WO2019080735A1 - Method for detecting open and closed state of doors and windows based on wi-fi signals - Google Patents
Method for detecting open and closed state of doors and windows based on wi-fi signalsInfo
- Publication number
- WO2019080735A1 WO2019080735A1 PCT/CN2018/110225 CN2018110225W WO2019080735A1 WO 2019080735 A1 WO2019080735 A1 WO 2019080735A1 CN 2018110225 W CN2018110225 W CN 2018110225W WO 2019080735 A1 WO2019080735 A1 WO 2019080735A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- window
- signal
- csi
- time
- variance
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V3/00—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation
- G01V3/12—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation operating with electromagnetic waves
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/02—Arrangements for detecting or preventing errors in the information received by diversity reception
- H04L1/06—Arrangements for detecting or preventing errors in the information received by diversity reception using space diversity
- H04L1/0618—Space-time coding
- H04L1/0675—Space-time coding characterised by the signaling
Definitions
- the invention belongs to the field of artificial intelligence technology, and particularly relates to a method for detecting a door and window opening and closing state based on a WiFi signal.
- the data source of the system uses an RSSI (Received Signal Strength) signal, and the RSSI signal has a small amount of data (one value is collected each time), only It can induce large movements, that is, the detection system includes low information, low detection accuracy, and high false alarm rate.
- RSSI Received Signal Strength
- the invention provides a method for detecting a door and window opening and closing state based on a WiFi signal.
- a method for detecting opening and closing state of a door and window based on a WiFi signal comprising the following steps:
- Step 1 Collect the WiFi wireless signal sent by the indoor WIFI router, and mark the opening and closing state of the door and window at this time;
- Step 2 extracting an instant CSI (Channel State Information) signal from the received WiFi wireless signal;
- Step 3 Calculate an average number, a variance, a median, and a miscibility index of the CSI values in the window period according to the instantaneous CSI signal extracted in the set time window as a signal feature;
- Step 4 determining an optimal window length and window overlap according to the degree of hybridization of the CSI signals
- Step 5 input the CSI signal feature into the intelligent algorithm, perform model training, and determine the state of the door and window after completion.
- the calculation method of the hybridity index is:
- Y represents the degree of confounding, which represents the jitter of the current CSI signal
- the median, variance, and mean are time-series feature values calculated from the CSI amplitude in the time window;
- the median, variance, and mean subscripts Pre represent the previous time window
- the median, variance, and mean subscripts Cur represent the current time window.
- the degree of overlap of the time window is determined by the hybridity index of the CSI signal.
- the calculation method is as follows: When the hysteresis index continues to increase,
- the adjacent time is reduced by adding an overlapping CSI packet, but it is necessary to ensure that two adjacent time windows are consecutive in time.
- the window length is reduced by 1, and the minimum window length is 2;
- the window length is increased by 1, and the maximum window length is 10.
- Obtain a CSI signal obtain a piece of data through a time window, calculate a time domain statistical value of the mean, variance, and deviation signal, and then perform a hybridization index;
- the instantaneous CSI signal extracted from the received wireless signal is lower than the false positive rate of the RSSI signal collected in the prior art, and the detection accuracy is high.
- the instantaneous CSI signal fluctuation sent by the wifi router will be in a stable state; when the door and window are opened, the received CSI signal will obviously fluctuate due to signal scattering, attenuation and energy loss. .
- the indoor intrusion detection method adopted by the invention only needs a relatively simple device for accepting and calculating the wifi signal, such as a microcomputer with basic computing capability, thereby realizing monitoring.
- the microcomputer has no installation position limitation and is flexible and simple to arrange.
- the WiFi signal door and window state detecting method of the present invention is a method for detecting the opening and closing state of the door and window through software, and can be widely used in the scenes of security and maintenance of a home or a business building.
- the cost is lower, the installation and maintenance are simple, and the reliability is high.
- FIG. 1 is a schematic diagram of a time window in the highest frequency monitoring rate test involved in the embodiment of the present invention.
- FIG. 2 is a schematic diagram of a time window during the lowest frequency monitoring test involved in the embodiment of the present invention.
- FIG. 3 is a schematic diagram of a variable time window length involved in an embodiment of the present invention.
- FIG. 4 is a schematic diagram showing the reduction of overlapping portions of a time window involved in an embodiment of the present invention.
