CN107294621A - The method and system of Humidity Detection based on wireless aware - Google Patents
The method and system of Humidity Detection based on wireless aware Download PDFInfo
- Publication number
- CN107294621A CN107294621A CN201710525205.5A CN201710525205A CN107294621A CN 107294621 A CN107294621 A CN 107294621A CN 201710525205 A CN201710525205 A CN 201710525205A CN 107294621 A CN107294621 A CN 107294621A
- Authority
- CN
- China
- Prior art keywords
- wireless
- channel
- humidity
- characteristic parameter
- condition information
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000013507 mapping Methods 0.000 claims description 15
- 238000012706 support-vector machine Methods 0.000 claims description 14
- 239000000428 dust Substances 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 11
- 238000012360 testing method Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 230000004044 response Effects 0.000 claims description 10
- 238000005259 measurement Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 4
- 241000208340 Araliaceae Species 0.000 claims description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 3
- 235000008434 ginseng Nutrition 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000011895 specific detection Methods 0.000 abstract description 2
- 230000008054 signal transmission Effects 0.000 abstract 1
- 238000001914 filtration Methods 0.000 description 9
- 230000006872 improvement Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 229920000742 Cotton Polymers 0.000 description 2
- 239000012141 concentrate Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000003920 environmental process Methods 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000013100 final test Methods 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010025 steaming Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display
- G01N33/0068—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display using a computer specifically programmed
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/309—Measuring or estimating channel quality parameters
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Food Science & Technology (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- General Physics & Mathematics (AREA)
- Medicinal Chemistry (AREA)
- Combustion & Propulsion (AREA)
- Quality & Reliability (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
- Air Conditioning Control Device (AREA)
- Monitoring And Testing Of Transmission In General (AREA)
Abstract
The present invention relates to wireless network signal transmission technology, it discloses a kind of method and system of the Humidity Detection based on wireless aware.This method gathers the wireless signal launched from transmitting terminal using wireless signal acquiring device, and assesses channel condition information, the purpose detected with the humidity information reached to surrounding environment.The step of methods described, includes:The wireless signal launched using wireless signal acquiring device with specific layout collection from transmitting terminal.The present invention utilizes existing wireless network and equipment, without installing other specific detection devices, with high popularization.
Description
Technical field
The present invention relates to radio detection field, more particularly to a kind of Humidity Detection based on wireless aware method and be
System.
Background technology
Radio network technique had rapid development in the last few years, and people attempt to apply it to side's aspect of life
Face.Simultaneously with the development and the progress of life in epoch, people increasingly pay close attention to the relation of itself and the Nature.Atmospheric humidity is made
For a kind of ambient parameter, natural economy, and the important effect of performer in various environmental processes are affected strongly.For example it is each
The growth for planting crops all be unable to do without suitable humidity.With reference to current hotspot, atmospheric humidity prison is carried out using wireless aware technology
The research of survey, so as to allow technology preferably to serve life.
Existing humidity measuring method can be largely classified into two kinds.One is, look-up table, and common hygrometer is used with this
The method of kind.General principles are as follows:Because the bulb, of wet-bulb thermometer encloses cotton yarn, the lower end of cotton yarn is soaked in water, the steaming of water
Send out and the temperature registration of wet-bulb thermometer is always less than the temperature registration of dry-bubble temperature meter, and this temperature gap is with water evaporation
Speed (relative humidity i.e. at that time) can find the relatively wet of air about readings of the according to two temperatures meter from table or curve
Degree.Two are, damped method, the principle that can have been decayed when being transmitted in atmosphere based on electromagnetic wave by the influence of vapor, lead to
The RSSI (Received Signal Strength Indicator) of measurement transmitting terminal and receiving terminal is crossed, so that according to decay journey
Spend to speculate the size of humidity.
Summarize both the above method.Method one, is measured using physical phenomenon to humidity, and artificial error is larger.And
And when we need to know the humidity value of many places simultaneously, this is accomplished by placing multiple hygrometers, and such cost is just too high.Side
Method two, because the influence that vapor is transmitted to signal is smaller after all.Therefore, needed in practical operation to (long through long-distance
Up to several kilometers) transmission after signal intensity measure.Under long range, other weather conditions, such as rain, snow and mist are added
To the possibility of effect of signals, so as to cause measurement limited.Furthermore, increase the inconvenience of measurement in itself over long distances.
