detection network : (103) when the human is at position (307) Likewise; the baseline (21 1) has been updated to be equal to the baseline in position (307),: Which can then be used to detect further tbanges M the position of a human (201). This detection method uses changes in the wireleSii$Ipial baselines (*wed by changes in the position of a human (01) in the. detectiOn (103). This system has many advantage. over prior art motion detection technologies, such as passive infrared, in that this system is not obscured by objects 0.0t4i#
detect Slow Of gradual changes in position, which may be overlooked by prior ail Systems. in an embodiment using this methodology, the baselines may be continuously updated.
[01412] In another embodiment, the system or method comprises making a confidence determination. This aspect may determine a degree of confidence that a third baseline corresponds to either a first or second set of baselines, The confidence determination may use any number of techniques, including techniques known in the art, such as supervised training or the use of statistical methods to determine a degree of similarity or difference. between data sets. The confident* May increase Or decrease esVer.: ,time, allowing for decisions to be auton*ticoUy:olade, *th reSpectle baseline differences that are minimally different, but may still indicate the presence of a human in the detection network 003):
Confidence in a determMation of presence or abscmce of a human in the detection network (103):
may be determined based on how similar a third baseline is to a first or second baseline. For example, if a third baseline is known to: indicate the *Sent of a mass whose impact on signal characteristics is known, comparing the first or second baseline to the third may improve (or decrease) the confidence level that the identified mass is the same as the mass identified in the third baseline. Based on confidence, the system can be configured to use different confidence thteShORIS in different operational contexts (e.g:, HVAC, security, lighting, .safety, etc), A
system or method including a confidence determination may operate across a plurality of systems using a common communication system, wherein the systems can include disparate nodes in communication with one another. A given node May operate in a plurality of detection networks (103), allowing for better system scaling when deploying. the systents and methods to multiple adjacent detection networks (103).
[0143] In another embodiment, baseline diMrences may be used to count or estimate the number of humans present in the detection network. In an embodiment, this may be done by estimating the amount of human mass in the detection network, and dividing by an average mass per person. This may be done by establishing a first, empty baseline when there are no humans in the detection network (103), and establishing a second, occupied baseline when some known number of humans are present in the detection network (103). Next, a third baseline is taken and compared to the first empty baseline and the second occupied baseline_ The system software then interprets where the third baseline wireless signal characteristics fit on a spectrum of profiles between the first empty baseline and the second occupied baseline, and from that determination estimate the total amount of human mass in the detection network This estimation may be based upon the total mats of humans in the detection network when the second occupied baseline was established.
[0144] By way of example and not limitation, if the signal distortion in the third baseline is moderate as compared to the first empty baseline, the system may estimate that the amount of human mass present is relatively low. However, if the amount of signal distortion is closer to that shown in the second occupied baseline, the system may determine that the estimated amount of human mass present in the detection network (103) is closer to the amount that was present when the second baseline was taken. Similarly, if the amount of distortion is determined to be even more extreme than that reflected in the second baseline, the system may determine that the total amount of human mass present when the third baseline was taken exceeds the amount present when the second baseline was taken. The estimation of human mass may be based broadly upon the algorithms and methods described herein, and adjusted to estimate a number of humans in a space as generally described above.
[0145] In another embodiment, a system uses entrance and exit signatures in network diapostic information to estimate the number of humans present in a space based upon such signatures.
[0146] In such a method, an entrance profile is established by a human entering a space, an exit profile is established by a human leaving the same space, and another later-captured profile is compared to the entrance and exit profiles to determine whether a human has entered or exited the space. Entrance and exit profiles are learned through normal system operation, based upon estimation from the presence detection technology and its determination following a state change. By way of example and not limitation, if a system detects a change and presence goes from not being detected to being detected, such an event may be classified as an entrance.
Similarly, by way of example and not limitation, if the system detects a change and determines that a space has gone from occupied to unoccupied, such an event may be classified as an exit.
The difference between entrance count and exit count may be used to estimate the number of humans present in the space.
[0147] In another embodiment, a. system uses entrance and exit signatures in network diagnostic information in combination with people count estimates derived from comparing a sample profile against presence profiles of varying people counts.
[0148] Each of these methods may be used in anti unction with one or more counting methods to enhance the accuracy.
[0149] In an embodiment, the count or estimate of humans present in the detection network::
(103) may be used to operate another system, such as, hut not necessarily limited to, a HVAC, system, [0150] In an embodiment, the location or poSitiOn a a human in the detection netWOrk, IS:
estimated. This may be done by estimating the range between various devices to determine the location of a human,: examining subset detection areas Constructed from higher numbers of nod*: using various location baselines,: and further extending the fiinction of a location system to analyze locations Over time to estimate speed and direction. of a human in the detection network. In one embodiment: Of such a method, the system .to4y: use VatiOns :node pairs, estimating the, position of a human between those pairs based on baseline information, Wine overlapping estimates within the node pairs, then determining a highest probability position for a human in the detection network based on those overlapping estimates to determine the actual location of the human.
[0151] In another embodiment, systems with larger number of nodes can use more subset detection areas, generally each with three or more nodes, to determine the presence or absence of a human in each space, and estimate location based. on overlapping occupied areas wherein the common occupied space might be assumed to be the most Specific WOO .o.r a human in the deteetiOn netwOrk. By way: Of example and not limitations Set of fOttr nodes may be subdivided into four sets of three nodes, where location maybe determined based upon which :subsets of three nodes presence is detected within. This sub-area creation allows for detections within subareas where Such sub-shapes are defined by overlapping:. areaS
(treated With sets of three Or more nodes. Alternatively, a plurality Of baselines for humans in different locations within a detection network may be established, with subsequent baselines compared against said baselines to determine the location within the detection network of a human. By way of example and not limitation, a detection profile play be created for various locations within a detection area where a given detection profile corresponds with a human in a given position within the network, a sample profile is compared against a set of detection profiles corresponding to different positions, the system determines which detection profiles correlate most with the sample profile, and the system makes a determination of the location of the human based on the location of the detection profiles deemed most similar to the sample profile.
[0152] Additionally, based on detected changes in locations of humans in the detection network over time, a human's travel speed and dirtvtion in the detection network may be estimated. This may be done, for exampleõ through the use of interpolation and dead reckoning, or direct reconnaissance. An exemplary embodiment of such a system and method is depicted in FIG, 3B, In the depicted embodiment, a human is located in a detection network (103) at position (401) at Timeo. At a subsequent point in Timei, the Human is detected at a different position (403). Because position (401) and position (403) are known, a Distance' between them can be calculated. Additionally, the amount of time elapsed from Time to Time can be determined or is known. Given that distance equals rate times time, the rate of movement of the human from position (401) to position (403) can be determined.
Additionally, a Vector could be determined representing the movement of the human, embodying both direction and magnitude (speed).
[0153] Having oily twc, sample points,. however, faise,s the possibility of a high error rate, and more than two sample points is desired. For example, in the depicted embodiment, a third profile taken at Time, places the human at position (405). Again, the Distance2 from position (403) to position (405) can be determined, and arate of speed between these positions may also be determined. In the depicted embodiment, these positions are generally linear, suggesting that the human is rfloviriR in a more or less straight line in a given direction, defined by Vector.
The system may thus further estimate the future or expected position of the human based on this data, That is, at Times an estimated position (407) of the human may be determined based on the prior detected locatiorm This estimate may place the human outside of the detection network (103), and may be further used to estimate the arrival or departure of a human in or from the detection network (103). Additionally, this information may be used to alert another segment of the detection network, or another detection network entirely, of a:potentially soon to be arriving human, This may be done, tir example by communications using the computer server (109) via the network (115).