- the method for detecting door and window closure based on WIFI signal of the invention comprises:
- Step 1 Collect the wireless signal sent by the indoor WIFI router, and mark the opening and closing state of the door and window at this time;
- Step 2 extracting an instantaneous CSI signal from the received wireless signal
- Step 3 Calculate the average number, variance, median, and the proposed degree of hybridization of the CSI values in the window period according to the instantaneous CSI signal extracted in a certain time window as a signal feature;
- Step 4 Determine an optimal window length and window overlap according to the degree of hybridization of the CSI signals
- Step 5 The signal feature is input into the intelligent algorithm to perform model training, and the door and window state can be judged after completion;
- the time window in step 3 is the time window of the highest frequency monitoring rate test shown in FIG. 1, wherein the horizontal axis is the time axis, and each digital square represents CSI data collected in time series; W1 is time window 1, so In Figure 1, a total of eight time windows are shown, and the window length is 10.
- FIG. 2 is a schematic diagram of a time window at the time of the lowest frequency monitoring check, wherein the horizontal axis is the time axis, each digital square represents CSI data collected in chronological order; W1 is time window 1, and thus, three time windows are represented in the figure.
- the window length is 10.
- Figure 3 is a schematic diagram of variable time window lengths, the window lengths of w1 and w2 are 5, and the lengths of w3 and w4 are 10.
- the time window can be dynamically adjusted according to signal changes.
- the degree of overlap of the time window is determined by the degree of miscibility of the CSI signal.
- the highest and lowest degree of overlap are defined by the graphs in Figures 1 and 2.
- the calculation method is as follows:
- the adjacent time is reduced by adding an overlapping CSI packet, but it is necessary to ensure that two adjacent time windows are consecutive in time. as shown in picture 2.
- Figure 4 is a schematic illustration of the overlap of the overlapping portions of the time window.
- the calculation method of the hybridity index is:
- Y indicates the degree of confounding, which represents the jitter of the current CSI signal
- the median, variance, and mean are time-series feature values calculated from the CSI amplitude in the time window;
- the subscript Pre of the parameter indicates the previous time window; the table Cur below indicates the current time window.
- the time window size is adjusted according to the current CSI signal mixing degree.
- the window length is reduced by "1" and the minimum window length is 2 (can be set manually).
- the hysteresis indicator does not increase, every 10 seconds (pre-settable), the window length is increased by "1” and the maximum window length is 10 (can be set manually).
- the time domain statistics of the average number, variance, and deviation are calculated, and then the hybridity index is obtained. These statistical indicators are used to train the model and are used to judge the opening and closing of doors and windows.
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Signal Processing (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Environmental & Geological Engineering (AREA)
- Geology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Geophysics (AREA)
- Mobile Radio Communication Systems (AREA)
- Alarm Systems (AREA)
Abstract
A method for detecting the open and closed state of doors and windows based on Wi-Fi signals, comprising the following steps: step 1: collecting a Wi-Fi wireless signal emitted by an indoor Wi-Fi router, and noting the open or closed state of a door and window at this time; step 2: extracting an instant CSI signal from the received Wi-Fi wireless signal; step 3: on the basis of the instant CSI signal extracted during a set time window, calculating the mean, variance, median, and hybridity indices of the CSI value in said window as signal characteristics; step 4: on the basis of the hybridity of the CSI signal, determining an optimal window length and window overlap degree; and step 5: inputting the CSI signal characteristics to a smart algorithm, and performing model training to be able to determine the door and window state.
Description
本发明属于人工智能技术领域,特别涉及一种基于WiFi信号的门窗开闭状态检测方法。The invention belongs to the field of artificial intelligence technology, and particularly relates to a method for detecting a door and window opening and closing state based on a WiFi signal.
当前普遍使用的门窗状态监测方式大多依靠传感器信号采集,成本较高且排布线比较麻烦,容易遭到破坏,日常维护成本高。At present, most commonly used door and window state monitoring methods rely on sensor signal acquisition, which has high cost and troublesome wiring, is easily damaged, and has high daily maintenance costs.