The content of the invention
In order to overcome the weak point in above-mentioned signified existing measuring method, the present invention provides a kind of based on wireless aware
Humidity Detection method and system.Utilize the wireless signal transmitting device being widely deployed, such as commercial routers, in spy
In fixed layout, by CSI (the Channel State Information channel condition informations) data being collected into, one is used
Serial algorithm is analyzed data, so as to detect the humidity information of surrounding environment.This method has good basis of reality:Nothing
Gauze network is by ubiquitous deployment.Relative to conventional method, measurement cost is reduced, applicability is improved.
The present invention is achieved by the following technical solutions:
A kind of humidity detection method based on wireless aware, comprises the following steps:
S1, wireless receiving end receive the wireless signal from wireless transmitting terminals, and assess channel condition information;Wherein, often
Individual wireless channel includes multiple subcarriers, and the channel condition information of the wireless channel includes multiple subcarriers in the channel
The average value of CIS values;
S2, CSI data characteristics are extracted, and export target pattern, i.e. the status information of multiple wireless channels to obtaining is carried out
Data processing, obtains the characteristic parameter collection of environment space where characterizing the multiple wireless channel;
S3, the target pattern that will be exported in step S2, using svm classifier, to detect the humidity information of surrounding environment, bag
Include:Obtained characteristic parameter collection is input to the classification corresponding with the characteristic parameter of wireless channel of set in advance, ambient humidity
In model, classified or belonged to judgement to it, and then obtain ambient humidity;
S4, feedback adjust the parameter of sorting algorithm, further lift accuracy for the response message of testing result, wrap
Parameter value and testing result that the characteristic parameter obtained according to this detection is concentrated are included, the parameter to the disaggregated model is adjusted
It is whole.
As a further improvement on the present invention:The step S1 further comprises:
S11, in a wireless channel, carried while measuring and obtaining in the wireless channel continuous T height in N number of subcarrier
The CSI values of ripple;
S12, the T CSI value obtained average value as the wireless channel channel condition information;
S13, in M wireless channel simultaneously or successively perform above-mentioned steps, obtain M channel condition information;
Wherein, M, N and T are the natural number more than 1, and N is more than T.
As a further improvement on the present invention:The step S2 further comprises:
S21, M obtained channel condition information is carried out asking its average, normalized standard deviation, average absolute inclined respectively
The calculating of difference, quartile scope and signal entropy, respectively obtains the average of the M channel condition information, normalized standard
Difference, mean absolute deviation, quartile scope and signal entropy;
S22, by average obtained above, normalized standard deviation, mean absolute deviation, quartile scope and signal entropy
It is placed into a vector set, obtains the characteristic parameter collection of this detection.
As a further improvement on the present invention:The disaggregated model being previously set includes characteristic parameter collection
Mapping set, the mapping set includes multiple characteristic parameter collection and the ring of the setting by being obtained under the ambient humidity of setting
The set element of border humidity composition;The step S3 further comprises:
S31, the parameter for concentrating the characteristic parameter currently obtained compare one by one with the characteristic parameter collection in the disaggregated model
Compared with the characteristic parameter for finding and currently obtaining concentrates the closest set element of all characteristic ginseng values;
S32, ambient humidity in the set element is selected to be current environment humidity.
As a further improvement on the present invention:Set environment humidity value linear distribution in the mapping set is in measurement model
In enclosing.
As a further improvement on the present invention:The disaggregated model is adjusted including by the characteristic parameter currently obtained
Collection and the ambient humidity currently selected form the set element, and are added in the mapping set.
Invention also provides a kind of dust humidity detection system based on wireless aware, including:
CSI acquisition modules, the channel condition information for obtaining each in multiple wireless channels;Wherein, it is each wireless
Channel includes multiple subcarriers, and the channel condition information of the wireless channel includes the CIS values of multiple subcarriers in the channel
Average value;
Characteristic parameter collection obtains module, and the status information for multiple wireless channels to obtaining carries out data processing, obtains
The characteristic parameter collection of environment space to where characterizing the multiple wireless channel;
Detection module module, for obtained characteristic parameter collection to be input into set in advance, ambient humidity and wireless communication
In the corresponding disaggregated model of characteristic parameter in road, classified or belonged to judgement to it, and then obtain ambient humidity;
Feedback module:The parameter value and testing result concentrated for the characteristic parameter obtained according to this detection, to described
The parameter of disaggregated model is adjusted.