[0154] Continuing the Owmplary embodiment above, in the depicted embodiment, the human's detected change in position from Timer to Timei Js 0. meters %eters it one secoti,i. for a speed :of .8 meters per second. 'fhe detected change in distance fitoti Timei to Tim 02 is meters, with one additional elapsed second, or, 2.0 total meters Over twO
total elapsed seconds, for an average speed of one meter per second. Thus, at Times, one second later, an additional one meter of movement may be anticipated, making the estimated future position (407) one meter further along Vector than position (405).
[0155] In an embodiment, the systems and methods use machine learning to further train the system over time. By way of example and not limitation, a system may accumulate data from one or more of the above.-described Change detection techniques using a combination of knOwt feedback and/or feedhatkfrOm third pattySystenis:sOch as hut nOt limited to interactions With:
other Smart deviceS:(thermostatSõ: yoke recognitiol:sy#00$; 00. andlor ttse inference icer time to improve operation based on expected or anticipated system behavior.
Such inferences may be based upon ordinary behavior in a space: direct human interaction with elements of the system, :Or Sample:profile changes from human reactions to system decisions.
By Way of example and not limitation, in a ,s,Stem implementing change detection to operate lighting or HVAC systems, user feedback may be provided to the system as supervised training data, indicating whether a given operation was correct (i.e., whether a change in the lighting or I-1VAC system should have been made or not).
[0156] Similarly, hi a system implementing presence detection; a ,t1Ser may force change detection to trigger while within a detection network, providing the system an automated means to establish a baseline practice for the occupied space based upon the time that change riggerinlevenis occur and, faCilitating times far removed from change triggering events to be detected ag generally otopty When cOnibined with infecting OcCupancy based on roOtn: type,, such a I nethod may facilitate he system training itself, improving fortetibmdiiy over time from change detection to presence detection level functionality. Effectively, by using the system based on change detection, the system may infer presence and absence, allowing it to establish baseline profiles for when no tOiltn is present and detection: profiles based on When there is a human present. In such a way, the system would be capable of training hell to move from operating as a change detection system into one operating as a true presence detection system, [0157] In an embodiment implementing counting, combinations of change detection and presence detection may determine an estimated count of humans within a detection network, estimating such counting baseline profiles and improving them over time. Such a system may thcilitate the system training itself over time to count the number of humans within the detection network [0158] In an embodiment implementing, locating people, Combinations Of Change detection, prOsen(e detection, and counting people may be utilized to determine eStnnateS
Of location based on overlapping areas and occupancy counts eventually establishing more accurate baseline !eatirnateS, ollowing the system over time to improve Tocatina humanS
Within lA
detection netµVork. Such a sy!nem may comprise an inference :
Such as computer = Software running on the serVet; and/or build an estimation of expected system operation from normal operations, and may adjust operational parameters in accordance with expected behavior. For example, if a detection area is typically empty from I 0:00am until 3:00pm, and occupied from 3:00pm until 6:00pm, parameters may be adjusted to expect emptiness from 10:00aim3:00pm and to expect presence from 3:00pm until 6:00pr4 Such inferences may be:
developed over time and may improve performance at those times, while maintaining overall flex [01591 Nodes may be disposed in. various location combinations to improve system operation:
A system may Operate with nodes located on walls, ceilings, 'liked nodes, mobile nodes, and/or in mixed configurations. Because spaces are three-dimensional, detection areas may be defined by nodes on ditierent floors of a building. Nodes may be placed on wails in POsitiOns such as:
Switches and outlets. The broadcast range generally defines the perimeter :Of a detection areas and the system May be configured to exaMinenettyork. diagnostics aSstttning humans are within said perimeter.
[0160] In an embodiment, one or more nodes may be placed on a:ceiling. By way ofeXample and not limitation, this might occur when nodes are integrated into fixtures and/or lighting systems. in such an embodiment, nodes may radiate generally downward into the detection area, and a system may be configured to examine network diagnostics based on different radiation and multi-path patterns than might be seen from a switch and outlet based system. In such an embodiment, nodes generate communications:in:A generally dOgniWard direction where reflections from *ati$, objeot , and fit** generally ensure that the RI energy reaches other nodes yialmiltipath The multipath also generally provides for cOverage of the detection area, Such coverage due to multipath means that ceiling mounted nodes function similarly to wAli mounted nodes with regards to the impact Of a human on network diagnostic information.
[0161] Other fixed nodes are also contemplated, such as, Ottibilt televisions;
monitot*atid; smart home !nibs. Such nodes May be installed on A wall, ceiling, or at a fixed location. Still other nodes, such as smartphones, tablets, and laptop computers, may be used in a detection network as a mobile node. However, in such an embodiment, a mobile node may first locate itself relative to fixed nodes in the system_ Having its location established within the network may further enhance the accuracy of the system.
[0162] In an embodiment, combinations of nodes may be used in a detection area. When combining larger number of nodes, the system may determine the optimal nodes for operation.
Optimal nodes may be determined by, among other things, determining the most efficient nodes for a chosen level of functionality. As node count increases, accuracy of cletennimaion gem rally increases, as does level of functionality, [0.16:3] in an enibodi merit one. or more nodes may operate in a plurality of detection areas. This facilitates improved system scali ng, particularly for adjacent detection areas.. Such scaling may additionally result in inference within a larger network of nodes including the plurality of detection areas, further facilitating the tracking of human detections front one detection area to the next. For example, nodes may be shared between detection areas_ A given node in a first detection network may have network diagnostic information based on communications within said first detection area, and may also be part of a second detection network and have network diagnostic information based on communications within said second detection network, The system can make independent decisions on how to operate third party systems in each of the two detection areas. Examining inference across detection areas can improve the determination of the presote or absence of humans within the detection areas, particularly when. a person leaves one detection area and enters another. Detected changes in signal characteristics can be used to determine the presence or absence of a human in the individual areas, based on information shared between the first and second detection area [0164] In an embodiment, the systems and methods may operate through the use of a mass identification technique. In such an embodiment, a "mass" is identified and tracked. A unique identity may be assigned to the mass by the computer systems, and tracked based on changes to wire:less signal characteristics. By way of example, and not limitation, if a mass is first detected near the center of a room, and next detected at a location several feet away from the:
center of the room, but the system has not detected any other masses as entering the room, the system may infer that the second detected mass is the same mass as the first detected mass, but has relocated to a new position. Based on the difference in signal characteristics caused by the interference of the mass in the network, the system may infer, for example, that other Masse*
exhibiting similar movement would have similar effects on the signal characteristics. In this :way, the system can "leart" hp* to identify a mass, and track. it.
[01.45] Although each human mass in the system Causes different interference characteristics when disposed at any locatiOk for most indoor locations, the total set of humans likely to be present in a room is generally finite. That is most indoor spaeeSate, for any appreciable length of time, occupied by the same basic set of people most of the time, with only minor and infrequent variations. For example, the same set of people generally show up each day to a workplace, or a school, or even a public location such as a restaurant.
Because most indoor spaces can only be entered from a limited number of points of entry, such as doorways, the system can detect a person entering at the point of ingress, and determine the specific interference :pattern caused by: the presence of that particular human upon entering the spate.
Based on the signal characteristics (interference ) and the vvay that those characteristics Change = totripare4 to other hunlansin the *ee,it On be determined where and hoW
each human trfass:
moves through the room.
[0166] It is c.ontemplated that a system may automate varions aspectS Of setup, particularly:
with regards to grouping nodes: into detection areas and building levels of functionality nominally based on the machine learning methods described herein. A system Which determines nearest nodes and estimates detection areas through inference requires no setup by a user. Based upon best estimates, a user may simply place nodes throughout a building, and the nodes automatically group into detection areas using unsupervised machine learning, ultimately resulting in a building system learning, how to detect occupants, Occupancy can then be related to actions taken by occupants, developing an automation system which reduces or eliminates the need for human input for normal system operation, [01.67] In an embodiment, the method is a method for detecting the presence of a human comprising: providing a first transceiver disposed at a first location within a= detection area;
providing a second transceiver disposed at a second location within said detection area; a computer server communicably coupled to said firs t.nanseeiver; said first transceiver receiving a first set of wireless signals from said second transceiver; said computer ser,, er: receiving a first set of signal data from said first tmnsceiver, said first set of signal data.comprising data about properties of said first set of wireless signals; inferring that said first Set of signal data is indicative of the presence of a human in said detection area; creating a detection signal profile .fir wireless communications from said second transceiver to said first transceiver based at least in part on said properties of said first set of wireless signals in said first set of signal data when a human is inferred present in said detection area: said first transceiver receiving a second set of wireless signals from said second transceiver; said computer server:
receiving a second set of signal data from said first transceiver, said second set of signal data comprising data about properties of said second set of wireless signals; infening that said second set of signal data is indicative of the absence of any humans in said deteetion area; creating a baseline signal profile for wireless communications from said second transceiver to said first transceiver based at least in part on said properties of said second set of v,eireless signals in said second set of signal data when the absence of any humans in in said detection area is infermd; said rust transceiver receiving a third set of wireless signals from said second transceiver; said computer server receiving a third set of signal data from said first transceiver, said third set of signal data comprising data about properties of said third set of wireless signals;
determining whether said third set of signal data is indicative of the presence of a human, or absence of any humans, in said detection area, said determining based at least in part a comparison of said third set of signal data to said detection signal profile and said baseline signal profile, [0168] In a further embodiment, the method comprises: in said inferring that said first set of signal data it indicative of the presence of a human in said detection area, said inferring is based at leaStin part on additional Signal data Sets for signals received by said first transceiver from other transceivers in the detection area; and in said inferring that said second set of signal data is indicative Of the absekeof any humans in said detection area, said inferring is based at least in part on additional Signal data sets for signals received by said first:
transceiver from other transceivers in the detection area.
[0169] In a further embodiment, the method comprise: Said Computer Server;
Storing aplurality of historical data records indicative of whether a human was determined to be present in said detection area over a period of time, each of said historical data records comprising an indication of a number of humans determined to be present in said detection area and a date and time when each of said number of humans was determined to be present in said detection area; and said computer server making at least some of said plurality of historical data records available to One Or more edema] computer systems Via an interface, [0170] In a Anther embodimeOt:The method cotnpriSek Said computer s'erver IS
operatively COUPled to a:SecOnd system; and otflyafterSaid computer seryer:determinesa homan is present in said detection area, said computer server: operates said second system.
[0171] In a further embodiment, the method comprises: said tirst transceiver and said second system are configured to communicate using an identical eommunicationprotbea [0172] In a further embodiment, the method comprises: Said second sySteM is Selected from the group consisting of: an electrical system; a lighting system; a heating, venting, and cooling (11VAC) system; a security system; and, an industrial automation system.an electrical system.
[0173] In a further embodiment, the method comprises: said wireless communication utilizes a protocol selected from the group consisting of: BluetoothTM. BluetoothTm Low Energy, ANT, ANT+, WiFi, Zigbee, Thread, and Z-Wave, [0174] In a further embodiment, the method comprises: said wireless communications from said second transceiver to said first transceiver have a carrier frequency in the range of 850 MHz and 17,5 G Hz inclusive.
[0175] In a further embodiment, the method comprises: said computer server determining whether said third set Of signal data is indicative of the presence of a human includes a confidence metric.
[0176] In a further embodiment, the method comprises: said first transceiver and said second transceiver are configured to calculate their relative positions within said detection area automatically.
[0 177] In, another embodiment, the method comprises a method for estimating the number of humans present in an area comprising: providing a first transceiver disposed at a first location within a detection area; providing a second transceiver disposed at a second location within said detection area; a computer server communicably coupled to said first transceiver., said first transceiver receiving a first set of wireless signals from said second transceiver when no humans are present within said detection area; said computer server receiving It first set of signal data from said first transceiver, said first set of signal data comprising data about properties of saki first set of v,eireless signals; said computer server creating a baseline signal profile for wireless communications from said second transceiver to said first transceiver, said baseline signal profile being based at least in part on said properties of said first set of wireless signals in said first set of signal data when no humans are present in said detection area; said first transceiver receiving a second set of wireless signals from said second transceiver when a first plurality of humans is present in said detection area, said first plurality of humans having a total mass; said computer server receiving a second set of signal data from said lint transceiver, said second set of signal data comprising data about properties of said second set of wireless signals; said computer server creating a second baseline signal profile for wireless communications from said second transceiver to said first transceiver, said second 'baseline signal profile being based at least in part on said properties of said second set of wireless signals in said second set of signal data. when said first plurality of humans is present in said detection area; said first. transceiver receiving a third set of wireless signals from said second transceiver when a second plurality of humans is present within said detection area; said computer server receiving a third set of signal data from said first transceiver, said third set of signal data comprising data about properties of said third. set of wireless signals; said computer server estimating the total mass of said second plurality of humans, said estimating based at least in.
part on a comparison of said properties of said third set of wireless signals in said third set of wireless signal data to said baseline signal profile and to said baseline signal profile; said computer server estimating the total number of humans in said plurality of humans based at least in part on dividing said estimated total mass of said plurality of humans by an average mass per human.
[0178] In a further embodiment, the method comprises: said computer server estimating the total mass of said second plurality of humans is further based at least in part on a comparison of said properties of said third set of wireless signals in said third set of wireless signal data to said properties of said second set of wireless signals in said second set of wireless signal data.
[0179] :In a further embodiment, the method comprises: said properties of said first set of wireless signals, said second set of wireless signals, and said third set of wireless signals comprise wireless network signal protocol properties determined by said first transceiver.
[0180] In a further embodiment, the method comprises: each or said wireless network signal protocol properties is selected from the group consisting of: received signal strength, latency, and bit error rate, [0181] In a father embodiment, the method comprises: said 'computer server :estimating Comprises interpolating the total T1 14$ S of humans in said 'second plurality Of hair!**
[0182] in a further embodiment, the method comprises: said interpolating uses an assumed nias :of zero for said baseline signal profile and said total mass of humans in said first plurality of humans for said second baseline signal profile.
[0183] In a further embodiment, the method comprises: Said total MOS is a discrete user, supplied quantity.
[0184] T In a further embodiment, the method comprises: said average mass per human is 0 discrete user-supplied quantity.
[0185] In a further embodiment, the method comprises: said computer server storing a plurality of historical data records indicative of whether a human was present in the detection area over a period of time, each of said historical data records comprising an indication of a number of humans deeded in said detection area and a date and time when each Of said number of humans was detected in Said detection area, and said computer !.-lerVer Making at least some Of said plurality of historical data:records:n*1We to one Orrnore external cOmputet7systeois yin an interface:
[0186] In a further embodiment, the method comprises: said computer server estimating the total mass of said second plurality of humans is adjusted based on machine learning comprises:
determining a first sample total mass Of a plurality of humans having a fiducial element in Said detection area, said first sample mass being determined based upon detecting said fiducial element; determining a second sample total mass of said plurality of humans in said detection area, said second sample mass being determined based at least in part on a comparison of said received second set of signal data to said baseline signal profile; comparing said first sample mass and said second sample mass; and adjusting said estimation of said total mass of said second plurality of humans based upon said comparing.
[0187] In a further embodiment, the method comprises: said computer server estimating the total mass of said second plurality of humans is adjusted based on machine learning comprises:
determining a first sample total mass of a plurality of humans based on inferences in said detection area; determining a second sample total mass of a plurality of humans in said detection area, said second sample mass being determined based at least in part on a comparison of said received second set of signal data to said baseline signal profile;
comparing said first sample mass and. said second sample mass; and adjusting said determination of said second sample mass based upon said comparing.
[0188] In a further embodiment, the method comprises: said determining a .first sample location of a human based on inference in said detection area comprises said computer server inferring from a detected operation of a network element in said detection area that a human is present in said detection area near said network element.
[0189] In a further embodiment, the method comprises: said network component is a component of an electrical system, a lighting system, a heating, venting, and cooling (FIVAC) system, a security system, or an industrial automation systent [0190] In a further embodiment, the method comprises: n said estimating the total number of humans in said plurality of humans includes a confidence metric.
[0191] :In a further embodiment, the method comprises: said first transceiver and said second transceiver are configured to calculate their relative positions within said detection area automatically.
[0192] In a further embodiment, the method comprises: said Vvireless:communication utilizes a protocol selected from the group consisting of: BluetoothTm, BluetoodiTm Low Energy, ANT, ANT+, Wi Fi, Zigbee, Thread, and Z-Wave, [01931 In afather embodiment, the method comprises: said wireless cOmmunications from said second transceiver to Said firStlranscei vet have a carrier frequency in the range of 850 MHz and 1'7,5 Gliz inclusive.
[0194] While the invention has been disclosed in conjunction with a description of certain embodimentS; including those that are currently t*iieed to be preferred embodiments, the demi ied deseription is intended to be illustrative :add Siithild not be utWerStobd tOttit the scope of the present &Closure. As would be understood by one of ordinary skill in the art, embodiments other than those described in detail herein are encompassed by the present invention. Modifications and variations of the described embodiments may be made without departing from the spirit and scope of the invention.
Claims (75)
1. A method for detecting a presence of a human comprising:
providing a first transceiver disposed at a first location within a detection area;
providing a second transceiver disposed at a second location within said detection area;
a computer sever communicably coupled to said first transceiver;
said first transceiver receiving a first set of wireless signals from said second transceiver when a human is present within said detection area at a first position;
said computer server receiving a first set of signal data from said first transceiver, said first set of signal data comprising data about properties of said first set of wireless signals;
said computer server creating a baseline signal profile for wireless communications from said second transceiver to said first transceiver, said baseline signal profile being based at least in part on said properties of said first set of wireless signals in said first set a signal data when said human is present in said detection area at said first position;
said human moving from said first position to a second position in said detection area;
said first transceiver receiving a second set of wireless signals from said second transceiver when said human is present at said second position;
said computer server receiving a second set of signal data from said first transceiver, said second set of signal data comprising data about properties of said second set of wireless signals;
and said computer server determining if the position of said human in said detection area has changed, said determination based at least in part on a comparison of said properties of said second set of wireless signals in said second set of wireless signal data to said baseline signal profile.
providing a first transceiver disposed at a first location within a detection area;
providing a second transceiver disposed at a second location within said detection area;
a computer sever communicably coupled to said first transceiver;
said first transceiver receiving a first set of wireless signals from said second transceiver when a human is present within said detection area at a first position;
said computer server receiving a first set of signal data from said first transceiver, said first set of signal data comprising data about properties of said first set of wireless signals;
said computer server creating a baseline signal profile for wireless communications from said second transceiver to said first transceiver, said baseline signal profile being based at least in part on said properties of said first set of wireless signals in said first set a signal data when said human is present in said detection area at said first position;
said human moving from said first position to a second position in said detection area;
said first transceiver receiving a second set of wireless signals from said second transceiver when said human is present at said second position;
said computer server receiving a second set of signal data from said first transceiver, said second set of signal data comprising data about properties of said second set of wireless signals;
and said computer server determining if the position of said human in said detection area has changed, said determination based at least in part on a comparison of said properties of said second set of wireless signals in said second set of wireless signal data to said baseline signal profile.
7. The method of claim 0, wherein said properties of said first set of wireless signals comprise wireless network signal protocol properties determined by said first transceiver.
3. The method of claim 0, wherein, said each of said wireless network signal protocol properties is selected from the group consisting of: received signal strength, latency, and bit error rate.
4. The method of claim 0, further comprising:
said human moving to a new position in said detection area;
said first transceiver receiving a new set of wireless signals from said second transceiver when said human is present in said detection area at said new position;
said computer server receiving a new set of signal data from said first transceiver; said new set of signal data comprising data about properties of said new set of wireless signals;
said computer server replacing said baseline signal profile with a new baseline signal for wireless communications from said second transceiver to said first transceiver when said human is at said new position, said second baseline signal profile being created based at least in part on said properties of said new set of wireless signals in said new set of signal data when said human is present in said detection area at said new position.
said human moving to a new position in said detection area;
said first transceiver receiving a new set of wireless signals from said second transceiver when said human is present in said detection area at said new position;
said computer server receiving a new set of signal data from said first transceiver; said new set of signal data comprising data about properties of said new set of wireless signals;
said computer server replacing said baseline signal profile with a new baseline signal for wireless communications from said second transceiver to said first transceiver when said human is at said new position, said second baseline signal profile being created based at least in part on said properties of said new set of wireless signals in said new set of signal data when said human is present in said detection area at said new position.
5. The method of claim 0, further comprising: before said computer server replacing said baseline signal profile with said new baseline signal, said computer server storing a historical data record of said baseline profile.
6. The method of claim 0, wherein said stored historical data record is indicative a said human being detected in said detection area and comprises a date and time when said humans was detected in said detection area.
7. The method of claim 0, repeating said moving, receiving, and replacing steps one or more times.
8. The method of claim 0, wherein said computer server determining if the position of said human in said detection area has changed is adjusted based on machine learning comprises:
determining a first sample location of a human having a fiducial element in said detection area, said first sample location being determined based upon detecting said fiducial element;
determining a second sample location of said human in said detection, area, said second sample location being determined based at least in part on a comparison of said received second set of signal data to said baseline signal profile;
comparing said first sample location and said second sample location; and.
adjusting said determination of said second sample location based upon said comparing.
determining a first sample location of a human having a fiducial element in said detection area, said first sample location being determined based upon detecting said fiducial element;
determining a second sample location of said human in said detection, area, said second sample location being determined based at least in part on a comparison of said received second set of signal data to said baseline signal profile;
comparing said first sample location and said second sample location; and.
adjusting said determination of said second sample location based upon said comparing.
9. The method of claim 0, wherein said computer server determining if the position of said human in said detection area has changed is adjusted based on machine learning comprises:
determining a first sample location of a human based on inferences in said detection area;
determining a second sample location of said human in said detection area, said second sample location being determined based at least in part on a comparison of said received second set of signal data to said baseline signal profile;
comparing said first sample location and said second sample location; and adjusting said determination of said second sample location based upon said comparing.
determining a first sample location of a human based on inferences in said detection area;
determining a second sample location of said human in said detection area, said second sample location being determined based at least in part on a comparison of said received second set of signal data to said baseline signal profile;
comparing said first sample location and said second sample location; and adjusting said determination of said second sample location based upon said comparing.
10. The method of claim 9, wherein:
said determining a first sample location of a human based on inference in said detection area comprises said computer server inferring front a detected operation of a network element in said detection area .that a Inman is present' it said detection area near said network element
said determining a first sample location of a human based on inference in said detection area comprises said computer server inferring front a detected operation of a network element in said detection area .that a Inman is present' it said detection area near said network element
11. The method of claim 10, wherein said network component is a com.ponent of an electrical system, a lighting system, a heating, venting, and cooling (HVAC) system, a security system, or an industrial automation system,
12. The method of claim 0, further comprising.
said computer server storing a plurality of historical data records indicative of whether a human changed locations in the detection area over a period of time, each of said historical data records comprising an indication of a number of humans detected in said detection area and a date and time when each of said number of humans was determined to have changed locations in said detection area; and said computer server making at least some of said plurality of historical data records available to one or more external computer systems via an interface.
said computer server storing a plurality of historical data records indicative of whether a human changed locations in the detection area over a period of time, each of said historical data records comprising an indication of a number of humans detected in said detection area and a date and time when each of said number of humans was determined to have changed locations in said detection area; and said computer server making at least some of said plurality of historical data records available to one or more external computer systems via an interface.
13. The method of claim 0, further comprising: said computer server being operatively coupled to a second system; and only after said computer server determines a human has changed locations in said detection area, said computer server operates said second system.
14, The method of claim 3, wherein said first transceiver and said second system are configured to communicate using an identical communication protocol.
15, The method of claim 0, wherein said second system is selected from the group consisting of; an electrical system; a lighting system; a beating, venting, and cooling (HVAC) system; a security system; and, an industrial automation system,
16. The method of claim 1, wherein said wireless communication utilizes a protocol selected from the group consisting of: Bluetooth.TM., Bluetooth.TM. Low Energy, ANT, ANT+, WiFi, Zigbee, Thread, and Z-Wave.
17. The method of claim 1, wherein said wireless communications from said second transceiver to said first transceiver have a carrier frequency in the range of 850 MHz and 17.5 GHz inclusive.
18. The method of claim 1 wherein said computer server determining if the position of said human in said detection area has changed includes a confidence metric.
39. The method of claim 3 wherein said first transceiver and said second transceiver are configured to calculate their relative positions within said detection area automatically.
20. The method of claim 1 where said first transceiver and said second transceiver are configured to define automatically a detection area including said first transceiver and said second transceiver,
21. A method for detecting the presence of a human comprising:
providing a first transceiver disposed at a first location within a detection area;
providing a second transceiver disposed at a second location within said detection area;
a computer server communicably coupled to said first transceiver;
said first transceiver receiving a first set of wireless signals from said second transceiver;
said computer server:
receiving a first set of signal data from said first transceiver, said first set of signal data comprising data about properties of said first set of wireless signals;
inferring that said first set of signal data is indicative of the presence of a human in said detection area;
creating a detection signal profile for wireless communications from said second transceiver to said first transceiver based at least in part on said properties of said. first set of wireless signals in said first set of signal data when a human is inferred present in said detection area;
said first transceiver receiving a second set of wireless signals from said second transceiver;
said computer server:
receiving a second set of signal data from said first transceiver, said second set of signal data. comprising data about properties of said second set of wireless signals;
inferring that said second set of signal data is indicative of the absence of any humans in said detection area;
creating a baseline signal profile for wireless communications from said second transceiver to said first transceiver based at least in part on said properties of said second set of wireless signals in said second set of signal data when the absence of any humans in in said detection area is inferred;
said first transceiver receiving a third set of wireless signals from said second transceiver;
said computer server receiving a third set of signal data from said first transceiver, said third set of signal data comprising data about properties of said third set of wireless signals;
determining whether said third set of signal data is indicative of the presence of a human, or absence of any humans, in said detection area, said determining based at least in part a comparison of said third set of signal data to said detection signal profile and said baseline signal profile.
providing a first transceiver disposed at a first location within a detection area;
providing a second transceiver disposed at a second location within said detection area;
a computer server communicably coupled to said first transceiver;
said first transceiver receiving a first set of wireless signals from said second transceiver;
said computer server:
receiving a first set of signal data from said first transceiver, said first set of signal data comprising data about properties of said first set of wireless signals;
inferring that said first set of signal data is indicative of the presence of a human in said detection area;
creating a detection signal profile for wireless communications from said second transceiver to said first transceiver based at least in part on said properties of said. first set of wireless signals in said first set of signal data when a human is inferred present in said detection area;
said first transceiver receiving a second set of wireless signals from said second transceiver;
said computer server:
receiving a second set of signal data from said first transceiver, said second set of signal data. comprising data about properties of said second set of wireless signals;
inferring that said second set of signal data is indicative of the absence of any humans in said detection area;
creating a baseline signal profile for wireless communications from said second transceiver to said first transceiver based at least in part on said properties of said second set of wireless signals in said second set of signal data when the absence of any humans in in said detection area is inferred;
said first transceiver receiving a third set of wireless signals from said second transceiver;
said computer server receiving a third set of signal data from said first transceiver, said third set of signal data comprising data about properties of said third set of wireless signals;
determining whether said third set of signal data is indicative of the presence of a human, or absence of any humans, in said detection area, said determining based at least in part a comparison of said third set of signal data to said detection signal profile and said baseline signal profile.
22. The method of claim 21, wherein:
in said inferring that said first set of signal data is indicative of the presence of a human in said detection area, said inferring is based at least in part on additional sig,nal data sets for signals received by said first transceiver from other transceivers in the detection area; and in said inferring that said second set of signal data is indicative of the absence of any humans in said detection area, said inferring is based at least in part on additional signal data sets for signals received by said first transceiver from other transceivers in the detection area,
in said inferring that said first set of signal data is indicative of the presence of a human in said detection area, said inferring is based at least in part on additional sig,nal data sets for signals received by said first transceiver from other transceivers in the detection area; and in said inferring that said second set of signal data is indicative of the absence of any humans in said detection area, said inferring is based at least in part on additional signal data sets for signals received by said first transceiver from other transceivers in the detection area,
23 The method of claim 21, further comprising;
said. computer server storing a plurality of historical data records indicative of whether a human was determined to be present in said detection area over a period of time, each of said historical data records comprising an indication of a number of humans determined to be present in said detection area and a date and time when each of said number of humans was determined to be present in said detection area; and said computer server making at least some of said plurality of historical data records available to one or more external computer systems via an interface,
said. computer server storing a plurality of historical data records indicative of whether a human was determined to be present in said detection area over a period of time, each of said historical data records comprising an indication of a number of humans determined to be present in said detection area and a date and time when each of said number of humans was determined to be present in said detection area; and said computer server making at least some of said plurality of historical data records available to one or more external computer systems via an interface,
24. The method of claim 21, wherein:
said computer server is operatively coupled to a second system; and only after said computer server determines a human is present in said detection area, said computer server operates said second system.
said computer server is operatively coupled to a second system; and only after said computer server determines a human is present in said detection area, said computer server operates said second system.
25. The method of claim 24, wherein said first transceiver and said second system are configured to communicate using an identical communication protocol,
26. The method of claim 24, wherein said second system is selected from the group consisting of: an electrical system; a lighting system; a heating, venting, and cooling (HVAC) system; a security system; an industrial automation system; and an electrical system.
27. The method of claim 21, wherein said wireless communication utilizes a protocol selected from the group consisting of Bluetooth.TM., Bluetooth.TM. Low Energy, ANT, ANT+, WiFi, Zigbee, Thread, and Z-Wave,
28, The method of claim 21, wherein said wireless communications from said second transceiver to said first transceiver have a carrier frequency in the range of 850 MHz and 17.5 GHz inclusive.
29. The method of claim 21 wherein said computer server determining whether said third set of signal data is indicative of the presence of a human includes a confidence metric.
30. The method of claim 21 wherein said first transceiver and said second transceiver are configured to calculate their relative positions within said detection area automatically.
31. A method for estimating the number of humans present in an area comprising:
providing a first transceiver disposed at a first location within a detection area;
providing a second transceiver disposed at a second location within said detection area;
a computer server communicably coupled to said first transceiver;
said first transceiver receiving a first set of wireless signals from said second transceiver when no humans are present within said detection area;
said computer server receiving a first set of signal data from said first transceiver, said first set of signal data comprising data about properties of said first set of wireless signals;
said computer server creating a first baseline signal profile for wireless communications from said second transceiver to said first transceiver, said first baseline signal profile being based at least in part on said properties of said first set of wireless signals in said first set of signal data when no humans are present in said detection area;
said first transceiver receiving a second set of wireless signals from said second transceiver when a first plurality of humans is present in said detection area, said first plurality of humans having a total mass;
said computer server receiving a second set of signal data from said first transceiver, said second set of signal data comprising data about properties of said second set of wireless signals;
said computer server creating a second baseline signal profile for wireless communications from said second transceiver to said first transceiver, said second baseline signal profile being based at least in part on said properties of said second set of wireless signals in said second set of signal data when said first plurality of humans is present in said detection area;
said first transceiver receiving a third set of wireless signals from said second transceiver when a second plurality of humans is present within said detection area;
said computer saver receiving a third set of signal data from said first transceiver, said third set of signal data comprising data about properties of said third set of wireless signals;
said computer server estimating the total mass of said second plurality of humans, said estimating based at least in part on a comparison of said properties of said third set of wireless signals in said third set of wireless signal data to said first baseline signal profile and to said second baseline signal profile;
said computer server estimating the total number of humans in said plurality of humans based at least in part on dividing said estimated total mass of said plurality of humans by an average mass per human.
providing a first transceiver disposed at a first location within a detection area;
providing a second transceiver disposed at a second location within said detection area;
a computer server communicably coupled to said first transceiver;
said first transceiver receiving a first set of wireless signals from said second transceiver when no humans are present within said detection area;
said computer server receiving a first set of signal data from said first transceiver, said first set of signal data comprising data about properties of said first set of wireless signals;
said computer server creating a first baseline signal profile for wireless communications from said second transceiver to said first transceiver, said first baseline signal profile being based at least in part on said properties of said first set of wireless signals in said first set of signal data when no humans are present in said detection area;
said first transceiver receiving a second set of wireless signals from said second transceiver when a first plurality of humans is present in said detection area, said first plurality of humans having a total mass;
said computer server receiving a second set of signal data from said first transceiver, said second set of signal data comprising data about properties of said second set of wireless signals;
said computer server creating a second baseline signal profile for wireless communications from said second transceiver to said first transceiver, said second baseline signal profile being based at least in part on said properties of said second set of wireless signals in said second set of signal data when said first plurality of humans is present in said detection area;
said first transceiver receiving a third set of wireless signals from said second transceiver when a second plurality of humans is present within said detection area;
said computer saver receiving a third set of signal data from said first transceiver, said third set of signal data comprising data about properties of said third set of wireless signals;
said computer server estimating the total mass of said second plurality of humans, said estimating based at least in part on a comparison of said properties of said third set of wireless signals in said third set of wireless signal data to said first baseline signal profile and to said second baseline signal profile;
said computer server estimating the total number of humans in said plurality of humans based at least in part on dividing said estimated total mass of said plurality of humans by an average mass per human.
32. The method of claim 31, wherein said computer server estimating the total mass of said second plurality of humans is further based at least in part on a comparison of said properties of said third set of wireless signals in said third set of wireless signal data to said properties of said second set of wireless signals in said second set of wireless signal data.
33. The method of. claim 31, wherein said properties of said first set of wireless signals, said second set of wireless signals, and said third set of wireless signals comprise wireless network signal protocol properties determined by said first transceiver.
34. The method of claim 31, wherein each of said wireless network signal protocol properties is selected from the group consisting of: received signal strength, latency, and bit error rate.
35. The method of claim 31, wherein said computer server estimating comprises interpolating the total mass of humans in said second plurality of humans.
36. The method of claim 31, wherein said interpolating uses an assumed mass of zero for said baseline signal profile and said total mass of humans in said first plurality of humans for said second baseline signal profile.
37. The method of claim 31, wherein said total mass is a discrete user-supplied quantity.
38. The method of claim 31, wherein said average mass per human is a discrete user-supplied quantity.
39. The method of claim 31, further comprising:
said computer server storing a plurality of historical data records indicative of whether a human was present in the detection area over a period of time, each of said historical data records comprising an indication of a number of humans detected in said detection area and a date and time when each of said number of humans was detected in said detection area; and said computer server making at least some of said plurality a historical data records available to one or more external computer system via an interface.
said computer server storing a plurality of historical data records indicative of whether a human was present in the detection area over a period of time, each of said historical data records comprising an indication of a number of humans detected in said detection area and a date and time when each of said number of humans was detected in said detection area; and said computer server making at least some of said plurality a historical data records available to one or more external computer system via an interface.
40. The method of claim 31, wherein said computer server estimating the total mass of said second plurality of humans is adjusted based machine learning comprises:
determining a first sample total mass of a plurality of humans having a fiducial element in said detection area, said first sample mass being determined based upon detecting said fiducial element;
determining a second sample total mass of said plurality of humans in said detection area, said second sample mass being determined based at least in part on a comparison of said received second set of signal data to said baseline signal profile;
comparing said first sample mass and said second sample mass; and adjusting said estimation of said total mass a said second plurality of humans based upon said comparing,
determining a first sample total mass of a plurality of humans having a fiducial element in said detection area, said first sample mass being determined based upon detecting said fiducial element;
determining a second sample total mass of said plurality of humans in said detection area, said second sample mass being determined based at least in part on a comparison of said received second set of signal data to said baseline signal profile;
comparing said first sample mass and said second sample mass; and adjusting said estimation of said total mass a said second plurality of humans based upon said comparing,
41. The method of claim 31 wherein said computer server estimating the total mass of said second plurality of humans is adjusted based on machine learning comprises:
determining a first sample total mass of a plurality of humans based on inferences in said detection area;
determining a second sample total mass of a plurality of humans in said detection area, said second sample mass being determined based at least in part on a comparison of said received second set of signal data to said baseline signal profile;
comparing said first sample mass and said second sample mass; and adjusting said determination of said second sample mass based upon said comparing.
determining a first sample total mass of a plurality of humans based on inferences in said detection area;
determining a second sample total mass of a plurality of humans in said detection area, said second sample mass being determined based at least in part on a comparison of said received second set of signal data to said baseline signal profile;
comparing said first sample mass and said second sample mass; and adjusting said determination of said second sample mass based upon said comparing.
42. The method of claim 21, wherein:
said determining a first sample location of a human based on inference in said detection area comprises said computer server inferring from a detected operation of a network element in said detection area that a human is present in said detection area near said network element
said determining a first sample location of a human based on inference in said detection area comprises said computer server inferring from a detected operation of a network element in said detection area that a human is present in said detection area near said network element
43. The method of claim 22, wherein said network component is a component of an electrical system, a lighting system, a heating, venting, and cooling (HVAC) system, a security system, or an industrial automation system.
44. The method of claim 31 wherein said estimating the total number of humans in said plurality of humans includes a confidence metric.
45. The method of claim 31 wherein said first transceiver and said second transceiver are configured to calculate their relative positions within said detection area automatically.
46. The method of claim 31, wherein said wireless communication utilizes a protocol selected from the group consisting of: Bluetooth.TM., Bluetooth.TM. Low Energy, ANT, ANT+, WiFi, Zigbee, Thread, and Z-Wave.
47. The method of claim 31, wherein said wireless communications front said second transceiver to said first transceiver have a carrier frequency in the range of 850 MHz and 17.5 GHz inclusive.
48. A method for detecting the presence of an object that affects RF
signals comprising:
providing a first transceiver disposed at a first location within a detection area;
providing a second transceiver disposed at a second location within said detection area; and a computer server communicably coupled to said first transceiver;
said first transceiver receiving a first set of wireless signals from said second transceiver when an object that affects RF signals is present within said detection area at a first position;
said computer server receiving a first set of signal data from said fast transceiver, said first set of signal data comprising data about properties of said first set of wireless signals;
said computer server creating a baseline signal profile for wireless communications from said second transceiver to said first transceiver, said baseline signal profile being based at least in part on said properties of said first set of wireless signals in said first set of signal data when said object that affects RF signals is present in said detection area at said first position;
said object moving from said first position to a second position in said detection area;
said first transceiver receiving a second set of wireless signals from said second transceiver when said object that affects RF signals is present at. said second position;
said computer server receiving a second set of signal data from said first transceiver, said second set of signal data comprising data about properties of said second set of wireless signals; and, said computer server determining if the position of said object that affects RF signals in said detection area has changed, said determination based at least in part on a comparison of said properties of said second set of wireless signals in said second set of wireless signal data to said baseline signal profile.
signals comprising:
providing a first transceiver disposed at a first location within a detection area;
providing a second transceiver disposed at a second location within said detection area; and a computer server communicably coupled to said first transceiver;
said first transceiver receiving a first set of wireless signals from said second transceiver when an object that affects RF signals is present within said detection area at a first position;
said computer server receiving a first set of signal data from said fast transceiver, said first set of signal data comprising data about properties of said first set of wireless signals;
said computer server creating a baseline signal profile for wireless communications from said second transceiver to said first transceiver, said baseline signal profile being based at least in part on said properties of said first set of wireless signals in said first set of signal data when said object that affects RF signals is present in said detection area at said first position;
said object moving from said first position to a second position in said detection area;
said first transceiver receiving a second set of wireless signals from said second transceiver when said object that affects RF signals is present at. said second position;
said computer server receiving a second set of signal data from said first transceiver, said second set of signal data comprising data about properties of said second set of wireless signals; and, said computer server determining if the position of said object that affects RF signals in said detection area has changed, said determination based at least in part on a comparison of said properties of said second set of wireless signals in said second set of wireless signal data to said baseline signal profile.
49. The method of claim 48, wherein said properties of said first set of wireless signals comprise wireless network signal protocol properties determined by said first transceiver.
50. The method of claim 49, wherein each of said wireless network signal protocol properties is selected from the group consisting of: received signal strength, latency, and bit error rate.
51. The method of claim 48, wherein said object that affects RF signals comprises a weapon.
52. The method of claim 48, further comprising:
said object that affects RF signals moving to a new position in said detection area;
said first transceiver receiving a new set of wireless signals from said second transceiver when said object that affects RF signals is present in said detection area at said new position;
said computer server receiving a new set of signal data from said first transceiver, said new set of signal data comprising data about properties of said new set of wireless signals;
said computer server replacing said baseline signal profile with a new baseline signal for wireless communications from said second transceiver to said first transceiver when said object that affects RF signals is at said new position, said second baseline signal profile being created based at least in part on said properties of said new set of wireless signals said new set of signal data when said object that affects RF signals is present in said detection area at said new position.
said object that affects RF signals moving to a new position in said detection area;
said first transceiver receiving a new set of wireless signals from said second transceiver when said object that affects RF signals is present in said detection area at said new position;
said computer server receiving a new set of signal data from said first transceiver, said new set of signal data comprising data about properties of said new set of wireless signals;
said computer server replacing said baseline signal profile with a new baseline signal for wireless communications from said second transceiver to said first transceiver when said object that affects RF signals is at said new position, said second baseline signal profile being created based at least in part on said properties of said new set of wireless signals said new set of signal data when said object that affects RF signals is present in said detection area at said new position.
53. The method of claim 52, further comprising: before said computer server replacing said baseline signal profile with said new baseline signal, said computer server storing a historical data record of said baseline profile
54. The method of claim 53, wherein said stored historical data record is indicative of said object that affects RF signals being detected in said detection area and comprises a date and time when said object was detected in said detection area,
55. The method of claim 52, repeating said object that affects RF signals moving, said server receiving, and said server replacing at least twice.
56. The method of claim 48, wherein said computer server determining if the position of said object that affects RF signals in said detection area has changed is adjusted based on machine learning comprising:
determining a first sample location of an object that affects RF signals having a fiducial element in said detection area, said first sample location being determined based upon detecting said fiducial. element;
determining a second sample location of said object that affects RF signals in said detection area, said second sample location being determined based at least in part on a comparison of said received second set of signal data to said baseline signal profile not utilizing the fiducial element;
comparing said first sample location and said second sample location; and adjusting the determination step of said second sample location to improve the location calculating capabilities of the system, said adjusting based upon the comparison between first and second determinations.
determining a first sample location of an object that affects RF signals having a fiducial element in said detection area, said first sample location being determined based upon detecting said fiducial. element;
determining a second sample location of said object that affects RF signals in said detection area, said second sample location being determined based at least in part on a comparison of said received second set of signal data to said baseline signal profile not utilizing the fiducial element;
comparing said first sample location and said second sample location; and adjusting the determination step of said second sample location to improve the location calculating capabilities of the system, said adjusting based upon the comparison between first and second determinations.
57. The method of claim 48 wherein an existing historical record of said first signal data and said second signal data are retrieved from a server, and adjusted to allow the use of said historical record in a different operational environment.
58. The method of claim 48, wherein said object that affects RF includes a metal.
59, The method of claim 48, wherein said object causes a measurable variation in signal metrics due to one or more phenomena from the list of: reflection, refraction, diffraction, scattering and absorption.
60. The method of claim 48, wherein said object that affects RF is a vehicle
61. A method for correlating the detection of human activity in a space with a desired system action comprising:
a training phase where the system is provided with an overall training data set of a human activity and a system input;
said human activity comprising one or more of the following: change in position of one or more humans, presence of one or more humans, count of humans within a physical space, and/or location of humans within a physical space;
a model building phase wherein:
the system calculates a best fit relationship between the system input and the human activity; and the system predicting an action to take based on the best fit relationship;
and an action phase wherein the system performs the predicted action.
a training phase where the system is provided with an overall training data set of a human activity and a system input;
said human activity comprising one or more of the following: change in position of one or more humans, presence of one or more humans, count of humans within a physical space, and/or location of humans within a physical space;
a model building phase wherein:
the system calculates a best fit relationship between the system input and the human activity; and the system predicting an action to take based on the best fit relationship;
and an action phase wherein the system performs the predicted action.
62. The method of claim 61 where the training phase and the model building phase are repeated prior to the action phase.
63. The method of claim 61 where the system input includes at least one of:
time of day, calendar date, day of the week, current weather, or predicted weather,
time of day, calendar date, day of the week, current weather, or predicted weather,
64. The method of claim 63 where the system input includes n comparison of a new system input to a previous system input.
65. The method of claim 61 where the system input includes output from a sensor.
66. The method of claim 65 where the sensor is selected from the group consisting of: a light sensor, a temperature sensor, a carbon dioxide sensor, or a location beacon.
67. A method for estimating the number of people in a space comprising:
providing a plurality of presence sensing networks in said space, each of said presence sensing networks being capable of providing at least one data element for a detection area within said space specific to that network, each of said data elements being selected from the group consisting of:
detecting presence of at least one person in said specific detection area, determining a number of people in said detection area, and calculating a metric correlated to an average number of people in said specific detection area within a time; and aggregating all said data elements from all said presence sensing networks to provide an overall estimate of people in said space.
providing a plurality of presence sensing networks in said space, each of said presence sensing networks being capable of providing at least one data element for a detection area within said space specific to that network, each of said data elements being selected from the group consisting of:
detecting presence of at least one person in said specific detection area, determining a number of people in said detection area, and calculating a metric correlated to an average number of people in said specific detection area within a time; and aggregating all said data elements from all said presence sensing networks to provide an overall estimate of people in said space.
68. The method of claim 67 where a result of said aggregating is timestamped and recorded periodically.
69. The method of claim 67 where a result of said aggregating is provided to a requesting party.
70. The method of claim 69 wherein said requesting party comprises first responders to an emergency at said space.
71. The method of claim 69 wherein said data elements are presented as one or more of a map, a real-world audible or visual signal, an overlay on a display, or directional information in a virtual reality display.
72. The method of claim 69 wherein said result is updated by new information from said plurality of presence sensing networks periodically,
73. The method of claim 72 wherein said result indicates when one of said presence sensing networks is no longer transmitting data elements,
74. The method of claim 69 wherein said requesting party comprises a robot.
75, The method of claim 69, wherein said result also includes information provided from other sensors in said space and information from sensors external said space,
Applications Claiming Priority (9)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/674,328 US10455357B2 (en) | 2015-09-16 | 2017-08-10 | Detecting location within a network |
US15/674,487 | 2017-08-10 | ||
US15/674,487 US10325641B2 (en) | 2017-08-10 | 2017-08-10 | Detecting location within a network |
US15/674,328 | 2017-08-10 | ||
US15/713,309 US10064014B2 (en) | 2015-09-16 | 2017-09-22 | Detecting location within a network |
US15/713,309 | 2017-09-22 | ||
US15/713,219 | 2017-09-22 | ||
US15/713,219 US10142785B2 (en) | 2015-09-16 | 2017-09-22 | Detecting location within a network |
PCT/US2018/045835 WO2019032718A1 (en) | 2017-08-10 | 2018-08-08 | Detecting location within a network |
Publications (2)
Publication Number | Publication Date |
---|---|
CA3073589A1 true CA3073589A1 (en) | 2019-02-14 |
CA3073589C CA3073589C (en) | 2023-10-17 |
Family
ID=65271639
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CA3073589A Active CA3073589C (en) | 2017-08-10 | 2018-08-08 | Detecting location within a network |
Country Status (5)
Country | Link |
---|---|
EP (1) | EP3662296A4 (en) |
KR (2) | KR102478928B1 (en) |
CN (1) | CN111201441B (en) |
CA (1) | CA3073589C (en) |
WO (1) | WO2019032718A1 (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
ES2974064T3 (en) * | 2019-05-14 | 2024-06-25 | Signify Holding Bv | Receiver for a presence detection arrangement based on radio frequency, RF |
ES2956023T3 (en) * | 2019-11-26 | 2023-12-11 | Signify Holding Bv | System, network, method and computer program for controlling baseline re-establishment of a network device that is part of the network |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU2003239787A1 (en) * | 2002-06-26 | 2004-01-19 | It-Hojskolen | A method of and a system for surveillance of an environment utilising electromagnetic waves |
JP2009229318A (en) * | 2008-03-24 | 2009-10-08 | Nippon Telegr & Teleph Corp <Ntt> | Human detection device and human detection method |
WO2012082758A1 (en) * | 2010-12-13 | 2012-06-21 | Xandem Technology Llc | Systems and methods of device-free motion detection and presence detection |
JP2012190161A (en) * | 2011-03-09 | 2012-10-04 | Panasonic Corp | Event detection device, event detection system, event detection method, and event detection program |
US8866663B2 (en) * | 2011-12-27 | 2014-10-21 | Massachusetts Institute Of Technology | Methods and apparatus for sensing organic tissue |
US9185528B2 (en) * | 2012-06-28 | 2015-11-10 | Northrop Grumman Systems Corporation | WiFi mapping and motion detection |
US9960929B2 (en) * | 2012-09-21 | 2018-05-01 | Google Llc | Environmental sensing with a doorbell at a smart-home |
JP2015052475A (en) * | 2013-09-05 | 2015-03-19 | 住友電気工業株式会社 | Monitoring system |
US9408041B1 (en) * | 2015-04-24 | 2016-08-02 | Insensi, Inc. | Premise occupancy detection based on smartphone presence |
US9474042B1 (en) * | 2015-09-16 | 2016-10-18 | Ivani, LLC | Detecting location within a network |
-
2018
- 2018-08-08 CA CA3073589A patent/CA3073589C/en active Active
- 2018-08-08 CN CN201880065996.0A patent/CN111201441B/en active Active
- 2018-08-08 WO PCT/US2018/045835 patent/WO2019032718A1/en unknown
- 2018-08-08 KR KR1020217041716A patent/KR102478928B1/en active IP Right Grant
- 2018-08-08 KR KR1020207006884A patent/KR102343167B1/en active IP Right Grant
- 2018-08-08 EP EP18842993.0A patent/EP3662296A4/en active Pending
Also Published As
Publication number | Publication date |
---|---|
KR102343167B1 (en) | 2021-12-24 |
KR20210157432A (en) | 2021-12-28 |
CA3073589C (en) | 2023-10-17 |
CN111201441A (en) | 2020-05-26 |
CN111201441B (en) | 2023-01-31 |
KR102478928B1 (en) | 2022-12-19 |
WO2019032718A1 (en) | 2019-02-14 |
KR20200041341A (en) | 2020-04-21 |
EP3662296A4 (en) | 2021-01-20 |
EP3662296A1 (en) | 2020-06-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11711667B2 (en) | Detecting location within a network | |
US10455357B2 (en) | Detecting location within a network | |
US10325641B2 (en) | Detecting location within a network | |
US11423968B2 (en) | Detecting location within a network | |
CA3073589A1 (en) | Detecting location within a network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
EEER | Examination request |
Effective date: 20200310 |
|
EEER | Examination request |
Effective date: 20200310 |
|
EEER | Examination request |
Effective date: 20200310 |
|
EEER | Examination request |
Effective date: 20200310 |
|
EEER | Examination request |
Effective date: 20200310 |
|
EEER | Examination request |
Effective date: 20200310 |
|
EEER | Examination request |
Effective date: 20200310 |
|
EEER | Examination request |
Effective date: 20200310 |
|
EEER | Examination request |
Effective date: 20200310 |