现有技术中也有利用WiFi进行入侵检测的室内入侵检测***,但是这种***的数据源采用的是RSSI(接收信号强度)信号,RSSI信号数据量小(每次采集到1个数值),只能对较大的动作产生感应,也即,该检测***包含信息低、检测精度低、误报率高。In the prior art, there is also an indoor intrusion detection system using WiFi for intrusion detection, but the data source of the system uses an RSSI (Received Signal Strength) signal, and the RSSI signal has a small amount of data (one value is collected each time), only It can induce large movements, that is, the detection system includes low information, low detection accuracy, and high false alarm rate.
发明内容Summary of the invention
本发明提供一种基于WiFi信号的门窗开闭状态检测方法。The invention provides a method for detecting a door and window opening and closing state based on a WiFi signal.
一种基于WiFi信号的门窗开闭状态检测方法,该方法包括以下步骤:A method for detecting opening and closing state of a door and window based on a WiFi signal, the method comprising the following steps:
步骤1,采集室内WIFI路由器发出的WiFi无线信号,标注此时门窗开闭状态;Step 1: Collect the WiFi wireless signal sent by the indoor WIFI router, and mark the opening and closing state of the door and window at this time;
步骤2,从接收到的WiFi无线信号中提取出即时CSI(Channel State Information,信道状态信息)信号;Step 2: extracting an instant CSI (Channel State Information) signal from the received WiFi wireless signal;
步骤3,根据设定的时间窗口内提取的即时CSI信号,计算此窗口期内的CSI数值的平均数、方差、中位数、以及混杂度指标作为信号特征;Step 3: Calculate an average number, a variance, a median, and a miscibility index of the CSI values in the window period according to the instantaneous CSI signal extracted in the set time window as a signal feature;
步骤4,根据CSI信号混杂程度,确定最优的窗口长度和窗口重叠度; Step 4, determining an optimal window length and window overlap according to the degree of hybridization of the CSI signals;
步骤5,将CSI信号特征输入到智能算法中,进行模型训练,完成后即可判断门窗状态,Step 5: input the CSI signal feature into the intelligent algorithm, perform model training, and determine the state of the door and window after completion.
其中,混杂度指标计算方法是:Among them, the calculation method of the hybridity index is:
Y=abs(中位数pre–中位数cur)+abs(方差pre–方差cur)+abs(均值pre–均值cur)Y=abs (median pre–median cur)+abs (variance pre–variance cur)+abs (mean pre–mean cur)
Y表示混杂度指标,代表现在CSI信号的抖动情况;Y represents the degree of confounding, which represents the jitter of the current CSI signal;
中位数、方差、均值是由时间窗口内CSI振幅计算出的时序特征值;The median, variance, and mean are time-series feature values calculated from the CSI amplitude in the time window;
中位数、方差、均值下标Pre表示上一个时间窗口;The median, variance, and mean subscripts Pre represent the previous time window;
中位数、方差、均值下标Cur表示当前的时间窗口。The median, variance, and mean subscripts Cur represent the current time window.
时间窗口的重叠程度,由CSI信号的混杂度指标来确定,计算方法如下:当混杂度指标持续增加时,The degree of overlap of the time window is determined by the hybridity index of the CSI signal. The calculation method is as follows: When the hysteresis index continues to increase,
每隔a秒,相邻时间窗口增加一个重叠CSI数据包,但需保证两个相邻的时间窗口中至少有一个数据包不完全相同;Adding an overlapping CSI packet to the adjacent time window every a second, but ensuring that at least one of the two adjacent time windows is not identical;
当混杂度指标没有增加时,When the hysteresis indicator does not increase,
每隔b秒,相邻时间减少增加一个重叠CSI数据包,但需保证两个相邻的时间窗口在时间上是连续的。Every b seconds, the adjacent time is reduced by adding an overlapping CSI packet, but it is necessary to ensure that two adjacent time windows are consecutive in time.
根据当前的CSI信号混杂程度,调整时间窗口大小,Adjust the time window size according to the current CSI signal mixing degree.
当混杂度指标持续增加时,When the hybridity indicator continues to increase,
每隔c秒,窗口长度减1,最小窗口长度为2;Every c seconds, the window length is reduced by 1, and the minimum window length is 2;
当混杂度指标没有增加时,When the hysteresis indicator does not increase,
每隔d秒,窗口长度加1,最大窗口长度为10。Every d seconds, the window length is increased by 1, and the maximum window length is 10.