As a further improvement on the present invention:The CSI acquisition modules include:
Sensing unit, for gathering initial channel status data, based on MIMO technique, the initial channel shape
State data include the CSI values of N number of subcarrier in M spatial flow, and M and N are the natural number more than 1;
Data processing unit, for each spatial flow, asking for the CSI of the T continuous subcarrier on same time point
The average value of value, using this average value as channel condition information, T is the natural number more than 1 less than N.
As a further improvement on the present invention:The characteristic parameter obtains module and further comprised:
Computing unit, for carrying out feature extraction to CSI data, the feature of extraction includes:Average, normalized standard
Difference, mean absolute deviation, quartile scope and signal entropy;
Model unit is set up, causes letter for based on Statistical Learning Theory, pre-establishing to set different moisture levels in space
Channel state information becomes the high dimensional feature model for being turned to training sample;
Detection unit, for mapping to the target pattern of output in the high dimensional feature model of SVMs, is isolated
Target humidity class.
As a further improvement on the present invention:The feedback module includes:The feedback module further comprises:For anti-
Feedback adjusts the high dimensional feature model of SVMs for the response message of current environment Humidity Detection.
Beneficial effects of the present invention:A kind of more preferable assessment to radio propagation channel is used as relative to RSSI, CSI;This
Invention have devised a kind of dust humidity detection system based on wireless aware, and enable correction module more accurate using CSI advantage
Really the humidity information to surrounding environment is detected;This detection method is on the basis of existing wireless network and equipment, to enter
Row Humidity Detection is worked, and other specific detection devices need not be installed by being detected in environment, with high popularization.
Brief description of the drawings
Accompanying drawing 1 is a kind of system configuration schematic diagram of the Humidity Detection based on wireless aware of embodiment of the present invention;
Accompanying drawing 2 is the implementation process sketch of the humidity detection method of the present invention;
Accompanying drawing 3 is a kind of implementation process schematic diagram of the humidity detection method of embodiment of the present invention;
Accompanying drawing 4 is a kind of frame diagram of the dust humidity detection system of embodiment of the present invention.
Embodiment
For the ease of the understanding of those skilled in the art, present invention work is further retouched with example below in conjunction with the accompanying drawings
State.
Support Vector Machine are SVM
A kind of humidity detection method based on wireless aware, comprises the following steps:
S1, wireless receiving end receive the wireless signal from wireless transmitting terminals, and assess channel condition information;
S2, CSI data characteristics are extracted, and export target pattern;
S3, the target pattern that will be exported in step S2, using svm classifier, to detect the humidity information of surrounding environment;
S4, feedback adjust the parameter of sorting algorithm, further lift accuracy for the response message of testing result.
The step S1, which assesses channel condition information, to be included:
S11, collection initial channel status data, based on MIMO technique, the initial channel state data packets
The CSI values of N number of subcarrier in M spatial flow are included, M and N are the natural number more than 1;
S12, to each spatial flow, ask for the average value of the CSI values of T continuous subcarrier on same time point, will
This average value is as channel condition information, and T is the natural number more than 1 less than N;
S13, using data filtering techniques, filtration treatment is carried out to channel condition information, to reduce in surrounding environment because of thing
Moving for body and the interference to channel condition information caused.
The step S2 includes carrying out average Mean, normalized standard deviation The Normalized to CSI data
Standard Deviation, mean absolute deviation Mean Absolute Deviation, quartile scope
Interquartile Range and signal entropy Signal Entropy totally five aspect feature extraction.
The sorting algorithm that the step S3 is classified according to the feature of CSI data is support vector machines method.
The step S3 includes:
S31, based on Statistical Learning Theory, pre-establish causes channel condition information to change to set different moisture levels in space
It is used as the high dimensional feature model of training sample;
S32, the target pattern that will be exported in step S2, using svm classifier, to detect the humidity information of surrounding environment.
As a further improvement on the present invention:In the step S4, feedback is adjusted for the response message of Humidity Detection result
The high dimensional feature model of whole SVMs.
