Port personnel behavior identification system based on WiFi cross-band communication

Abstract

The invention relates to a port personnel behavior recognition system based on WiFi cross-band communication, and belongs to the technical field of Internet of Things. According to the system, cross-band communication is carried out by using WiFi signals, multi-channel CSI data are obtained, and personnel behaviors are identified through feature extraction and a classification algorithm. According to the method, a cross-frequency communication mode is adopted in behavior recognition for the first time, a feature library is expanded, a channel selection algorithm based on feature weights is provided, and the recognition accuracy is effectively improved. The invention further provides a high-speed cross-frequency communication scheme which can be realized on the commercial WiFi equipment, and the synchronism of multichannel data is ensured. The method can be applied to the fields of port / wharf personnel safety monitoring, behavior analysis, man-machine interaction and the like, and has a wide application prospect.

Description

Technical Field

[0001] The invention belongs to the technical field of Internet of Things and relates to a port personnel behavior recognition system based on WiFi cross-band communication. Background Art

[0002] With the rapid development of science and technology and the popularization of computers in the 21st century, human-computer interaction has become the focus of attention and research in many countries, among which human behavior recognition occupies an important position. Human behavior recognition is of great significance to promoting the development of human-computer interaction technology and improving the quality of human life. Traditional human behavior recognition technology generally requires special equipment, such as human behavior recognition based on computer vision and human behavior recognition based on wearable sensor devices. Although their recognition accuracy is relatively high, the equipment is expensive, and the application scenarios and scope of action are very limited, and it will cause discomfort to people and involve personal privacy issues. Some scholars have proposed DI-Gesture, which is a real-time gesture recognition system with an average recognition rate of up to 97%, but due to the many limitations of millimeter-wave radar, it is currently difficult to promote to real life scenarios.

[0003] In recent years, with the rapid development of wireless communication technology, human behavior recognition technology based on WiFi perception has been widely studied. At present, the behavior recognition technology that can be actually applied to commercial WiFi devices can be divided into two categories. The first is based on the received signal strength indication (RSSI). The performance of the RSSI-based system is greatly affected by the link quality. In a complex environment, multipath propagation will cause fluctuations in link quality, so good performance cannot always be guaranteed. The second is based on channel state information (CSI). CSI is a fine-grained value device derived from the WiFi physical layer. It can reflect the frequency response of the channel to capture the phase and amplitude information of different subcarriers of the signal. More information is extracted to capture subtle changes in link quality. Therefore, the CSI-based system has good robustness to complex environments.

[0004] Although the channel state information (CSI)-based systems have a high recognition accuracy when identifying various human behaviors with high resolution, their shortcomings can be divided into the following three aspects: (1) The recognition accuracy of similar behaviors is not evaluated or their recognition accuracy is significantly low when identifying similar behaviors. (2) When using various classification algorithms based on deep learning, they select a sufficient number of training samples, but in some special scenarios, it is usually impossible to obtain a large number of behavior samples in a short time. (3) The CSI they obtain is only from a single channel, and the presence of noise will affect the accuracy of the classifier. In addition to environmental noise, the carrier frequency offset inside the device will also cause burst noise. In addition, "Wireless Communication" written by Professor A. Goldsmith shows that co-channel interference will also cause unstable mutations in the amplitude and phase of CSI. Therefore, even after filtering, some noise will still exist. These uncontrollable factors will seriously affect the recognition accuracy of the behavior recognition system working on a single channel, especially for similar behaviors. If the amplitude or phase of any subcarrier in the CSI jumps due to interference, it may lead to misjudgment of the behavior category.

[0005] On the basis of using WiFi signals to obtain CSI, in order to solve the above problems, in the present invention, WI-FHOP is proposed: a behavior recognition system based on WiFi cross-band communication, which can be implemented in the commercial WiFi device ESP32. WI-FHOP can maintain a high recognition accuracy when identifying similar behaviors and the number of training samples is small. First, a high-rate frequency hopping communication scheme suitable for commercial WiFi equipment ESP32 is proposed, and CSI data of different channels are obtained; then, the obtained CSI data is processed by filtering, behavior data interception, and data division according to channels; then, the data after channel division is subjected to principal component analysis, wavelet transform, feature extraction and standardization steps for feature analysis and extraction; then, a channel selection algorithm based on feature weights is proposed, which combines traditional classification algorithms (KNN, SVM, Bagging) to select the optimal channel according to the feature data of multiple channels, and the recognition result of the channel is used as the final recognition result. In this way, the influence of burst noise on a single channel is avoided, and the recognition accuracy of the system in identifying similar actions and a small number of training samples is improved; finally, the performance of WI-FHOP is evaluated through experiments. Summary of the invention

[0006] In view of this, the object of the present invention is to provide a port personnel behavior recognition system based on WiFi cross-band communication.

[0007] In order to achieve the above object, the present invention provides the following technical solutions:

[0008] The behavior recognition system based on WiFi cross-band communication of the present invention comprises the following steps:

[0009] Step 1, the present invention selects channel 1, channel 6 and channel 11 in the 2.4G WiFi frequency band. In cross-frequency communication, the most important thing is to ensure that the channel settings at both ends are consistent when sending and receiving data. However, due to the asynchrony of the clocks of the devices at both ends, the time of switching channels is different, which leads to the failure of sending data. This is the main reason affecting the cross-frequency communication rate. Based on this, a cross-frequency communication scheme is proposed, and the behavior data samples are collected using the scheme;

[0010] Step 2: Process the continuous CSI data received by the receiving end on multiple channels during the entire test period, including filtering out high-frequency noise in the original CSI using a Butterworth low-pass filter, extracting row data using a sliding window technique, and dividing data by channel;

[0011] Step 3: Analyze and extract the behavioral characteristics of the amplitude data on the channel, including using the principal component analysis (PCA) algorithm to reduce the dimension of the CSI amplitude, then perform wavelet transform (DWT) on each PCA principal component to extract the time-frequency characteristics, extract statistical features from the feature matrix after DWT (selecting six different statistical features of the mean, standard deviation, interquartile range, 0.5 percentile, 0.683 percentile and 0.95 percentile of the probability distribution), use the z-score normalization method to process the feature data, and convert all features to the same scale;

[0012] Step 4: After the data processing of the above steps is completed, the present invention proposes a channel selection algorithm based on feature weights, which can significantly improve the recognition accuracy no matter which benchmark classification algorithm is combined with it, such as KNN, SVM, and Bagging.

[0013] The beneficial effects of the present invention are:

[0014] 1. The present invention adopts cross-frequency communication in behavior recognition for the first time. The same action data can reflect different features on multiple different channels, thereby expanding the feature library.

[0015] 2. The present invention proposes a channel selection algorithm based on feature weights, which selects an optimal channel based on feature data on multiple channels in combination with a traditional classification algorithm, and uses the recognition result on this channel as the final recognition result, thereby avoiding the influence of burst noise on individual channels on the final recognition result and at the same time improving the recognition accuracy of the system in scenarios where similar behaviors are identified and the number of training samples is small.

[0016] 3. The present invention proposes a high-speed cross-frequency communication scheme that can be implemented on a commercial WiFi device ESP32, with a packet sending rate of up to 200 Hz, and ensures that the channels experienced by the CSI on each group of multiple channels in the WI-FHOP system are time-invariant.

[0017] Other advantages, objectives and features of the present invention will be described in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the following examination and study, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below in conjunction with the accompanying drawings, wherein:

[0019] Figure 1 is a flow chart of the present invention;

[0020] Figure 2 This is the schematic diagram of cross-frequency communication;

[0021] Figure 3 This is a schematic diagram of the deployment of this system at the dock yard;

[0022] Figure 4 This is the early warning flow chart. DETAILED DESCRIPTION

[0023] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0024] Among them, the drawings are only used for illustrative explanations, and they only represent schematic diagrams rather than actual pictures, and should not be understood as limitations on the present invention. In order to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of actual products. For those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0025] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right", "front", "rear", etc. indicate the orientation or position relationship, they are based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, the terms describing the position relationship in the drawings are only used for illustrative purposes and cannot be understood as limiting the present invention. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0026] Figure 1 The flow chart of the present invention is as follows:

[0027] Step 1: Consider the CSI signal propagation environment, which includes static reflectors (walls) and dynamic reflectors (people). The CSI data calculated by the receiving end should be the superposition of multiple path signals, which can be expressed by formula (1):

[0028]

[0029] Where H(f j ,t) and arg(H(f j ,t)) represent the amplitude and phase of the jth (j=1,2,...,51) subcarrier at time t, respectively. j is the frequency of the jth subcarrier, e -j2πΔft represents the phase offset caused by inconsistent carrier frequency, N represents a total of N multipaths, a k (f j ,t) is a complex number, which represents the propagation attenuation and initial phase offset of the kth multipath. It means that due to the propagation delay τ k (t) caused by the phase shift, n(f j ,t) represents noise. When the dynamic target in the link has a behavior action, a multipath (set as k°) in the environment changes, and the corresponding a k° (f j ,t) and τ k°(t) also changes, causing the CSI amplitude of the received signal to change, and by intercepting the CSI data block corresponding to human activity and analyzing its characteristics, different behavioral activities can be distinguished based on different characteristics. The WI-FHOP system adopts cross-frequency communication, the purpose of which is to combine the different amplitude characteristics reflected by the same behavior in different frequency bands to improve the recognition accuracy. Therefore, it is hoped that the channel experienced by each set of multi-channel CSI data received by the receiver is time-invariant, because only when the multi-channel CSI data corresponds to the same time series, the different characteristics of the same action reflected in different frequency bands are comparable. In human action recognition, all data packets received within the channel coherence time can be considered to arrive at the receiver at the same time, so the total time interval of each set of CSI data on multiple channels received by the receiver should be less than the channel coherence time. Channel coherence time T c It can be expressed as where f d is the Doppler shift. Previous researchers have studied the Doppler shift caused by typical mobile environments. Usually, the Doppler shift caused by human activity is less than 12 Hz, and the corresponding T c It is about 40ms. Assuming that the time when a group of CSI data containing 3 channels arrives at the receiving end in sequence is t1, t2, and t3 respectively, the above content can be expressed by formula (2):

[0030] (t3-t2)+(t2-t1)≤40ms (2)

[0031] Therefore, this paper proposes a high-speed cross-frequency communication scheme. The frequency of the same subcarrier on different channels is different, that is, f in formula (1) j Different, according to formula (1), this makes the CSI amplitudes of different frequency bands different. In addition, the reason why this paper chooses channels 1, 6 and 11 in the 2.4G WiFi band is that in the 2.4G WiFi band, the spectra of channels 1, 6 and 11 do not overlap with each other, and the burst noises they are subjected to are also unrelated. This leads to a decrease in the correlation of the CSI amplitude characteristics of different frequency bands. Because for the same human behavior, it reflects different characteristics in different frequency bands. This is equivalent to communicating on three different channels on the basis of a single frequency band. It can not only avoid the impact of burst noise on certain frequency bands on the recognition accuracy, but also expand its feature number to three times the original. The more features there are, the more fully a behavior can be described. In cross-frequency communication, the most important thing is to ensure that the channel settings at both ends of the transmitter and receiver are consistent when sending and receiving data. However, due to the asynchronous clocks of the devices at both ends of the transmitter and receiver, the time for switching channels is different, which leads to the failure of sending data. This is the main reason affecting the cross-frequency communication rate. In response to this problem, the proposed cross-frequency communication scheme is as follows Figure 2First, the sender sends data on channel 1. The receiver receives the data at t1 and sends an ACK signal to the sender almost at the same time. Then, the sender switches the channel to the next channel 6 at t2. The sender receives the ACK signal at t3, switches the channel to the next channel 6 at t4, and sends data on channel 6 at t5. It can be seen that the sender does not send data immediately after completing the channel switch, but after a delay of t d This is the reality. Due to the limitation of API, there is an additional delay in the actual start of channel switching. This means that the time t4 when the sender actually completes the channel switching may be less than the time t2 when the receiver actually completes the channel switching. Therefore, a delay t is artificially imposed on the sender after the channel switching is completed. d The purpose is to ensure that t5>t2. The subsequent channel switching process is the same.