获取CSI信号,通过时间窗获取一段数据后,计算平均数、方差、偏差信号时域统计值,然后进行求出混杂度指标;Obtain a CSI signal, obtain a piece of data through a time window, calculate a time domain statistical value of the mean, variance, and deviation signal, and then perform a hybridization index;
将这些统计指标用以训练模型,并用以对门窗开闭的检测。These statistical indicators are used to train the model and are used to detect the opening and closing of doors and windows.
本发明的基于wifi信号的门窗开闭状态检测方法,从接收到的无线信号中提取出的即时CSI信号比现有技术中采集的RSSI信号的误报率低,检测精度高。当门窗处于关闭状态时,wifi路由器所发出的即时CSI信号波动会处于一个稳定状态;而当门窗打开时,由于信号的散射,衰减以及能量的损失,会导致接收到的CSI信号出现明显的波动。According to the wifi signal-based door and window opening and closing state detecting method of the present invention, the instantaneous CSI signal extracted from the received wireless signal is lower than the false positive rate of the RSSI signal collected in the prior art, and the detection accuracy is high. When the door and window are closed, the instantaneous CSI signal fluctuation sent by the wifi router will be in a stable state; when the door and window are opened, the received CSI signal will obviously fluctuate due to signal scattering, attenuation and energy loss. .
本发明采用的室内入侵检测方法只需要较为简单的接受wifi信号并对其进行运算的装置,如一台具备基本运算能力的微机,即可实现监控。微机没有安装位置限制,排布灵活简单。The indoor intrusion detection method adopted by the invention only needs a relatively simple device for accepting and calculating the wifi signal, such as a microcomputer with basic computing capability, thereby realizing monitoring. The microcomputer has no installation position limitation and is flexible and simple to arrange.
与现有技术相比,本发明WiFi信号门窗状态检测方法是一种通过软件形式进行门窗开闭状态检测的方法,可以广泛用于家用或商务楼宇的安防、维护等场景。成本更加低廉,安装维护简单,可靠性高。Compared with the prior art, the WiFi signal door and window state detecting method of the present invention is a method for detecting the opening and closing state of the door and window through software, and can be widely used in the scenes of security and maintenance of a home or a business building. The cost is lower, the installation and maintenance are simple, and the reliability is high.
通过参考附图阅读下文的详细描述,本发明示例性实施方式的上述以及其他目的、特征和优点将变得易于理解。在附图中,以示例性而非限制性的方式示出了本发明的若干实施方式,其中:The above and other objects, features and advantages of the exemplary embodiments of the present invention will become < In the drawings, several embodiments of the invention are shown in the
图1是本发明实施例中涉及的最高测频监率检验时的时间窗口示意图。1 is a schematic diagram of a time window in the highest frequency monitoring rate test involved in the embodiment of the present invention.
图2是本发明实施例中涉及的最低频率监测检验时的时间窗口示意图。2 is a schematic diagram of a time window during the lowest frequency monitoring test involved in the embodiment of the present invention.
图3是本发明实施例中涉及的可变的时间窗口长度示意图。3 is a schematic diagram of a variable time window length involved in an embodiment of the present invention.
图4是本发明实施例中涉及的时间窗口的重叠部分减少示意图。4 is a schematic diagram showing the reduction of overlapping portions of a time window involved in an embodiment of the present invention.
本发明的基于WIFI信号进行门窗关闭检测的方法,包括:The method for detecting door and window closure based on WIFI signal of the invention comprises:
步骤1:采集室内WIFI路由器发出的无线信号,且需要标注此时门窗开闭状态;Step 1: Collect the wireless signal sent by the indoor WIFI router, and mark the opening and closing state of the door and window at this time;
步骤2:从接收到的无线信号中提取出即时CSI信号;Step 2: extracting an instantaneous CSI signal from the received wireless signal;
步骤3:据一定时间窗口内提取的即时CSI信号,计算此窗口期内的CSI数值的平均数、方差、中位数、以及提出混杂度指标等作为信号特征;Step 3: Calculate the average number, variance, median, and the proposed degree of hybridization of the CSI values in the window period according to the instantaneous CSI signal extracted in a certain time window as a signal feature;
步骤4:根据CSI信号混杂程度,确定最优的窗口长度和窗口重叠度;Step 4: Determine an optimal window length and window overlap according to the degree of hybridization of the CSI signals;
步骤5:信号特征输入到智能算法中,进行模型训练,完成后即可判断门窗状态;Step 5: The signal feature is input into the intelligent algorithm to perform model training, and the door and window state can be judged after completion;
步骤3中时间窗口如图1所示的最高测频监率检验时的时间窗口,其中,横轴是时间轴,每一个数字方块代表按照时间顺序采集的CSI数据;W1是时间窗口1,如此,图1中共表示了8个时间窗口,窗口长度是10。The time window in step 3 is the time window of the highest frequency monitoring rate test shown in FIG. 1, wherein the horizontal axis is the time axis, and each digital square represents CSI data collected in time series; W1 is time window 1, so In Figure 1, a total of eight time windows are shown, and the window length is 10.