In summary, in the present embodiment, in above-mentioned humidity detection method, between wireless receiving end and wireless transmitting terminals
The connection of wireless channel is set up, and assesses channel condition information;Wherein, each wireless channel includes multiple subcarriers, described
The channel condition information of wireless channel includes the average value of the CIS values of multiple subcarriers in the channel;It is right after above-mentioned connection is set up
The status information of obtained multiple wireless channels carries out data processing, obtains characterizing environment space where the multiple wireless channel
Characteristic parameter collection;Obtained characteristic parameter collection is input to the characteristic parameter of set in advance, ambient humidity and wireless channel
In corresponding disaggregated model, classified or belonged to judgement to it, and then obtain ambient humidity;It can also be detected according to this
Parameter value and testing result that the characteristic parameter arrived is concentrated, the parameter to the disaggregated model are adjusted.
Idiographic flow includes:In a wireless channel, connect while measuring and obtaining in the wireless channel in N number of subcarrier
Continue the CSI values of T subcarrier;The average value of the T CSI value obtained as the wireless channel channel condition information;At M
Above-mentioned steps are performed simultaneously or successively in wireless channel, M channel condition information is obtained;Wherein, M, N and T are oneself more than 1
So number, and N is more than T.
Then, M obtained channel condition information is carried out asking its average, normalized standard deviation, average absolute respectively
The calculating of deviation, quartile scope and signal entropy, respectively obtains the average of the M channel condition information, normalized mark
Accurate poor, mean absolute deviation, quartile scope and signal entropy;By average obtained above, normalized standard deviation, it is averaged absolutely
Deviation, quartile scope and signal entropy are placed into a vector set, the characteristic parameter collection of this detection is obtained.
In the present embodiment, because the disaggregated model being previously set includes the mapping ensemblen of a characteristic parameter collection
Close, the mapping set includes multiple characteristic parameter collection and the ambient humidity of the setting by being obtained under the ambient humidity of setting
The set element of composition;Therefore, in subsequent steps, can be by the parameter of the characteristic parameter currently obtained concentration and described point
Characteristic parameter collection in class model compares one by one, finds the characteristic parameter with currently obtaining and concentrates all characteristic ginseng values to connect the most
Near set element;Then it is current environment humidity to select the ambient humidity in the set element.
In the present embodiment, the set environment humidity value linear distribution in the mapping set is in measurement range.To institute
Disaggregated model is stated to be adjusted including the characteristic parameter currently obtained collection and the ambient humidity currently selected are formed into the set
Element, and be added in the mapping set.
Invention also provides a kind of dust humidity detection system based on wireless aware, including:
CSI acquisition modules, receive the wireless signal from wireless transmitting terminals, and assess channel status for wireless receiving end
Information;
Detection module, for the CSI data collected according to CSI acquisition modules, extracts feature, and carries out classification and matching,
Detect the humidity information of current environment;
Feedback module, result and known classification for detection module to be detected are compared, if there is deviation,
Then it is corrected, so that sorting algorithm is more accurate;
Display module, for showing the result detected.
The CSI acquisition modules include:
Sensing unit, for gathering initial channel status data, based on MIMO technique, the initial channel shape
State data include the CSI values of N number of subcarrier in M spatial flow, and M and N are the natural number more than 1;
Data processing unit, for each spatial flow, asking for the CSI of the T continuous subcarrier on same time point
The average value of value, using this average value as channel condition information, T is the natural number more than 1 less than N;
Filter element, for carrying out filtration treatment to channel condition information using data filtering techniques.
The detection module, including:
Computing unit, for carrying out feature extraction to CSI data, the feature of extraction includes:Average, normalized standard
Difference, mean absolute deviation, quartile scope and signal entropy;
Model unit is set up, causes letter for based on Statistical Learning Theory, pre-establishing to set different moisture levels in space
Channel state information becomes the high dimensional feature model for being turned to training sample;
Detection unit, for mapping to the target pattern of output in the high dimensional feature model of SVMs, is isolated
Target humidity class.
The feedback module includes:For feeding back the response message for current environment Humidity Detection, supporting vector is adjusted
The high dimensional feature model of machine;The display module includes but is not limited to mobile terminal screen, palm PC or LCDs.
In one embodiment, a kind of method of the Humidity Detection based on wireless aware, its step includes:
S1, wireless receiving end receive the wireless signal from wireless transmitting terminals, and assess channel condition information;
S2, CSI data characteristics are extracted, and average (Mean), normalized standard deviation are made respectively to the CSI data being collected into
(The Normalized Standard Deviation), mean absolute deviation (Mean Absolute Deviation), four
Dividing position scope, (Interquartile Range and signal entropy (Signal Entropy) processing, export target pattern;
S3, the target pattern that will be exported in step S2, using svm classifier, to detect the humidity information of surrounding environment;
S4, feedback adjust the parameter of sorting algorithm, further lift accuracy for the response message of testing result.