[0032] Step 2: First, use a Butterworth low-pass filter to filter out the high-frequency noise in the original CSI data. Then, according to formula (1), when there is human action, H(f j ,t) will change, so we can use H(f j ,t) to analyze the changes and determine whether human behavior is detected at the current time, and extract the CSI amplitude data block corresponding to each behavior action for subsequent behavior recognition. This paper uses sliding window technology and selects the variance within the sliding window as a metric to characterize signal jitter. It extracts the changes in the data stream within the sliding window and analyzes the signal jitter in a short period of time. The sliding window mean Δm of the amplitude of the jth subcarrier of the tth sliding window j,t Formula (3) and variance x j,t The calculation formula (4) is as follows:

[0033]

[0034]

[0035] Where l represents the sliding window length. For the CSI amplitude corresponding to a certain time period, when the variance of the consecutive k sliding windows is greater than a certain threshold s, it is considered that human behavior exists in the time period, where k is defined as the buffer band size. In the WI-FHOP system, after many actual verifications, the interception effect is best when l = 80, k = 100, and s = 0.4. The intercepted behavior data contains amplitude data on multiple channels. The data can be divided by the channel label on the CSI data packet. The data on each divided channel represents the amplitude jitter characteristics of the same behavior in each frequency band.

[0036] Step 3: The CSI signal contains information about 51 subcarriers. For the behavior recognition system, much of this information is redundant. Therefore, this paper first uses the PCA (Principal Component Analysis) algorithm to reduce the dimension of the CSI amplitude data, decomposes the covariance matrix by eigenvalues, and arranges it from large to small to obtain [λ1,λ2,...,λ 51 ], this paper selects the three principal components corresponding to [λ2,λ3,λ4], because the first principal component of PCA contains a lot of burst noise caused by the device itself, and [λ2,λ3,λ4] already satisfies λ2+λ3+λ4≥0.99. Through PCA, the original 51×N CSI amplitude matrix is ​​reduced to 3×N, where N represents the number of CSI packets. Then this paper performs Discrete Wavelet Transformation (DWT) on each PCA principal component to extract the time-frequency characteristics. The present invention sets the number of wavelet layers to 9. Through DWT, the matrix dimension changes from 3×N to [3×(9+1)]×N. Define H W is the characteristic matrix after wavelet transformation, where H W The jth row of H W,j The time-frequency component of a wavelet layer representing a principal component. Each time-frequency component obtained by DWT represents a different speed range. The size of each frequency component can help analyze the speed and intensity of different behaviors. Although the time-frequency characteristics can well reflect the speed and intensity of the behavior, the speed or rhythm of each behavior is inconsistent, resulting in inconsistent time lengths, that is, the length N of the feature sequence is inconsistent, which makes most pattern recognition methods unusable. Therefore, the present invention extracts H W The statistical information of the feature sequence is used to make the length of the feature sequence consistent. And six different statistical features of the probability distribution are selected: mean, standard deviation, interquartile difference, 0.5 percentile, 0.683 percentile and 0.95 percentile;

[0037] ① Mean: The mean is an indicator used in statistics to represent the center point of data. It can characterize the central trend of the time-frequency components of the same behavior at different times. Its calculation formula (5) is as follows:

[0038]

[0039] ② Standard deviation: Standard deviation is a statistical indicator used to indicate the degree of dispersion of data. It can characterize the fluctuation of time-frequency components of the same behavior at different times. Its calculation formula (6) is as follows:

[0040]

[0041] ③ The interquartile range is a robust statistic that characterizes the dispersion of data. Its calculation formula (7) is as follows:

[0042] IQR(H W,j )=Q3(H W,j )-Q1(H W,j )(7)

[0043] Among them, Q3(H W,j ) and Q1(H W,j ) represent H W,j The 3 / 4 quantile and 1 / 4 quantile of .

[0044] 3d. The 0.5 lower quantile, 0.683 lower quantile, and 0.95 lower quantile of the probability distribution: These three parameters are based on H W,j The cumulative probability distribution of They are three parameters commonly used in probability statistics, and their calculation formula (8) is as follows:

[0045]

[0046] There are 6 statistical features in total. Therefore, after statistical feature extraction, the amplitude jitter characteristics of any behavior on each channel can be described by a vector of length 6×3×(9+1). The feature data is processed using the z-score normalization method, and all features are converted to the same scale.

[0047] Step 4. This paper proposes a channel selection algorithm based on feature weights. Taking SVM as the benchmark classification algorithm and the binary classification problem as an example, the channel selection algorithm is introduced in detail below.

[0048] Define two different categories of behavior labels as -1 and 1. c,v Represents the 1×30 feature matrix corresponding to the vth statistical feature of a test behavior containing an unknown category on channel c, where c=1,6,11 represents different channels and v=1,2,3,4,5,6 corresponds to the six statistical features mentioned in the previous section. c,v Represents the m×30 feature matrix corresponding to the vth statistical feature of m training behaviors of two categories on channel c.

[0049] The algorithm consists of the following four steps:

[0050] 4a: By Ftr c,v Get the weight W of each feature v .

[0051] 4b: Ftr c,v As a training feature database, Fts c,vThe classification result RS is obtained by using the SVM classification algorithm c,v and P c,v , R.S. c,v is the classification result label, P c,v is the probability corresponding to the classification result, and this step is repeated until the classification results of all statistical features on all channels are obtained.

[0052] 4c: Calculate the total weight Q of each channel according to the formula c .Q c <0 means that under channel c, the label of the behavior is initially judged to be -1, otherwise Q c When ≥0, it is judged as 1.

[0053] 4d: Based on Q1, Q6, Q 11 The value distribution is used to make the final judgment on the behavior.

[0054] 4a can be understood as the work in the offline stage, finding the weight W of the first feature v , for Ftr c,1 Each row of is used as test data, and the remaining m-1 are used as training data. SVM is also used for classification and recognition. This step is repeated until the classification results of the statistical feature on all channels are obtained. During this period, the number of test behaviors num1 that are correctly classified with this feature is recorded. Then W1=num1 / (m×3), and W2, W3, ..., W6 can be obtained similarly.

[0055] Steps 4b and later are the work of the online stage. In 4b, a total of 6×3 groups of RS can be obtained. c,v and P c,v Based on this, in 4c, the corresponding RS c,v , P c,v and W v Multiply to get q c,v , that is, q c,v =RS c,v ×P c,v ×W v , based on RS c,v The positive and negative properties of q c,v It may be positive or negative. The total weight of each channel is Q c It is obtained by the following formula (9):

[0056]

[0057] Q c <0 means that after weighting under channel c, the label of the recognition result is -1 corresponding to q c,v dominates, that is, the behavior label of the test behavior under channel c is more likely to be -1, otherwise Q cWhen ≥0, it is more likely to be 1.

[0058] In 4d, first Q1, Q6, Q 11 Find the absolute values ​​of |Q1|,|Q6|,|Q 11 |, which is called the confidence of each channel in this paper, and 0≤|Q1|,|Q6|,|Q 11 |≤6, find the one with the largest absolute value. The larger the absolute value, the greater the probability that it is a certain behavior label under this channel. Here, we assume that |Q1| is the largest, and its corresponding channel number is used as the preliminary optimal channel c op =1, then count Q1, Q6, Q 11 The number of channels with the same positive and negative sign as Q1 is recorded as c sm , so c sm The range of the value is [1,2,3], and then the difference between |Q1| and the other two absolute weights is calculated, recorded as When c sm ≥2, maintain the original pair c op When c sm = 1, set a threshold Q related to the maximum total weight min and a threshold related to the absolute weight difference If |Q1| min , and as long as One of them satisfies When c is modified op For any other channel, because the recognition results of the other two channels are the same. The above situation means that on the channel with the largest total weight, it is not very sure to think which category the behavior belongs to, but there are channels with confidence close to this channel on other channels, and the recognition results of the other two channels are opposite to this channel. Therefore, if the principle of maximum confidence is still adhered to at this time, the misjudgment rate will be relatively high. sm = 1, the original pair c is still maintained in other sub-cases op Finally, according to c op The corresponding Q c , if Q c <0, the final output recognition result label is -1, otherwise the output is 1.

[0059] The above content fully describes the specific process of the channel selection algorithm when SVM is used as the benchmark classification algorithm. Similarly, when KNN or Bagging is used as the benchmark classification algorithm, the channel selection algorithm can also be implemented because they can get RS for any recognition result. c,v and P c,v In addition, in the WI-FHOP system, according to the actual performance, set Q min ​=2.8, When , the average recognition accuracy is the highest.

[0060] Terminal scene application:

[0061] The tallying operation at the general cargo terminal involves the movement and stacking of large timber, which can easily cause safety accidents and personal injuries. There are certain safety hazards (for example, when the timber forklift / transport truck is unloading timber, there are other workers in the operation area but they are not discovered). Therefore, safety management of the tallying operation is required. Through the implementation of this technology, accidents that occur during the tallying process at the timber terminal can be prevented.

[0062] Traditional safety protection measures are generally implemented through video surveillance. However, since a large amount of wood is stored in the yard, there is a large visual blind spot. At the same time, dock operations often take place at night, and video surveillance is affected by dim light and cannot provide effective early warning.

[0063] Therefore, the deployment of a behavior recognition system based on WiFi cross-band communication in the yard can not only identify whether there are people, but also identify people's behaviors, such as squatting and sitting, which further improves the protection measures. The schematic diagram of the deployment of this system in the terminal yard is shown in the figure below. Figure 3 shown.

[0064] Early warning process Figure 4 As shown, the steps are:

[0065] 1. Deploy WIFI devices near the timber yard to collect CSI data;

[0066] 2. Each WIFI device will transmit the collected data back to the central server;

[0067] 3. The central server processes the data and performs cross-band communication behavior recognition according to the method of this system;

[0068] 4. Since the CSI data sent back by each WIFI device has an IP or MAC address tag or some kind of association, the identified results can be matched with the WIFI device;

[0069] 5. The installation displacement of the WIFI device can also correspond to the IP or MAC of the WIFI, that is, it can be known that the result of identifying a person occurred in the coverage area of ​​that WIFI device.

[0070] 6. Based on the results of step 5, issue an early warning to avoid safety accidents.

[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution, which should be included in the scope of the claims of the present invention.

Claims

1. A port personnel behavior recognition system based on WiFi cross-band communication, characterized by: The system includes: A data acquisition module is used to collect channel state information (CSI) data from multiple different channels and send the collected CSI data to the data processing module; The data processing module is used to filter the received CSI data, intercept the behavior data and divide the channels, and send the processed behavior data blocks to the feature analysis module; A feature analysis module is used to perform principal component analysis, wavelet transform and statistical feature extraction on the received behavior data block, and send the extracted feature vector to the channel selection module; The channel selection module is used to select a channel according to the received feature vector and output the final recognition result.

2. According to claim 1, the port personnel behavior recognition system based on WiFi cross-band communication is characterized in that: The CSI data collected by the data collection module comes from channel 1, channel 6 and channel 11 in the 2.4 GHz WiFi frequency band.

3. According to claim 1, the port personnel behavior recognition system based on WiFi cross-band communication is characterized in that: The data processing module comprises: The filtering unit is used to filter out high-frequency noise in the original CSI using a Butterworth low-pass filter, as shown in the following formula: Among them, Δm j,t represents the sliding window mean of the amplitude of the jth subcarrier in the tth sliding window; H(f j ,t) represents the amplitude of the jth subcarrier at time t, f j represents the frequency of the jth subcarrier, f j ,t is the parameter of H() function; l represents the sliding window length. For the CSI amplitude corresponding to a certain time period, when the variance of d consecutive sliding windows is greater than a certain threshold s, it is considered that there is human behavior in this time period; d consecutive sliding windows are defined as the buffer band; j represents the index number of the subcarrier, j=1,2,...,51; The behavior data interception unit is used to extract the behavior data using the sliding window technology, and calculate the sliding window variance according to the following formula to determine whether there is human behavior; Among them, x j,t represents variance; Represents a channel division unit, which is used to divide the data into multiple channels according to the channel label on the CSI data packet; the intercepted behavior data contains amplitude data on multiple channels, and the data is divided according to the channel label on the CSI data packet. The data on each divided channel represents the amplitude jitter characteristics of the same behavior in each frequency band.

4. According to claim 1, the port personnel behavior recognition system based on WiFi cross-band communication is characterized in that: The feature analysis module comprises: The principal component analysis unit is used to reduce the dimension of the CSI amplitude data, as shown in the following formula: Among them, H(f j ,t) represents the amplitude of the jth subcarrier at time t, arg(H(f j ,t)) represents the phase of the jth subcarrier at time t, j = 1, 2, ..., 51, f j represents the frequency of the jth subcarrier, e -j2πΔft represents the phase offset caused by inconsistent carrier frequency, K represents the number of multipaths, a k (f j ,t) is a complex number, which represents the propagation attenuation and initial phase offset of the kth multipath. It means that due to the propagation delay τ k (t) caused by the phase shift, n(f j ,t) represents noise; when the dynamic target in the link has a behavior action, a multipath in the environment, set as k°, propagates and changes, and the corresponding a k° (f j ,t) and τ k° (t) changes, resulting in a change in the CSI amplitude of the received signal, and by intercepting the CSI data block corresponding to human activity and analyzing the characteristics of the CSI data block, different behavioral activities are distinguished based on different characteristics; A wavelet transform unit is used to perform wavelet transform on each PCA principal component to extract time-frequency features; A statistical feature extraction unit is used to extract statistical features from the feature matrix after DWT, including mean, standard deviation, interquartile range, 0.5 percentile, 0.683 percentile and 0.95 percentile; The mean is an indicator used statistically to represent the center point of the data, representing the central trend of the time-frequency components of the same behavior at different times. The calculation formula is: Among them, mean(H W,j ) represents the mean, N represents the number of CSI packets, and n represents the number of CSI packets; H W,j Represents the time-frequency component of a certain layer of wavelet of a certain principal component; The standard deviation is a statistical indicator used to indicate the degree of dispersion of data, which characterizes the fluctuation of the time-frequency components of the same behavior at different times. The calculation formula is: Among them, std(H W,j ) represents the standard deviation; The interquartile range is a robust statistic that characterizes the dispersion of data. The calculation formula is: IQR(H W,j )=Q3(H W,j )-Q1(H W,j ) Among them, IQR (H W,j ) represents the interquartile range; Q3(H W,j ) and Q1(H W,j ) represent H W,j The 3 / 4 quantile and 1 / 4 quantile of; The 0.5 lower quantile, 0.683 lower quantile, and 0.95 lower quantile of the probability distribution; these three parameters are based on H W,j The cumulative probability distribution of What we get are three parameters commonly used in probability statistics, and the calculation formula is: Among them, α 0.5 represents the 0.5 lower quantile of the probability distribution, α 0.683 represents the 0.683 lower quantile, α 0.95 Represents the 0.95 lower quantile.

5. According to claim 1, the port personnel behavior recognition system based on WiFi cross-band communication is characterized in that: The channel selection module adopts a channel selection algorithm based on feature weights, which combines the KNN classification algorithm, the SVM classification algorithm and the Bagging classification algorithm to select the optimal channel according to the feature data of multiple channels, and uses the recognition result of the channel as the final recognition result.

6. The port personnel behavior recognition system based on WiFi cross-band communication according to claim 5 is characterized by: The channel selection algorithm based on feature weights comprises the following steps: Offline stage: Calculate the weight of each feature as shown below: Among them, Q c represents the total weight of each channel; Q c <0, indicating that after weighting under channel c, the label of the recognition result is -1 corresponding to q c,v dominates, that is, the behavior label of the test behavior under channel c is more likely to be -1, Q c ≥0, indicating that it is more likely to be 1; v=1,2,3,4,5,6; q c,v represents the calculation weight of the vth feature of the cth channel; Online stage: The total weight of each channel is calculated according to the weight of each feature, and the optimal channel is selected according to the size of the total weight.

7. The port personnel behavior recognition system based on WiFi cross-band communication according to claim 6 is characterized by: The offline phase includes the following steps: For each feature, the feature matrix containing one test behavior of the unknown category on the channel is used as the test data, and the rest is used as the training data. SVM is used for classification and recognition, and the number of correctly classified test behaviors is recorded to obtain the weight of this feature.

8. The port personnel behavior recognition system based on WiFi cross-band communication according to claim 6 is characterized by: The online phase includes the following steps: For each channel, the total weight is calculated based on the weight of each feature and the classification result; The optimal channel is selected according to the total weight, and the recognition result on this channel is used as the final recognition result.

9. A method for identifying port personnel behavior using the system according to any one of claims 1 to 8, characterized in that: The following steps are involved: Collect CSI data from multiple different channels; Filter the collected CSI data, extract behavioral data, and divide channels; Perform principal component analysis, wavelet transform and statistical feature extraction on the data after channel division; The optimal channel is selected according to the feature weight, and the recognition result on this channel is used as the final recognition result.

10. A method for early warning using the method of claim 9, characterized in that: The following steps are involved: Deploy WIFI devices near the timber yard to collect CSI data; Each WIFI device will transmit the collected data back to the central server; The central server processes the data and performs cross-band communication behavior recognition according to the method of this system; The CSI data sent back by each WIFI device is marked with an IP or MAC address, and the identification result can be matched with the WIFI device; The installation displacement of the WIFI device corresponds to the IP or MAC of the WIFI, and the result of identifying a person is that it occurs within the coverage area of ​​the WIFI device; Based on the result of identifying people, early warning is issued to avoid safety accidents.

Images