图2是最低频率监测检验时的时间窗口示意图,其中,横轴是时间轴,每一个数字方块代表按照时间顺序采集的CSI数据;W1是时间窗口1,如此,图中共表示了3个时间窗口,窗口长度是10。2 is a schematic diagram of a time window at the time of the lowest frequency monitoring check, wherein the horizontal axis is the time axis, each digital square represents CSI data collected in chronological order; W1 is time window 1, and thus, three time windows are represented in the figure. The window length is 10.
图3是可变的时间窗口长度示意图,w1与w2的窗口长度为5,w3和w4的长度10.时间窗口可以根据信号变化而动态调整。Figure 3 is a schematic diagram of variable time window lengths, the window lengths of w1 and w2 are 5, and the lengths of w3 and w4 are 10. The time window can be dynamically adjusted according to signal changes.
所述步骤4中,时间窗口的重叠程度,由CSI信号的混杂度指标来确定。但其最高、最低的重叠程度,由图1、图2中的图形所限定。In the step 4, the degree of overlap of the time window is determined by the degree of miscibility of the CSI signal. However, the highest and lowest degree of overlap are defined by the graphs in Figures 1 and 2.
计算方法如下:The calculation method is as follows:
当混杂度指标持续增加时,每10秒(可预先设定),相邻时间窗口增加一个重叠CSI数据包,但需保证两个相邻的时间窗口中至少有一个数据包不完全相 同。如图1所示。When the hysteresis indicator continues to increase, every 10 seconds (pre-settable), an overlapping CSI packet is added to the adjacent time window, but it is necessary to ensure that at least one of the two adjacent time windows is not identical. As shown in Figure 1.
当混杂度指标没有增加时,每5秒(可预先设定),相邻时间减少增加一个重叠CSI数据包,但需保证两个相邻的时间窗口在时间上是连续的。如图2所示。When the hysteresis index is not increased, every 5 seconds (pre-settable), the adjacent time is reduced by adding an overlapping CSI packet, but it is necessary to ensure that two adjacent time windows are consecutive in time. as shown in picture 2.
图4是时间窗口的重叠部分在减少的示意图。Figure 4 is a schematic illustration of the overlap of the overlapping portions of the time window.
混杂度指标计算方法是:The calculation method of the hybridity index is:
Y=abs(中位数pre–中位数cur)+abs(方差pre–方差cur)+abs(均值pre–均值cur)Y=abs (median pre–median cur)+abs (variance pre–variance cur)+abs (mean pre–mean cur)
其中,among them,
Y:表示混杂度指标,代表现在CSI信号的抖动情况;Y: indicates the degree of confounding, which represents the jitter of the current CSI signal;
中位数、方差、均值是由时间窗口内CSI振幅计算出的时序特征值;The median, variance, and mean are time-series feature values calculated from the CSI amplitude in the time window;
其中参数的的下标Pre表示上一个时间窗口;下表Cur表示当前的时间窗口。The subscript Pre of the parameter indicates the previous time window; the table Cur below indicates the current time window.
所述步骤4中,根据当前的CSI信号混杂程度,调整时间窗口大小。当混杂度指标持续增加时,每15秒(可预先设定),窗口长度减“1”,最小窗口长度为2(可手动设置)。当混杂度指标没有增加时,每10秒(可预先设定),窗口长度加“1”,最大窗口长度为10(可手动设置)。In the step 4, the time window size is adjusted according to the current CSI signal mixing degree. When the hysteresis index continues to increase, every 15 seconds (pre-settable), the window length is reduced by "1" and the minimum window length is 2 (can be set manually). When the hysteresis indicator does not increase, every 10 seconds (pre-settable), the window length is increased by "1" and the maximum window length is 10 (can be set manually).