Specifically, in step sl, assessing channel condition information includes:
S11, collection initial channel status data, based on MIMO technique, the initial channel state data packets
The CSI values of N number of subcarrier in M spatial flow are included, M and N are the natural number more than 1;
S12, to each spatial flow, ask for the average value of the CSI values of T continuous subcarrier on same time point, will
This average value is as channel condition information, and T is the natural number more than 1 less than N;
S13, using data filtering techniques, filtration treatment is carried out to channel condition information, to reduce in surrounding environment because of thing
Moving for body and the interference to channel condition information caused.
When the system starts of the present invention, wireless transmitting terminals propagate wireless network signal, while in specific region
Interior wireless receiving end (computer as being equipped with network interface card) can collect CSI as initial channel status data, then carry out at data
Reason.
Referring to Fig. 1, it is the experimental arrangement figure of whole experiment scene.
The step S2 includes carrying out average (Mean), normalized standard deviation (The Normalized to CSI data
Standard Deviation), mean absolute deviation (Mean Absolute Deviation), quartile scope
(Interquartile Range) and signal entropy (Signal entropy) totally five aspect feature extraction.
The step S3 includes:
S31, based on Statistical Learning Theory, pre-establish causes channel condition information to change to set different moisture levels in space
It is used as the high dimensional feature model of training sample;
S32, the target pattern that will be exported in step S2, using svm classifier, to detect the humidity information of surrounding environment.
The step S4 includes:Feedback is for the response message of Humidity Detection result, and the higher-dimension for adjusting SVMs is special
Levy model.
Flow chart as shown in Figure 2, discloses four important steps of the detection method of the present invention, including:Channel shape
State is assessed, CSI data characteristicses are extracted, humidity is classified and feedback testing result.
In another embodiment, as shown in Figure 3, present invention also offers a kind of realization of the humidity detection method of embodiment
Flow, its step includes:
S301, wireless receiving end receive the wireless signal from wireless transmitting terminals, while gathering initial channel status data;
S302, take merge subcarrier CSI average values as channel condition information;
S303, to channel condition information carry out filtration treatment;
S304, to channel condition information carry out feature extraction;
S305, output target pattern;
S306, the high dimensional feature model that target pattern is mapped to SVMs;
S307, classified using SVMs;
S308, the humidity information for whether detecting current environment, in this way, perform step S309, otherwise return to step S301;
S309, in display module show testing result, adjusting parameter, optimizing detection and sorting algorithm.
Present invention also offers a kind of dust humidity detection system, as shown in Figure 4, including:
CSI acquisition modules 41, receive the wireless signal from wireless transmitting terminals, and assess channel shape for wireless receiving end
State information;
Detection module 42, for the CSI data collected according to CSI acquisition modules, extracts feature, exports target pattern,
And map to the target pattern of output in the high dimensional feature model of SVMs, isolate target humidity class;
Feedback module 43, result and known classification for detection module to be detected are compared, if there is inclined
Difference, then be corrected, so that sorting algorithm is more accurate;
Display module 44, using the display screen of mobile phone terminal or other display modules, for showing the result detected.
The CSI acquisition modules include:
Sensing unit 411, for gathering initial channel status data, based on MIMO technique, the initial letter
Road status data includes the CSI values of N number of subcarrier in M spatial flow, and M and N are the natural number more than 1;
Data processing unit 412, for each spatial flow, asking for the T continuous subcarrier on same time point
The average value of CSI values, using this average value as channel condition information, T is the natural number more than 1 less than N;
Filter element 413, for carrying out filtration treatment to channel condition information using data filtering techniques.
The detection module, including:
Computing unit 421, for carrying out feature extraction to CSI data, the feature of extraction includes:Average (Mean), normalizing
The standard deviation (Normalized Standard Deviation) of change, mean absolute deviation (Mean Absolute
Deviation), quartile scope (Interquartile Range) and signal entropy (Signal Entropy), export mesh
Mark pattern;
Model unit 422 is set up, is caused for based on Statistical Learning Theory, pre-establishing with setting different moisture levels in space
Channel condition information becomes the high dimensional feature model for being turned to training sample;
Humidity recognition unit 423, for the target pattern of output being mapped in the high dimensional feature model of SVMs,
Isolate target humidity class.
