CN109325399B - Stranger gesture recognition method and system based on channel state information - Google Patents
Stranger gesture recognition method and system based on channel state information Download PDFInfo
- Publication number
- CN109325399B CN109325399B CN201810771509.4A CN201810771509A CN109325399B CN 109325399 B CN109325399 B CN 109325399B CN 201810771509 A CN201810771509 A CN 201810771509A CN 109325399 B CN109325399 B CN 109325399B
- Authority
- CN
- China
- Prior art keywords
- data
- module
- value
- gesture
- classifier
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
- H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
- H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
- H04B7/0613—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission
- H04B7/0615—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal
- H04B7/0619—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal using feedback from receiving side
- H04B7/0621—Feedback content
- H04B7/0626—Channel coefficients, e.g. channel state information [CSI]
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Image Analysis (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention belongs to the field of artificial intelligence, and particularly relates to a stranger gesture recognition method and system based on channel state information in a wireless network. The system comprises four modules, namely an acquisition and preprocessing module of original data, an effective data denoising module, a gesture abnormal data extraction module and a characteristic value extraction and classifier classification module. The invention takes the maximum value and the wavelet variance in the wave peak values in the time domain characteristics as characteristic values and finishes the classification of strangers and non-strangers through a random forest classifier. The method has high identification accuracy and can be used for classifying the personnel in the actual use environment. The invention discloses a method for using channel state information in a commercial wireless network environment, which can identify gestures of strangers from subtle differences of the same gesture actions of different people and ensure that the safety of intelligent household users is guaranteed by identifying the gesture actions of the strangers.
Description
Technical Field
The invention belongs to the field of artificial intelligence, and particularly relates to a stranger gesture recognition method and system based on channel state information in a wireless network.
Background
With the continuous maturity of internet technology, the cost of network hardware equipment and network software equipment is gradually reduced, and the output of intelligent mobile terminal equipment such as mobile phones and mini-laptops is increased year by year, thereby driving the rapid development of wireless WiFi to a great extent. The shadow of the wireless WiFi is visible anywhere in commercial places such as restaurants, large-scale comprehensive markets and chain hotels, or public places such as railway stations, comprehensive hospitals and schools. The popularization of the multifunctional electric heating device brings great convenience to people in both working and living.
Channel state information in the field of wireless communications refers to known channel characteristics of the communication link. The channel state information may be used to describe not only the propagation process of the signal between the transmitting end and the receiving end, but also the composite effect of the signal, such as the scattering of the signal, the fading of the signal, and the attenuation of power with the increase of distance, so the channel state information is also called channel estimation. The channel state information can make the signal transmission adapt to the current channel state, thereby making the signal achieve the purpose of reliable transmission in a multi-antenna system with high data rate.
Although some existing methods can identify strangers in reality, the basis for distinguishing the strangers is based on the large-scale human body motions of different people and different gesture motions defined for different people, the problem is not solved by the same gesture motions of different people, and more importantly, the method cannot define different gesture motions for each recognized person or require the recognized person to perform a large amount of human body motions in real life. Therefore, the method for identifying the strangers by finding the differences of the same gesture actions of different people becomes a brand-new stranger identification method.
Disclosure of Invention
The invention aims to provide a stranger gesture recognition method based on channel state information.
The invention aims to provide a stranger gesture recognition system based on channel state information.
The object of the invention is achieved in that the method comprises the following steps:
(1) firstly, a tool which is released by Washington university and runs on a commercial 802.11n network card is used, the tool runs under a Linux operating system which is provided with 3 antennae on an Intel5300 wireless network card, and wireless channel state information based on 802.11 standard is collected.
(2) Extracting corresponding 90 pieces of subcarrier information from the collected information after preprocessing operation, and extracting phase information from the information;
(3) performing linear transformation on the phase data in the extracted subcarriers, and separating effective phase data from the phase data;
(4) performing Gaussian filtering denoising processing on the phase data subjected to linear transformation;
(5) extracting an abnormal value from the data of a certain subcarrier after the denoising operation by using an improved sliding quartile range method;
(6) calculating the value of the maximum peak in each group of abnormal data for the extracted abnormal value data, calculating the value of the small wave variance in each group of abnormal data, and taking the small wave variance and the small wave variance as characteristic values on a time domain;
(7) extracting characteristic values in the residual data according to the method in the step (6) to form a characteristic value data matrix of the test set;
(8) respectively putting data of each gesture action in a characteristic value data matrix as a training set into a random forest classifier for training, and ensuring that no intersection exists among characteristic values of different gestures in the training set;
(9) and substituting the characteristic matrixes of the test set and the training set into a random forest classifier for classification, and displaying the experimental result through a data line graph of stranger identification accuracy.
The step (5) above, wherein the calculation flow of the sliding quartering distance outlier extraction algorithm based on the improved algorithm is as follows:
(5.1) setting the size of the sliding window to be N;
(5.2) quartering the signal data after being arranged from small to large, and extracting the value of the 3/4 th position;
(5.3) respectively calculating the average value of each section in four equally divided sections of data, comparing the average value with the median of the section of data, and selecting the larger one of the average value and the median as a value to be used next;
(5.4) summing the value of each segment obtained in the previous step with the data of the 3/4 th position point of the segment, thereby obtaining an upper bound curve of the sliding quartile distance in the segment;
(5.5) selecting a check coefficient with a value less than 1, and multiplying the check coefficient with data in the upper-bound curve to obtain an improved upper-bound curve;
(5.6) regarding the points exceeding the improved upper-bound curve as outlier points and extracting them all.
A stranger gesture recognition system based on channel state information comprising: the system comprises an original data acquisition and preprocessing module, an effective data denoising module, a gesture abnormal data extraction module and a characteristic value extraction and classifier classification module;
the acquisition module of the original data is mainly completed by a CSI Tools developed by Washington university, and the Tools can form an m multiplied by n matrix according to the number of transmitting antennas m and receiving antennas n for representing the collected original data, wherein the original data comprises amplitude and phase information; the collected original phase data is subjected to linear transformation through a preprocessing module of the original data to eliminate the originally obvious noise in the signal, so that effective phase information is obtained; storing the information in a temporary data file in matlab software in a corresponding data structure;
the effective data denoising module is used for processing the effective phase data extracted in the last step, removing noise mixed in the effective phase data, and simultaneously keeping the characteristics of the emitters of different gestures, which are different from others;
the gesture abnormal data extraction module is mainly used for separating gesture motion data mixed in the data after denoising processing by using an improved sliding quartile moment method;
the characteristic value extraction and classifier classification module comprises a characteristic value extraction module and a classifier classification module, wherein the characteristic value extraction module extracts one or more characteristic values of different people making the same gesture motion in a time domain, a frequency domain or a time-frequency domain from the gesture motion data module obtained in the last step; the classifier classification module selects a classifier which can distinguish characteristic value data of different people, and classifies the extracted data of all people through trained training set characteristic values by using the classifier.
The step (1), the step (2) and the step (3) are realized by the raw data acquisition and preprocessing module, the step (4) is realized by the effective data denoising module, the step (5) is realized by the gesture abnormity extraction module, the steps (6) to (9) are realized by the characteristic value extraction and classifier classification module, the step (6) is realized by the characteristic value extraction module, and the steps (7) to (9) are realized by the classifier classification module
The method has the advantages that the method for identifying strangers and non-strangers through slight differences of the gesture actions of different people is provided, the maximum value and the wavelet variance in the wave peak values in the time domain features are used as feature values, and classification of the strangers and the non-strangers is completed through the random forest classifier. The method has high identification accuracy and can be used for classifying the personnel in the actual use environment.
Drawings
FIG. 1 is a flow chart of the stranger gesture recognition system of the present invention.
Fig. 2(a) is a classification result diagram in the line-of-sight path according to the present invention.
Fig. 2(b) is a classification result diagram in the non-line-of-sight path according to the present invention.
FIG. 3 is a workflow diagram of the stranger gesture recognition method of the present invention.
Detailed Description
The invention is described in detail below with reference to the attached drawing figures:
the gesture recognition system is an indispensable ring in the field of artificial intelligence, and aims to achieve the purpose of recognizing different people through the difference of the same gesture made by each person, and finally achieve the purpose of guaranteeing the safety of the gesture recognition system. The traditional stranger identification system based on the channel state information can not distinguish strangers from non-strangers from the same gestures of different persons by defining different gestures for different persons or increasing the difference between different testers through large-amplitude movement of individuals.
The invention aims to provide a method for recognizing gestures of strangers from slight differences of the same gesture actions of different people by using a method based on channel state information in a commercial wireless network environment, and an evaluation device designed according to the method on the basis of the method. The invention also aims to ensure that the safety of intelligent household users is guaranteed by recognizing the gesture actions of strangers.
The invention relates to a gesture recognition system for strangers based on channel state information in a wireless network; the gesture recognition system comprises an original data acquisition and preprocessing module, an effective data denoising module, a gesture abnormal data extraction module and a characteristic value extraction and classifier classification module;
the acquisition module of the raw data is mainly completed by a CSITools tool developed by Washington university, and the tool can form an m x n matrix according to the number of transmitting antennas m and receiving antennas n for representing the collected raw data, wherein the raw data comprises amplitude and phase information. Because the collected raw data cannot detect and synchronize in real time to correct error data existing in the wireless device and the commercial wireless network card, the collected raw phase data needs to be linearly transformed by a raw data preprocessing module to eliminate the originally significant noise in the signal, so as to obtain effective phase information. Storing the information in a temporary data file in matlab software by using a corresponding data structure to prepare for the next denoising work of the original data;
the effective data denoising module is mainly used for processing the effective phase data extracted in the previous step, removing noise mixed in the effective phase data as much as possible, better keeping the characteristics of the emitters of different gestures, which are obviously different from others, and preparing for extracting the abnormal gesture data in the next step;
the gesture abnormal data extraction module is mainly used for separating gesture action data mixed in the data after denoising processing by using an improved sliding quartile moment method and preparing for the next extraction work of characteristic values;
the characteristic value extraction and classifier classification module comprises a characteristic value extraction module and a classifier classification module, and the characteristic value extraction module is used for extracting one or more characteristic values of different people making the same gesture motion in a time domain, a frequency domain or a time-frequency domain from the gesture motion data module obtained in the last step; the classifier classification module is used for selecting a classifier capable of distinguishing characteristic value data of different people and classifying the extracted data of all people through trained training set characteristic values by using the classifier.
Step 1, firstly, a tool which is released by washington university and runs on a commercial 802.11n network card is used, the tool runs under a Linux operating system with 3 antennas on an Intel5300 wireless network card, and wireless channel state information based on 802.11 standard is collected.
step 4, selecting data with good collection effect from the 3 gain antennas to perform Gaussian filtering denoising processing on the phase data after linear transformation;
step 5, extracting an abnormal value from the data of a certain subcarrier after the denoising operation by using an improved sliding quarter-bit distance method, and setting the size of a sliding window to 240 in the experiment;
step 6, calculating the value of the maximum peak in each group of abnormal data by using the self-contained max and findpeaks functions in matlab for the extracted abnormal value data, calculating the value of the small wave variance in each group of abnormal data by using a wavevarlet.m file written by the user, and taking the small wave variance as a characteristic value in a time domain;
step 7, respectively putting the data of each human gesture action in the characteristic value data matrix as a training set into a random forest classifier for training, and ensuring that no intersection exists among the characteristic values of different gestures in the training set;
step 8, extracting characteristic values in the residual data according to the method in the step 6 to form a characteristic value data matrix of the test set;
and 9, substituting the characteristic matrixes of the test set and the training set into a random forest classifier for classification, and displaying the experimental result through a data line graph of the identification accuracy of strangers.
And step 10, outputting an evaluation report at an output module and displaying the running states of various safety indexes in a dynamic graph mode. The calculation flow of the sliding quadrant distance abnormal value extraction algorithm based on the improved algorithm is as follows:
step 1, setting the size of a sliding window to be N;
step 4, summing the numerical value of each segment obtained in the previous step with the data of the 3/4 th position point of the segment, thereby obtaining an upper bound curve of the sliding quarter-bit distance in the segment;
step 5, selecting a test coefficient with a value less than 1, and multiplying the test coefficient with data in the upper bound curve to obtain an improved upper bound curve;
step 6 regards the points beyond the improved upper bound curve as outlier points and extracts them all.
Claims (1)
1. A stranger gesture recognition method based on channel state information is characterized by comprising the following steps:
(1) firstly, a tool which is released by Washington university and runs on a commercial 802.11n network card is used, the tool runs under a Linux operating system which is provided with 3 antennas on an Intel5300 wireless network card, and wireless channel state information based on 802.11 standard is collected;
(2) extracting corresponding 90 pieces of subcarrier information from the collected information after preprocessing operation, and extracting phase information from the information;
(3) performing linear transformation on the phase data in the extracted subcarriers, and separating effective phase data from the phase data;
(4) performing Gaussian filtering denoising processing on the phase data subjected to linear transformation;
(5) extracting an abnormal value from the data of a certain subcarrier after the denoising operation by using an improved sliding quartile range method;
(6) calculating the value of the maximum peak in each group of abnormal data for the extracted abnormal value data, calculating the value of the small wave variance in each group of abnormal data, and taking the small wave variance and the small wave variance as characteristic values on a time domain;
(7) extracting characteristic values in the residual data according to the method in the step (6) to form a characteristic value data matrix of the test set;
(8) respectively putting data of each gesture action in a characteristic value data matrix as a training set into a random forest classifier for training, and ensuring that no intersection exists among characteristic values of different gestures in the training set;
(9) substituting the characteristic matrixes of the test set and the training set into a random forest classifier for classification, and displaying the experimental result through a data line graph of stranger identification accuracy;
the step (5) above, wherein the calculation flow of the sliding quartering distance outlier extraction algorithm based on the improved algorithm is as follows:
(5.1) setting the size of the sliding window to be N;
(5.2) quartering the signal data after being arranged from small to large, and extracting the value of the 3/4 th position;
(5.3) respectively calculating the average value of each section in four equally divided sections of data, comparing the average value with the median of the section of data, and selecting the larger one of the average value and the median as a value to be used next;
(5.4) summing the value of each segment obtained in the previous step with the data of the 3/4 th position point of the segment, thereby obtaining an upper bound curve of the sliding quartile distance in the segment;
(5.5) selecting a check coefficient with a value less than 1, and multiplying the check coefficient with data in the upper-bound curve to obtain an improved upper-bound curve;
(5.6) regarding the points exceeding the improved upper bound curve as outlier points and extracting all of them;
the method comprises the following steps: the system comprises an original data acquisition and preprocessing module, an effective data denoising module, a gesture abnormal data extraction module and a characteristic value extraction and classifier classification module;
the acquisition module of the original data is completed by a CSITools tool developed by Washington university, an m multiplied by n matrix is formed according to the number of transmitting antennas m and receiving antennas n, and the matrix represents the collected original data, wherein the original data comprises amplitude and phase information; the collected original phase data is subjected to linear transformation through a preprocessing module of the original data to eliminate the originally obvious noise in the signal and obtain effective phase information; storing the information in a temporary data file in matlab software in a corresponding data structure;
the effective data denoising module is used for processing the effective phase data extracted in the last step, removing noise mixed in the effective phase data, and simultaneously keeping characteristics which are different from others and are possessed by emitters of different gestures;
the gesture abnormal data extraction module is mainly used for separating gesture motion data mixed in the data after denoising processing by using an improved sliding quartile moment method;
the characteristic value extraction and classifier classification module comprises a characteristic value extraction module and a classifier classification module, wherein the characteristic value extraction module extracts one or more characteristic values of different people making the same gesture motion in a time domain, a frequency domain or a time-frequency domain from the gesture motion data module obtained in the last step; the classifier classification module selects a classifier which can distinguish characteristic value data of different people, and classifies the extracted data of all people through trained characteristic values of a training set by using the classifier;
the step (1), the step (2) and the step (3) are realized by the raw data acquisition and preprocessing module, the step (4) is realized by the effective data denoising module, the step (5) is realized by the gesture abnormity extraction module, the steps (6) to (9) are realized by the characteristic value extraction and classifier classification module, the step (6) is realized by the characteristic value extraction module, and the steps (7) to (9) are realized by the classifier classification module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810771509.4A CN109325399B (en) | 2018-07-13 | 2018-07-13 | Stranger gesture recognition method and system based on channel state information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810771509.4A CN109325399B (en) | 2018-07-13 | 2018-07-13 | Stranger gesture recognition method and system based on channel state information |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109325399A CN109325399A (en) | 2019-02-12 |
CN109325399B true CN109325399B (en) | 2021-11-19 |
Family
ID=65263929
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810771509.4A Active CN109325399B (en) | 2018-07-13 | 2018-07-13 | Stranger gesture recognition method and system based on channel state information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109325399B (en) |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110062379B (en) * | 2019-04-15 | 2022-10-28 | 哈尔滨工程大学 | Identity authentication method based on channel state information under human behavior scene |
CN110059612B (en) * | 2019-04-15 | 2022-11-18 | 哈尔滨工程大学 | Position-independent gesture recognition method and system based on channel state information |
CN110502105B (en) * | 2019-07-08 | 2020-12-11 | 南京航空航天大学 | Gesture recognition system and method based on CSI phase difference |
CN110414468B (en) * | 2019-08-05 | 2022-10-21 | 合肥工业大学 | Identity verification method based on gesture signal in WiFi environment |
CN112861893B (en) * | 2019-11-27 | 2023-03-24 | 四川大学 | Stranger identification algorithm based on CSI amplitude-subcarrier probability distribution |
CN111626174B (en) * | 2020-05-22 | 2023-03-24 | 哈尔滨工程大学 | Attitude robust motion recognition method based on channel state information |
CN112163540B (en) * | 2020-10-09 | 2024-01-19 | 上海第二工业大学 | Gesture recognition method based on WiFi |
CN113359816B (en) * | 2021-05-21 | 2022-07-15 | 中国人民解放军陆军工程大学 | Unmanned aerial vehicle control method and system based on wireless gesture recognition |
CN113609976B (en) * | 2021-08-04 | 2023-07-21 | 燕山大学 | Direction-sensitive multi-gesture recognition system and method based on WiFi equipment |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102289558A (en) * | 2011-05-23 | 2011-12-21 | 公安部第一研究所 | Baseline adjusting method based on random signal processing |
CN202261388U (en) * | 2011-04-22 | 2012-05-30 | 喜讯无限(北京)科技有限责任公司 | Remote gesture recognition and transmission realization system for touch panel mobile device with communication module |
CN103529976A (en) * | 2012-07-02 | 2014-01-22 | 英特尔公司 | Interference elimination in gesture recognition system |
CN105046265A (en) * | 2015-03-03 | 2015-11-11 | 沈阳工业大学 | Iris image intestinal loop area detection method based on texture difference |
CN106599864A (en) * | 2016-12-21 | 2017-04-26 | 中国科学院光电技术研究所 | Deep face recognition method based on extreme value theory |
KR101731031B1 (en) * | 2016-02-12 | 2017-04-27 | 주식회사 엠씨넥스 | Car smart key for prohibitting use by a stranger |
CN107272903A (en) * | 2017-06-26 | 2017-10-20 | 王田 | Social intercourse system based on image processing algorithm |
CN107356979A (en) * | 2017-05-27 | 2017-11-17 | 淮海工学院 | A kind of method of ionized layer TEC exception detection |
-
2018
- 2018-07-13 CN CN201810771509.4A patent/CN109325399B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202261388U (en) * | 2011-04-22 | 2012-05-30 | 喜讯无限(北京)科技有限责任公司 | Remote gesture recognition and transmission realization system for touch panel mobile device with communication module |
CN102289558A (en) * | 2011-05-23 | 2011-12-21 | 公安部第一研究所 | Baseline adjusting method based on random signal processing |
CN103529976A (en) * | 2012-07-02 | 2014-01-22 | 英特尔公司 | Interference elimination in gesture recognition system |
CN105046265A (en) * | 2015-03-03 | 2015-11-11 | 沈阳工业大学 | Iris image intestinal loop area detection method based on texture difference |
KR101731031B1 (en) * | 2016-02-12 | 2017-04-27 | 주식회사 엠씨넥스 | Car smart key for prohibitting use by a stranger |
CN106599864A (en) * | 2016-12-21 | 2017-04-26 | 中国科学院光电技术研究所 | Deep face recognition method based on extreme value theory |
CN107356979A (en) * | 2017-05-27 | 2017-11-17 | 淮海工学院 | A kind of method of ionized layer TEC exception detection |
CN107272903A (en) * | 2017-06-26 | 2017-10-20 | 王田 | Social intercourse system based on image processing algorithm |
Non-Patent Citations (2)
Title |
---|
Device-Free Passive Identity Identification via WiFi Signals;Jiguang Lv等;《sensor》;20171102;第1-17页 * |
Jiguang Lv等.Device-Free Passive Identity Identification via WiFi Signals.《sensor》.2017,第1-17页. * |
Also Published As
Publication number | Publication date |
---|---|
CN109325399A (en) | 2019-02-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109325399B (en) | Stranger gesture recognition method and system based on channel state information | |
CN110059612B (en) | Position-independent gesture recognition method and system based on channel state information | |
CN112312457B (en) | Communication radiation source individual identification method based on complex depth residual error network | |
CN110502105B (en) | Gesture recognition system and method based on CSI phase difference | |
CN107968689A (en) | Perception recognition methods and device based on wireless communication signals | |
CN106650605A (en) | Morse signal automatic detection decoding method based on machine learning | |
CN104135327A (en) | Spectrum sensing method based on support vector machine | |
CN103093133B (en) | Biological identity authentication method facing institute of electrical and electronic engineers (IEEE) 802.15.6 | |
CN110730473B (en) | WiFi activity recognition-oriented signal feature extraction method | |
CN110287863A (en) | A kind of gesture identification method based on WiFi signal | |
CN110062379B (en) | Identity authentication method based on channel state information under human behavior scene | |
Shi et al. | Deep learning networks for human activity recognition with CSI correlation feature extraction | |
CN111652132B (en) | Non-line-of-sight identity recognition method and device based on deep learning and storage medium | |
Tamura et al. | Wireless devices identification with light-weight convolutional neural network operating on quadrant IQ transition image | |
CN111142668A (en) | Interaction method for positioning and activity gesture joint identification based on Wi-Fi fingerprint | |
CN108345873A (en) | A kind of multiple degrees of freedom body motion information analytic method based on multilayer convolutional neural networks | |
CN112272066A (en) | Frequency spectrum data cleaning method used in airport terminal area very high frequency communication | |
CN106707789A (en) | Smart home control system based on fingerprint recognition | |
CN110621038A (en) | Method and device for realizing multi-user identity recognition based on WiFi signal detection gait | |
Ahmed et al. | Wi-fi csi based human sign language recognition using lstm network | |
CN112883355B (en) | Non-contact user identity authentication method based on RFID and convolutional neural network | |
CN109117939A (en) | Neural network and the method for affixing one's name to neural network in mobile awareness upper side | |
Ding et al. | A new method of dynamic gesture recognition using Wi-Fi signals based on Adaboost | |
CN109710062B (en) | Cross-individual control method based on electroencephalogram and gesture signal fusion | |
CN101901337B (en) | Personal identification method based on dynamic characteristics |
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 |