获取CSI信号后,通过时间窗获取一段数据后,计算平均数、方差、偏差等信号时域统计值,然后进行求出混杂度指标。将这些统计指标用以训练模型,并用以对门窗开闭的判断。After acquiring the CSI signal, after obtaining a piece of data through the time window, the time domain statistics of the average number, variance, and deviation are calculated, and then the hybridity index is obtained. These statistical indicators are used to train the model and are used to judge the opening and closing of doors and windows.
值得说明的是,虽然前述内容已经参考若干具体实施方式描述了本发明创造的精神和原理,但是应该理解,本发明并不限于所公开的具体实施方式,对各方面的划分也不意味着这些方面中的特征不能组合,这种划分仅是为了表述的方便。本发明旨在涵盖所附权利要求的精神和范围内所包括的各种修改和等同布置。It is to be understood that the foregoing description has been described with reference to the specific embodiments of the invention Features in the aspects cannot be combined, and this division is for convenience only. The invention is intended to cover various modifications and equivalents
Claims (4)
- 一种基于WiFi信号的门窗开闭状态检测方法,其特征在于,该方法包括以下步骤:A method for detecting opening and closing state of a door and window based on a WiFi signal, characterized in that the method comprises the following steps:步骤1,采集室内WIFI路由器发出的WiFi无线信号,标注此时门窗开闭状态;Step 1: Collect the WiFi wireless signal sent by the indoor WIFI router, and mark the opening and closing state of the door and window at this time;步骤2,从接收到的WiFi无线信号中提取出即时CSI(Channel State Information,信道状态信息)信号;Step 2: extracting an instant CSI (Channel State Information) signal from the received WiFi wireless signal;步骤3,根据设定的时间窗口内提取的即时CSI信号,计算此窗口期内的CSI数值的平均数、方差、中位数、以及混杂度指标作为信号特征;Step 3: Calculate an average number, a variance, a median, and a miscibility index of the CSI values in the window period according to the instantaneous CSI signal extracted in the set time window as a signal feature;步骤4,根据CSI信号混杂程度,确定最优的窗口长度和窗口重叠度;Step 4, determining an optimal window length and window overlap according to the degree of hybridization of the CSI signals;步骤5,将CSI信号特征输入到智能算法中,进行模型训练,完成后即可判断门窗状态,Step 5: input the CSI signal feature into the intelligent algorithm, perform model training, and determine the state of the door and window after completion.其中,混杂度指标计算方法是:Among them, the calculation method of the hybridity index is:Y=abs(中位数pre–中位数cur)+abs(方差pre–方差cur)+abs(均值pre–均值cur)Y=abs (median pre–median cur)+abs (variance pre–variance cur)+abs (mean pre–mean cur)Y表示混杂度指标,代表现在CSI信号的抖动情况;Y represents the degree of confounding, which represents the jitter of the current CSI signal;中位数、方差、均值是由时间窗口内CSI振幅计算出的时序特征值;The median, variance, and mean are time-series feature values calculated from the CSI amplitude in the time window;中位数、方差、均值下标Pre表示上一个时间窗口;The median, variance, and mean subscripts Pre represent the previous time window;中位数、方差、均值下标Cur表示当前的时间窗口。The median, variance, and mean subscripts Cur represent the current time window.
- 根据权利要求1所述的基于WIFI信号的门窗关闭检测方法,其特征在于,时间窗口的重叠程度,由CSI信号的混杂度指标来确定,计算方法如下:The WIFI signal-based door and window closure detection method according to claim 1, wherein the degree of overlap of the time window is determined by a hybridization index of the CSI signal, and the calculation method is as follows:当混杂度指标持续增加时,When the hybridity indicator continues to increase,每隔a秒,相邻时间窗口增加一个重叠CSI数据包,但需保证两个相邻的时间窗口中至少有一个数据包不完全相同;Adding an overlapping CSI packet to the adjacent time window every a second, but ensuring that at least one of the two adjacent time windows is not identical;当混杂度指标没有增加时,When the hysteresis indicator does not increase,每隔b秒,相邻时间减少增加一个重叠CSI数据包,但需保证两个相邻的时间窗口在时间上是连续的。Every b seconds, the adjacent time is reduced by adding an overlapping CSI packet, but it is necessary to ensure that two adjacent time windows are consecutive in time.
- 根据权利要求2所述的基于WIFI信号的门窗关闭检测方法,其特征在于,根据当前的CSI信号混杂程度,调整时间窗口大小,The method for detecting a door and window closure based on a WIFI signal according to claim 2, wherein the time window size is adjusted according to the current degree of hybridization of the CSI signal,当混杂度指标持续增加时,When the hybridity indicator continues to increase,每隔c秒,窗口长度减1,最小窗口长度为2;Every c seconds, the window length is reduced by 1, and the minimum window length is 2;当混杂度指标没有增加时,When the hysteresis indicator does not increase,每隔d秒,窗口长度加1,最大窗口长度为10。Every d seconds, the window length is increased by 1, and the maximum window length is 10.
- 根据权利要求3所述的基于wifi信号的门窗检测方法,其特征在于,The method for detecting a door and window based on a wifi signal according to claim 3, wherein获取CSI信号,通过时间窗获取一段数据后,计算平均数、方差、偏差信号时域统计值,然后进行求出混杂度指标;Obtain a CSI signal, obtain a piece of data through a time window, calculate a time domain statistical value of the mean, variance, and deviation signal, and then perform a hybridization index;将这些统计指标用以训练模型,并用以对门窗开闭的检测。These statistical indicators are used to train the model and are used to detect the opening and closing of doors and windows.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710994094.2 | 2017-10-23 | ||
CN201710994094.2A CN107797153B (en) | 2017-10-23 | 2017-10-23 | A kind of door and window open and-shut mode detection method based on WiFi signal |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2019080735A1 true WO2019080735A1 (en) | 2019-05-02 |
Family
ID=61533536
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2018/110225 WO2019080735A1 (en) | 2017-10-23 | 2018-10-15 | Method for detecting open and closed state of doors and windows based on wi-fi signals |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN107797153B (en) |
WO (1) | WO2019080735A1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107797153B (en) * | 2017-10-23 | 2019-07-12 | 上海百芝龙网络科技有限公司 | A kind of door and window open and-shut mode detection method based on WiFi signal |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104502894A (en) * | 2014-11-28 | 2015-04-08 | 无锡儒安科技有限公司 | Method for passive detection of moving objects based on physical layer information |
CN105303743A (en) * | 2015-09-15 | 2016-02-03 | 北京腾客科技有限公司 | WiFi-based indoor intrusion detection method and device |
US20160277529A1 (en) * | 2015-03-20 | 2016-09-22 | The Trustees Of The Stevens Institute Of Technology | Device-free activity identification using fine-grained wifi signatures |
CN106658590A (en) * | 2016-12-28 | 2017-05-10 | 南京航空航天大学 | Design and implementation of multi-person indoor environment state monitoring system based on WiFi channel state information |
CN106664265A (en) * | 2014-07-17 | 2017-05-10 | 欧利景无线有限公司 | Wireless positioning systems |
CN106772219A (en) * | 2017-03-08 | 2017-05-31 | 南京大学 | Indoor orientation method based on CSI signals |
CN106792808A (en) * | 2016-12-08 | 2017-05-31 | 南京邮电大学 | Los path recognition methods under a kind of indoor environment based on channel condition information |
WO2017100706A1 (en) * | 2015-12-09 | 2017-06-15 | Origin Wireless, Inc. | Method, apparatus, and systems for wireless event detection and monitoring |
CN107154088A (en) * | 2017-03-29 | 2017-09-12 | 西安电子科技大学 | Activity personnel amount method of estimation based on channel condition information |
CN107797153A (en) * | 2017-10-23 | 2018-03-13 | 上海百芝龙网络科技有限公司 | A kind of door and window open and-shut mode detection method based on WiFi signal |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104615244A (en) * | 2015-01-23 | 2015-05-13 | 深圳大学 | Automatic gesture recognizing method and system |
CN105828289B (en) * | 2016-04-20 | 2019-09-03 | 浙江工业大学 | A kind of passive indoor orientation method based on channel state information |
CN107241696B (en) * | 2017-06-28 | 2020-05-26 | 中国科学院计算技术研究所 | Multipath effect distinguishing method and distance estimation method based on channel state information |
-
2017
- 2017-10-23 CN CN201710994094.2A patent/CN107797153B/en active Active
-
2018
- 2018-10-15 WO PCT/CN2018/110225 patent/WO2019080735A1/en active Application Filing
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106664265A (en) * | 2014-07-17 | 2017-05-10 | 欧利景无线有限公司 | Wireless positioning systems |
CN104502894A (en) * | 2014-11-28 | 2015-04-08 | 无锡儒安科技有限公司 | Method for passive detection of moving objects based on physical layer information |
US20160277529A1 (en) * | 2015-03-20 | 2016-09-22 | The Trustees Of The Stevens Institute Of Technology | Device-free activity identification using fine-grained wifi signatures |
CN105303743A (en) * | 2015-09-15 | 2016-02-03 | 北京腾客科技有限公司 | WiFi-based indoor intrusion detection method and device |
WO2017100706A1 (en) * | 2015-12-09 | 2017-06-15 | Origin Wireless, Inc. | Method, apparatus, and systems for wireless event detection and monitoring |
CN106792808A (en) * | 2016-12-08 | 2017-05-31 | 南京邮电大学 | Los path recognition methods under a kind of indoor environment based on channel condition information |
CN106658590A (en) * | 2016-12-28 | 2017-05-10 | 南京航空航天大学 | Design and implementation of multi-person indoor environment state monitoring system based on WiFi channel state information |
CN106772219A (en) * | 2017-03-08 | 2017-05-31 | 南京大学 | Indoor orientation method based on CSI signals |
CN107154088A (en) * | 2017-03-29 | 2017-09-12 | 西安电子科技大学 | Activity personnel amount method of estimation based on channel condition information |
CN107797153A (en) * | 2017-10-23 | 2018-03-13 | 上海百芝龙网络科技有限公司 | A kind of door and window open and-shut mode detection method based on WiFi signal |
Also Published As
Publication number | Publication date |
---|---|
CN107797153B (en) | 2019-07-12 |
CN107797153A (en) | 2018-03-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
AU2020265650B2 (en) | Machine learning motion sensing with auxiliary sensors | |
Hailemariam et al. | Real-time occupancy detection using decision trees with multiple sensor types | |
Jin et al. | Robust adaptive event detection in non-intrusive load monitoring for energy aware smart facilities | |
CN104538041A (en) | Method and system for detecting abnormal sounds | |
CN103812577A (en) | Method for automatically identifying and learning abnormal radio signal type | |
CN102855757B (en) | Identification method based on queuing detector information bottleneck state | |
CN117411811B (en) | Intelligent fault monitoring method for power communication equipment | |
CN104299417B (en) | Vehicle identification method based on waveforms detection | |
CN109672485A (en) | Enter to invade movement velocity detection method in real time based on channel state information indoor occupant | |
CN109347584A (en) | Frequency spectrum sensing method based on Smoothing Prediction | |
CN109874148B (en) | Antenna feeder anomaly detection method, device and system and computer equipment | |
CN106936517A (en) | A kind of automatic recognition system and its method of abnormal radio signal | |
CN113110085A (en) | Intelligent home management system based on big data | |
CN106658921A (en) | Lamp control switch system | |
WO2019080735A1 (en) | Method for detecting open and closed state of doors and windows based on wi-fi signals | |
Alcalá et al. | Event-based detector for non-intrusive load monitoring based on the Hilbert Transform | |
Seppänen et al. | Modal analysis of power systems with eigendecomposition of multivariate autoregressive models | |
CN101106487A (en) | A method and device for detecting exception of network traffic | |
CN116933895B (en) | Internet of things data mining method and system based on machine learning | |
US11248981B2 (en) | Methods and apparatus to detect leaks based on temperature data | |
CN105914877A (en) | Remote intelligent monitoring apparatus for the running of an electric power system terminal | |
Jin et al. | A whole-home level intrusion detection system using WiFi-enabled IoT | |
CN111750932A (en) | Monitoring alarm system based on smart home | |
CN103166723A (en) | Cognitive radio sensor network spectrum sensing method based on extensible correlation function | |
CN105573136A (en) | Home environment quality monitoring system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18871422 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 18871422 Country of ref document: EP Kind code of ref document: A1 |