The dust humidity detection system of the present invention also includes a feedback module 43, for feeding back for current environment Humidity Detection
Response message, adjusts the high dimensional feature model of SVMs.
The dust humidity detection system of the present invention also includes a display module 44, and the final testing result for showing shows mould
Block is mobile terminal screen, palm PC, LCDs and other display device (such as projecting apparatus for display content
Deng).
Above content is to combine specific preferred embodiment further description made for the present invention, should not assert this hair
Bright specific implementation is confined to described above.For those skilled in the art, present inventive concept is not being departed from
On the premise of, some simple deduction or replace can also be made, are regarded as what is determined by the claim that the present invention is submitted
Within protection domain.
Claims (10)
1. a kind of humidity detection method based on wireless aware, it is characterised in that comprise the following steps:
S1, wireless receiving end receive the wireless signal from wireless transmitting terminals, and assess channel condition information;Wherein, Mei Gewu
Line channel includes multiple subcarriers, and the channel condition information of the wireless channel includes the CIS of multiple subcarriers in the channel
The average value of value;
S2, CSI data characteristics are extracted, and export target pattern, i.e. the status information of multiple wireless channels to obtaining carries out data
Processing, obtains the characteristic parameter collection of environment space where characterizing the multiple wireless channel;
S3, the target pattern that will be exported in step S2, using svm classifier, to detect the humidity information of surrounding environment, including:Will
Obtained characteristic parameter collection is input to set in advance, ambient humidity disaggregated model corresponding with the characteristic parameter of wireless channel
In, classified or belonged to judgement to it, and then obtain ambient humidity;
S4, feedback adjust the parameter of sorting algorithm, further lift accuracy, including root for the response message of testing result
Parameter value and testing result that the characteristic parameter obtained according to this detection is concentrated, the parameter to the disaggregated model are adjusted.
2. the humidity detection method according to claim 1 based on wireless aware, it is characterised in that enter in the step S1
One step includes:
S11, in a wireless channel, while measuring and obtaining in the wireless channel continuous T subcarrier in N number of subcarrier
CSI values;
S12, the T CSI value obtained average value as the wireless channel channel condition information;
S13, in M wireless channel simultaneously or successively perform above-mentioned steps, obtain M channel condition information;
Wherein, M, N and T are the natural number more than 1, and N is more than T.
3. the humidity detection method according to claim 2 based on wireless aware, it is characterised in that the step S2 enters one
Step includes:
S21, M obtained channel condition information is carried out asking respectively its average, normalized standard deviation, mean absolute deviation,
The calculating of quartile scope and signal entropy, respectively obtain the average of the M channel condition information, normalized standard deviation,
Mean absolute deviation, quartile scope and signal entropy;
S22, by average obtained above, normalized standard deviation, mean absolute deviation, quartile scope and signal entropy place
Into a vector set, the characteristic parameter collection of this detection is obtained.
4. the humidity detection method according to claim 3 based on wireless aware, it is characterised in that described to be previously set
Disaggregated model includes the mapping set of a characteristic parameter collection, and the mapping set includes multiple environmental wets by setting
The set element that the lower characteristic parameter collection obtained of degree and the ambient humidity of the setting are constituted;The step S3 further comprises:
S31, the parameter for concentrating the characteristic parameter currently obtained are compared one by one with the characteristic parameter collection in the disaggregated model, are looked for
The closest set element of all characteristic ginseng values is concentrated to the characteristic parameter with currently obtaining;
S32, ambient humidity in the set element is selected to be current environment humidity.
5. the humidity detection method according to claim 4 based on wireless aware, it is characterised in that in the mapping set
Set environment humidity value linear distribution in measurement range.
6. the humidity detection method according to claim 5 based on wireless aware, it is characterised in that to the disaggregated model
It is adjusted including the characteristic parameter currently obtained collection and the ambient humidity currently selected are formed into the set element, and adds
Into the mapping set.
7. a kind of dust humidity detection system based on wireless aware, it is characterised in that including:
CSI acquisition modules, the channel condition information for obtaining each in multiple wireless channels;Wherein, each wireless channel
Include multiple subcarriers, the channel condition information of the wireless channel includes putting down for CIS values of multiple subcarriers in the channel
Average;
Characteristic parameter collection obtains module, and the status information for multiple wireless channels to obtaining carries out data processing, obtains table
The characteristic parameter collection of environment space where levying the multiple wireless channel;
Detection module module, for obtained characteristic parameter collection to be input into set in advance, ambient humidity and wireless channel
In the corresponding disaggregated model of characteristic parameter, classified or belonged to judgement to it, and then obtain ambient humidity;
Feedback module:The parameter value and testing result concentrated for the characteristic parameter obtained according to this detection, to the classification
The parameter of model is adjusted.
8. the dust humidity detection system according to claim 7 based on wireless aware, it is characterised in that the CSI obtains mould
Block includes:
Sensing unit, for gathering initial channel status data, based on MIMO technique, the initial channel status number
According to the CSI values of N number of subcarrier in M spatial flow are included, M and N are the natural number more than 1;
Data processing unit, the CSI values for each spatial flow, asking for T continuous subcarrier on same time point
Average value, using this average value as channel condition information, T is the natural number more than 1 less than N.
9. the dust humidity detection system according to claim 8 based on wireless aware, it is characterised in that the characteristic parameter takes
Module is obtained to further comprise:
Computing unit, for carrying out feature extraction to CSI data, the feature of extraction includes:It is average, normalized standard deviation, flat
Equal absolute deviation, quartile scope and signal entropy;
Model unit is set up, causes channel shape for based on Statistical Learning Theory, pre-establishing to set different moisture levels in space
State information change as training sample high dimensional feature model;
Detection unit, for mapping to the target pattern of output in the high dimensional feature model of SVMs, isolates target
Humidity class.
10. the dust humidity detection system according to claim 9 based on wireless aware, it is characterised in that the feedback module
Further comprise:For feeding back the response message for current environment Humidity Detection, the high dimensional feature mould of SVMs is adjusted
Type.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610521465.0A CN106198868A (en) | 2016-07-05 | 2016-07-05 | The method and system of Humidity Detection based on wireless aware |
CN2016105214650 | 2016-07-05 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107294621A true CN107294621A (en) | 2017-10-24 |
CN107294621B CN107294621B (en) | 2019-04-02 |
Family
ID=57466068
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610521465.0A Pending CN106198868A (en) | 2016-07-05 | 2016-07-05 | The method and system of Humidity Detection based on wireless aware |
CN201710525205.5A Active CN107294621B (en) | 2016-07-05 | 2017-06-30 | The method and system of Humidity Detection based on wireless aware |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610521465.0A Pending CN106198868A (en) | 2016-07-05 | 2016-07-05 | The method and system of Humidity Detection based on wireless aware |
Country Status (2)
Country | Link |
---|---|
CN (2) | CN106198868A (en) |
WO (1) | WO2018006798A1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109374652A (en) * | 2018-09-05 | 2019-02-22 | 深圳大学 | Humidity perception and detection method and system based on millimeter-wave signal |
CN110365429A (en) * | 2019-07-18 | 2019-10-22 | 珠海格力电器股份有限公司 | Detection method, device and system |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106198868A (en) * | 2016-07-05 | 2016-12-07 | 深圳大学 | The method and system of Humidity Detection based on wireless aware |
CN107273615B (en) * | 2017-06-15 | 2021-06-04 | 东华大学 | Ultra-wideband microwave humidity detection method based on machine learning |
CN113485218B (en) * | 2021-08-04 | 2022-06-07 | 广德绿巨人环境管理咨询有限公司 | Wisdom thing allies oneself with supervision platform based on 5G |
CN117641416A (en) * | 2022-08-26 | 2024-03-01 | 中兴通讯股份有限公司 | Wireless sensing method, communication device and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2463650A1 (en) * | 2010-12-10 | 2012-06-13 | Süd-Chemie AG | Indicator material and indicator device comprising said indicator material |
CN103023589A (en) * | 2012-12-06 | 2013-04-03 | 中山大学 | Indoor passive motion detection method and device |
CN104062654A (en) * | 2014-07-17 | 2014-09-24 | 电子科技大学 | Soil water content measuring method based on ultra wideband radar |
CN104615244A (en) * | 2015-01-23 | 2015-05-13 | 深圳大学 | Automatic gesture recognizing method and system |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE19706576A1 (en) * | 1997-02-20 | 1998-08-27 | Alsthom Cge Alcatel | Device and method for the environment-adaptive classification of objects |
CN101640570A (en) * | 2008-07-29 | 2010-02-03 | 株式会社Ntt都科摩 | Frequency spectrum cognitive method and energy detection method and device |
CN103606248B (en) * | 2013-09-30 | 2016-08-10 | 广州市香港科大***研究院 | A kind of falling over of human body automatic testing method and system |
CN103647591B (en) * | 2013-12-27 | 2016-06-08 | 中国电子科技集团公司第五十四研究所 | A kind of multipoint cooperative interference detection method based on SVMs |
CN106198868A (en) * | 2016-07-05 | 2016-12-07 | 深圳大学 | The method and system of Humidity Detection based on wireless aware |
-
2016
- 2016-07-05 CN CN201610521465.0A patent/CN106198868A/en active Pending
-
2017
- 2017-06-30 CN CN201710525205.5A patent/CN107294621B/en active Active
- 2017-07-04 WO PCT/CN2017/091670 patent/WO2018006798A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2463650A1 (en) * | 2010-12-10 | 2012-06-13 | Süd-Chemie AG | Indicator material and indicator device comprising said indicator material |
CN103023589A (en) * | 2012-12-06 | 2013-04-03 | 中山大学 | Indoor passive motion detection method and device |
CN104062654A (en) * | 2014-07-17 | 2014-09-24 | 电子科技大学 | Soil water content measuring method based on ultra wideband radar |
CN104615244A (en) * | 2015-01-23 | 2015-05-13 | 深圳大学 | Automatic gesture recognizing method and system |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109374652A (en) * | 2018-09-05 | 2019-02-22 | 深圳大学 | Humidity perception and detection method and system based on millimeter-wave signal |
CN110365429A (en) * | 2019-07-18 | 2019-10-22 | 珠海格力电器股份有限公司 | Detection method, device and system |
Also Published As
Publication number | Publication date |
---|---|
WO2018006798A1 (en) | 2018-01-11 |
CN106198868A (en) | 2016-12-07 |
CN107294621B (en) | 2019-04-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107294621B (en) | The method and system of Humidity Detection based on wireless aware | |
CN105025440B (en) | Indoor and outdoor scene detection method and equipment | |
CN105338489B (en) | A kind of intelligent terminal and bluetooth indoor locating system for indoor positioning | |
CN103596266B (en) | A kind of human testing and method, the apparatus and system of positioning | |
CN112040400B (en) | Single-site indoor fingerprint positioning method based on MIMO-CSI, storage medium and equipment | |
CN109587645A (en) | Personnel's recognition methods under indoor environment based on channel state information | |
CN107764976B (en) | Rapid diagnosis method and online monitoring system for soil nitrogen | |
CN104410689A (en) | Agricultural condition information acquiring system and method | |
CN110472575A (en) | A kind of string tomato maturation detection method based on deep learning and computer vision | |
CN107222682A (en) | Crop growth state testing method and device | |
CN109813276B (en) | Base station antenna downward inclination angle measuring method and system | |
CN103543179A (en) | Networked system and method for testing soil humidity and pH (Potential of Hydrogen) value | |
CN107947809A (en) | A kind of method for the automation level that radio is provided | |
CN108418867A (en) | A kind of method of environmental monitoring preventing human interference | |
CN106792769A (en) | A kind of WiFi localization methods and server and location model method for building up | |
CN102970771A (en) | Signal detection and acquisition method and system based on wireless sensor network | |
CN108344446A (en) | A kind of method of environmental monitoring preventing human interference | |
CN108718254A (en) | Subway indoor distributed system Fault Locating Method and system | |
CN108414008A (en) | A kind of city environmental quality monitoring system | |
CN107451605A (en) | A kind of simple target recognition methods based on channel condition information and SVMs | |
CN107016324A (en) | A kind of fingerprint image processing method and fingerprint detection equipment | |
CN108229240A (en) | A kind of method and device of determining picture quality | |
Dai et al. | mm-humidity: Fine-grained humidity sensing with millimeter wave signals | |
CN111561968A (en) | Sensor-based environmental parameter detection method and device and data processing equipment | |
CN107972423B (en) | Testing system and method of tire monitoring system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |