CN115499912A - Sight distance identification method based on Wi-Fi channel state information - Google Patents
Sight distance identification method based on Wi-Fi channel state information Download PDFInfo
- Publication number
- CN115499912A CN115499912A CN202211139741.9A CN202211139741A CN115499912A CN 115499912 A CN115499912 A CN 115499912A CN 202211139741 A CN202211139741 A CN 202211139741A CN 115499912 A CN115499912 A CN 115499912A
- Authority
- CN
- China
- Prior art keywords
- sight
- csi
- line
- data
- phase
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 239000002245 particle Substances 0.000 claims abstract description 56
- 238000005070 sampling Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 20
- 238000005457 optimization Methods 0.000 claims abstract description 13
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 12
- 238000001514 detection method Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000012706 support-vector machine Methods 0.000 claims description 18
- 238000012360 testing method Methods 0.000 claims description 16
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000009826 distribution Methods 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 10
- 238000005259 measurement Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 238000002474 experimental method Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 230000002776 aggregation Effects 0.000 claims description 3
- 238000004220 aggregation Methods 0.000 claims description 3
- 239000000969 carrier Substances 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000012986 modification Methods 0.000 claims description 3
- 230000004048 modification Effects 0.000 claims description 3
- 230000010363 phase shift Effects 0.000 claims description 2
- 238000012795 verification Methods 0.000 claims description 2
- 238000003860 storage Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 9
- 230000000007 visual effect Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 208000011597 CGF1 Diseases 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005562 fading Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000004039 social cognition Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
- H04W64/006—Locating users or terminals or network equipment for network management purposes, e.g. mobility management with additional information processing, e.g. for direction or speed determination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
- H04W84/10—Small scale networks; Flat hierarchical networks
- H04W84/12—WLAN [Wireless Local Area Networks]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Monitoring And Testing Of Transmission In General (AREA)
Abstract
The invention discloses a line-of-sight identification method based on Wi-Fi channel state information, which comprises the following steps: step 1, building a Wi-Fi detection environment of a single transmitter-single receiver, and acquiring Channel State Information (CSI) signals at different sampling points under the condition of line-of-sight and non-line-of-sight; step 2, preprocessing the data of the signals acquired in the step 1; step 3, extracting characteristics such as mean value, standard deviation, variation coefficient, skewness, kurtosis, phase difference factor and Rician-K factor of the signal preprocessed in the step 2, formulating category labels under the condition of line-of-sight and non-line-of-sight, and constructing a data set; step 4, carrying out minimum-maximum normalized processing on the data set obtained in the step 3; and 5, providing an SVM classifier based on a particle swarm optimization algorithm to perform sight distance recognition, and taking the training set data obtained in the step 4 as the input of the model in the step 5, so that the indoor sight distance and non-sight distance states can be accurately recognized. The method is low in cost, easy to deploy and high in identification accuracy.
Description
Technical Field
The invention belongs to the technical field of perception by using common wireless equipment, and relates to a line-of-sight identification method based on Wi-Fi channel state information.
Background
With the rapid rise of the internet of things technology, wireless basic equipment is widely deployed, human life tends to be intelligent, and the wireless sensing technology gradually gets the attention of most researchers. The Wi-Fi environment perception realizes corresponding personalized services such as human body detection, activity recognition, sight distance recognition and the like by perceiving environment changes. The wireless positioning distance measurement precision is low due to the fact that various obstacles which cannot be avoided exist in the complex indoor environment, and the main reason is non-line-of-sight distance measurement error, so that the recognition of the channel line-of-sight and non-line-of-sight scene states is important for the indoor positioning precision.
Line of sight (LOS) refers to a straight Line between a transmitting end and a receiving end without blocking signals, so that the communication signal quality is better; non line of sight (NLOS) means that a signal receiving and transmitting end is shielded by buildings, plants and the like, a wireless signal can only reach a receiving end in a reflection, scattering and diffraction mode and is received by the receiving end through various propagation paths, the multipath effect is more obvious, and the problems of asynchronous attenuation delay and the like of the signal are caused. Daniele Puccinelli et al performed non-line-of-sight identification based on RSSI, but there was a multipath effect resulting in a decrease in accuracy; the Channel State Information, is used as a Wi-Fi physical layer signal, is composed of amplitude and phase of subcarriers, can obtain amplitude-frequency response of a plurality of subcarriers with finer granularity than RSSI, and can inhibit obvious fading brought by CSI obtained by different subcarriers by a multi-input multi-output technology, such as IEEE 802.11n, 3GPP LTE and mobile WiMAX systems, and improve data throughput and transmission distance without increasing bandwidth and transmission power so as to improve communication quality. Xian-Song L and Krairiksh M propose a Rician-K factor method based on the first arrival path, the Rician-K factor is the ratio of LOS and NLOS component powers; liFi provides envelope distribution characteristics, namely Rician-K factors and skewness, by utilizing the characteristic that signals are Rician in an LOS environment based on a channel statistical characteristic method, and classifies the signals through binary hypothesis testing, but the amplitude characteristics are easily influenced by noise and have poor robustness. PhaseU proposes a phase-based feature, which obtains stable phase information by calculating the phase difference between two antennas as a feature value because the original phase information is randomly distributed; phaseU can well recognize non-line-of-sight signals, but has a higher recognition rate in a dynamic environment and is not suitable for a static environment. However, the methods all have several common problems, firstly, the acquired original CSI data are not preprocessed, and since the CSI data are influenced by external noise and an acquisition tool thereof in the acquisition process, the amplitude of the CSI data is abnormal and the phase of the CSI data is shifted, the identification result is influenced; and secondly, a threshold value is calculated by researching one to two statistical characteristics, and then classification is carried out through binary hypothesis testing, so that the classification effect is poor.
The invention aims to perform fine-grained sight distance identification, and the method has higher identification accuracy and environmental applicability compared with the traditional method.
Disclosure of Invention
The invention provides a line-of-sight identification method based on Wi-Fi channel state information, which is characterized by comprising the following steps of:
step 2, carrying out data preprocessing on the CSI signals acquired in the step 1;
step 3, extracting characteristic clusters such as standard deviation, variation coefficient, skewness, kurtosis, phase difference factor, rician-K factor and the like from the CSI signals preprocessed in the step 2, extracting by a proper method, setting corresponding class labels of line-of-sight and non-line-of-sight conditions as 0 and 1 respectively, and constructing a data set;
step 4, carrying out minimum-maximum standardization processing on the training set and the test set obtained in the step 3 to obtain a standardized data set;
and 5, taking the training set data obtained in the step 4 as the input of the model in the step 5, performing line-of-sight identification by using an SVM (support vector machine) classifier based on a particle swarm optimization algorithm, training a sampling point training set, and verifying by using a test set, so that the indoor line-of-sight and non-line-of-sight states can be accurately identified.
Further, in step 1, the CSI original signal is obtained specifically according to the following steps:
step 1.1, an experimental platform consists of two aspects of hardware architecture and software configuration; the hardware architecture comprises: (1) Installing a Linux system on the desktop, modifying the network card into an Intel 5300, and adding three antennas to complete desktop modification; (2) The model of a commercial standard 2.4GHz Wi-Fi b/g/n router is TL-WDR4900; software configuration utilizes a Linux 802.11n CSI-Tool, modifies bottom firmware, combines with open source drive, and records CSI data packet information based on IEEE 802.11n in detail;
furthermore, in the experiment, the modified desktop and the router belong to the same local area network, the router is used as a transmitting end, the modified desktop is used as a receiving end, and the packet sending frequency of the router is set to be 100Hz, so that nearly 6000 data packets can be received in one minute;
step 1.2, designing and arranging an experimental scene, and collecting CSI channel state information of sampling points under the condition of line-of-sight and non-line-of-sight;
further, in step 2, the amplitude information and the phase information after the preprocessing are obtained specifically according to the following steps:
step 2.1, reading the CSI signals by using the read _ bf _ file function based on a Matlab software platform by using the CSI original signals of the line-of-sight and non-line-of-sight scenes obtained in the step 1, wherein the CSI data is a two-dimensional matrix of N rows, and N is the number of data packets;
wherein the frequency response of the channel can be represented by the following formula:
wherein, H (f) i ) Representing a phase; h (f) i ) Is a center frequency of f i Channel state information of the subcarriers of (a); n is a radical of s The number of the subcarriers of a single antenna is 30 on the Intel 5300 wireless network card. Suppose the number of antennas at the transmitting end is N tx The number of antennas at the receiving end is N rx Then the CSI data may be expressed as:
H ij CSI data for the ith antenna of a transmit antenna (TX) to the jth antenna of a receive antenna (RX), each antenna pair data comprising N s Sub-carriers, then H ij It can be specifically expressed as:
each signal sample containing N tx ×N rx ×N s The CSI data of each subcarrier, the received signal contains 9 data streams, and the data contained in each data packet can be interpreted as follows:
H 1 ＝{H 1，1 ，H 1，2 ，H 1，3 ，……，H 1，29 ，H 1，30 }
H 2 ＝{H 2，1 ，H 2，2 ，H 2，3 ，……，H 2，29 ，H 2，30 }
H 3 ＝{H 3，1 ，H 3，2 ，H 3，3 ，……，H 3，29 ，H 3，30 }
H 4 ＝{H 4，l ，H 4，2 ，H 4，3 ，……，H 4，29 ，H 4，30 }
H 5 ＝{H 5，1 ，H 5，2 ，H 5，3 ，……，H 5，29 ，H 5，30 }
H 6 ＝{H 6，1 ，H 6，2 ，H 6，3 ，……，H 6，29 ，H 6，30 }
H 7 ＝{H 7，1 ，H 7，2 ，H 7，3 ，……，H 7，29 ，H 7，30 }
H 8 ＝{H 8，1 ，H 8，2 ，H 8，3 ，……，H 8，29 ，H 8，30 }
H 9 ＝{H 9，1 ，H 9，2 ，H 9，3 ，……，H 9，29 ，H 9，30 }
step 2.2, solving corresponding amplitude and phase of the CSI data collected in the step 2.1; the collected CSI data is in a matrix form, in each CSI matrix, each subcarrier of each CSI matrix is represented in a complex form, and can be represented as a + bi (wherein a is a real part, b is an imaginary part, and i is an imaginary unit); the amplitude Z and the phase theta of the CSI can be obtained by a complex calculation formula:
amplitude and phase information of each subcarrier on each link can be obtained through a complex matrix of the CSI, so that the extraction of features can be carried out;
step 2.3, abnormal point detection and removal are carried out on the amplitude of the original CSI signal obtained in the step 2.2;
step 2.4, removing the CSI signals of the abnormal amplitude points in the step 2.3, and filtering noise in the original CSI observation value by using a discrete wavelet transform method;
step 2.5, carrying out phase deviation correction on the original phase of the CSI signal obtained in the step 2.2; in actual data sampling, the phase information θ actually obtained due to clock synchronization error and carrier frequency offset between signal transceivers k Can be expressed as:
θ k ＝∠H(f k )+2πw k Δt+2πΔwt+δ k
wherein, angle H (f) k ) Is the true CSI phase information, 2 π w k Δ t and 2 π Δ wt represent random phase shifts, δ, caused by clock synchronization errors and carrier frequency shifts, respectively k Representing measurement noise; in order to reduce random noise in the original phase, a method of performing phase calibration by linear transformation is adopted, and the phase after calibration is as follows:
θ′ k ＝θ k -αw k -β
wherein α and β are phases θ, respectively k The slope and offset which change with all subcarriers can obtain phase distribution with better aggregation after linear transformation.
Further, in step 3, the feature vector is obtained and a corresponding category label is formulated specifically according to the following steps, and a data set is constructed:
step 3.1, extracting features of the amplitude data and the phase processed respectively in the steps 2.4 and 2.5 by a proper method, such as standard deviation, skewness, kurtosis, phase difference factors, rician-K factors and other feature clusters, setting corresponding class labels of line-of-sight and non-line-of-sight conditions as 0 and 1 respectively, and constructing a data set;
in the feature extraction process, the features of an amplitude type are extracted from amplitude samples [ A1, A2, \8230;, A30] of a group of CSI, and the features of a phase type are extracted from phase samples of three groups of CSI;
featrure＝[σ,S,K,ρ,K r ]
wherein σ is standard deviation, S is skewness, K is kurtosis, ρ is phase difference factor, and K is r Constructing a feature vector for the Rician-K factor;
skewness S is a general metric that describes the direction and extent of skew of a data distribution, and skewness is used to quantify skew characteristics, and the formula is as follows:
kurtosis is a statistic of steepness in the distribution of recorded data, and mathematically, kurtosis is defined as:
where x, μ, σ denote our measurements, mean and standard deviation, respectively;
the formula for calculating the phase difference rho between the two antennas is as follows:
n represents the total number of measured CSI subcarriers, σ 2 For any one of all variances, | H (f) i ) I represents sigma 2 The average amplitude i, j and n of the corresponding double antennas on the ith subcarrier is a positive integer;
the Rician-K factor is the ratio of line-of-sight and non-line-of-sight propagation power, and is formulated as follows:
wherein v is i Representing the amplitude peak, σ, of the ith subcarrier i The standard deviation of the amplitude of the ith subcarrier is shown.
Further, in the step 4, the normalized data set is obtained specifically according to the following steps:
step 4.1, respectively carrying out minimum-maximum normalization on the 5 characteristic values preprocessed in the step 3, and mapping the data values between [0,1 ]; the specific formula is as follows:
the CSI denoised eigenvalue signal x is normalized into an x' formula through the maximum and minimum: wherein, a represents a certain characteristic value of the current subcarrier, and minA and maxA are respectively the minimum value and the maximum value of the characteristic value of the current subcarrier.
Furthermore, an SVM classifier based on a particle swarm optimization algorithm is provided in the step 5 for sight distance identification, the training set data obtained in the step 4 are used as the input of the model in the step 5, the SVM classifier based on the particle swarm optimization algorithm is used for sight distance identification, a sampling point training set is trained, and verification is carried out by using a test set, so that indoor sight distance and non-sight distance states can be accurately identified.
The invention aims at solving the problems that the prior art does not preprocess original signals, focuses on a plurality of characteristic values, calculates threshold values, classifies through binary hypothesis test, has poor classification effect and the like, and has the innovation points that statistical characteristics are combined with machine learning, statistical characteristics are constructed in a proper mode by utilizing receivable subcarrier amplitude and phase information, and an SVM classifier based on a particle swarm optimization algorithm is provided, so that the sight distance identification effect is more intelligently obtained. The method provided by the invention has the advantages of low computational complexity, better performance than the traditional method, low cost and easy deployment, thereby having strong expansibility.
Drawings
Fig. 1 is a flowchart of a method for identifying a line-of-sight based on Wi-Fi channel state information according to the present invention.
Fig. 2 is a schematic view of a line-of-sight and non-line-of-sight scene in the line-of-sight identification method based on Wi-Fi channel state information according to the present invention.
Fig. 3 is a view of a visual range identification experiment scene in the visual range identification method based on Wi-Fi channel state information according to the present invention.
FIG. 4 is a schematic diagram of particle velocity direction update.
FIG. 5 is a flow chart of SVM classification model establishing particle swarm optimization algorithm.
FIG. 6 is a graph comparing the accuracy of the inventive method with that of the conventional method.
Fig. 7 is a schematic diagram of a computer-readable storage medium according to an embodiment of the present disclosure.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
Fig. 1 is an experimental overall framework diagram, and details the overall operation flow of the patent.
As shown in fig. 1, the present invention is a line-of-sight identification method based on Wi-Fi channel state information, which specifically includes the following steps:
the step 1 specifically comprises:
step 1.1, an experimental platform consists of two aspects of hardware architecture and software configuration; the hardware architecture comprises: (1) Installing a Linux system on the desktop, modifying the network card into an Intel 5300, and adding three antennas to complete desktop modification; (2) The model of a commercial standard 2.4GHz Wi-Fi b/g/n router is TL-WDR4900;
software configuration utilizes a Linux 802.11n CSI-Tool to perform detailed recording on CSI data packet information based on IEEE 802.11n by modifying bottom firmware and combining with open source drive; the tool comprises a specific driver iWLwifi, and the driver can acquire channel response information CFR from the OFDM system and decompose information for fine-grained processing;
in the experiment, the modified desktop and the router belong to the same local area network, the router is used as a transmitting end, the modified desktop is used as a receiving end, and the packet transmitting frequency of the router is set to be 100Hz, so that nearly 6000 data packets can be received in one minute; the purpose of doing so is to prevent the system from producing the unknown conflict problem with the work of other processes, can reduce the uncontrollable factor that may appear to the greatest extent, reduce interference and influence to the experimental result;
step 1.2, designing and arranging an experimental scene, and collecting CSI channel state information of a sampling point and a test point under the two conditions of line-of-sight and non-line-of-sight; the system comprises a sight distance scene transmitting end, a receiving end, a transmitting end, a receiving end and four test points, wherein no obstacle exists between the sight distance scene transmitting end and the receiving end, the transmitting end moves within a range of 6 meters away from the receiving end, five sampling points are arranged, and four test points respectively sample a 3-minute data packet; the sampling points and the test points of the non-line-of-sight scene and the line-of-sight scene are the same, and the only difference is that a bookcase is used as an obstacle to shield between the transmitting end and the receiving end.
And 2, performing data preprocessing on the CSI signals acquired in the step 1.
Detecting and deleting abnormal points of the amplitude signal, filtering amplitude noise in an original CSI observation value, and correcting phase deviation of an original phase;
due to the fact that the interference of abnormal points and random noise exists in the detection environment, the amplitude and the phase of the CSI original signals in the line-of-sight state and the non-line-of-sight state acquired in the step 1 are preprocessed on the basis of the Matlab software platform, the amplitude and the phase of the CSI signals are used for improving the accuracy of feature extraction and the accuracy of a classifier, and errors caused by the noise and the abnormal values are effectively reduced.
In the step 2, the amplitude and phase information after the preprocessing is obtained specifically according to the following steps:
the step 2 specifically comprises the following steps:
and 2.1, reading the CSI signals by using the read _ bf _ file function based on a Matlab software platform by using the CSI original signals of the line-of-sight and non-line-of-sight scenes obtained in the step 1, wherein the CSI data is a two-dimensional matrix of N rows, and N is the number of data packets.
Fig. 2 is a schematic view of a line-of-sight and non-line-of-sight scene in a line-of-sight identification method based on Wi-Fi channel state information according to the present invention.
A line-of-sight scene is shown in fig. 2 (a), and a non-line-of-sight scene is shown in fig. 2 (b); the sight distance refers to a straight line between the transmitting end and the receiving end without shielding of signals, and the communication signal quality is better; the non-line-of-sight signal transmitting and receiving end is shielded by buildings, plants and the like, wireless signals can only reach the receiving end in a reflection, scattering and diffraction mode and are received by the receiving end through various propagation paths, the multipath effect is more obvious, and the problems of asynchronous attenuation delay and the like of the signals are caused.
Fig. 3 is a view of an experimental scene of line-of-sight identification. The system comprises a sight distance scene transmitting end, a receiving end and nine sampling points, wherein no obstacle exists between the sight distance scene transmitting end and the receiving end, the transmitting end moves within a range of 6 meters away from the receiving end, the five sampling points are used for training, the four sampling points are used for testing, and each sampling point samples a 3-minute data packet; the sampling points of the non-line-of-sight scene and the line-of-sight scene are the same in position, and the only difference is that a bookcase is used as a barrier to shield between the transmitting end and the receiving end.
As shown in fig. 2, the transmitter has 3 transmit antennas, and the receiver has 3 receive antennas, so that the received signal includes 9 data streams, each data stream includes CSI data of 30 subcarriers, each signal sample includes 3 × 30=270 subcarrier CSI data, and thus the obtained CSI data is a two-dimensional matrix of N × 270;
wherein the frequency response of the channel can be represented by the following formula:
wherein, angle H (f) i ) Representing a phase; h (f) i ) Is centered at a frequency f i Channel state information of the subcarriers of (a); n is a radical of s The number of the subcarriers of a single antenna is 30 on the Intel 5300 wireless network card. Suppose that the number of antennas at the transmitting end is N tx The number of antennas at the receiving end is N rx Then, the CSI data may be expressed as:
H ij CSI data for the ith antenna of a transmit antenna (TX) to the jth antenna of a receive antenna (RX), each antenna pair data comprising N s Sub-carriers, then H ij It can be specifically expressed as:
each signal sample containing N tx ×N rx ×N s The CSI data of each subcarrier, the received signal contains 9 data streams, and the data contained in each data packet can be interpreted as follows:
H 1 ＝{H 1，1 ，H 1，2 ，H 1，3 ，……，H 1，29 ，H 1，30 }
H 2 ＝{H 2，1 ，H 2，2 ，H 2，3 ，……，H 2，29 ，H 2，30 }
H 3 ＝{H 3，1 ，H 3，2 ，H 3，3 ，……，H 3，29 ，H 3，30 }
H 4 ＝{H 4，1 ，H 4，2 ，H 4，3 ，……，H 4，29 ，H 4，30 }
H 5 ＝{H 5，1 ，H 5，2 ，H 5，3 ，……，H 5，29 ，H 5，30 }
H 6 ＝{H 6，l ，H 6，2 ，H 6，3 ，……，H 6，29 ，H 6，30 }
H 7 ＝{H 7，1 ，H 7，2 ，H 7，3 ，……，H 7，29 ，H 7，30 }
H 8 ＝{H 8，1 ，H 8，2 ，H 8，3 ，……，H 8，29 ，H 8，30 }
H 9 ＝{H 9，1 ，H 9，2 ，H 9，3 ，……，H 9，29 ，H 9，30 }
step 2.2, solving corresponding amplitude and phase of the CSI data acquired in the step 2.1; the collected CSI data is in a matrix form, and in each CSI moment, each subcarrier of each CSI matrix is represented in a complex form, which can be represented as a + bi; the amplitude Z and the phase theta of the CSI can be obtained by a complex calculation formula:
amplitude and phase information of each subcarrier on each link can be obtained through a complex matrix of the CSI, so that the extraction of features can be carried out;
step 2.3, abnormal point detection and removal are carried out on the amplitude of the original CSI signal obtained in the step 2.2;
after reading the CSI original signal, the amplitude signal is detected and outliers are removed by using a hanpell (Hampel) filter.
Step 2.4, removing the CSI signals of the abnormal amplitude points in the step 2.3, and filtering noise in the original CSI observation values by using a discrete wavelet transform method;
wherein, the discrete wavelet transform adopts db3 wavelet function to carry out 5-layer decomposition; after the signals are filtered, the graph curve becomes smoother, and frequent random fluctuation is removed through filtering;
step 2.5, carrying out phase deviation correction on the original phase of the CSI signal obtained in the step 2.2; in actual data sampling, the phase information θ actually obtained due to clock synchronization error and carrier frequency offset between signal transceivers k Can be expressed as:
θ k ＝∠H(f k )+2πw k Δt+2πΔwt+δ k
wherein, angle H (f) k ) Is the true CSI phase information, 2 π w k Δ t and 2π Δ wt represents the random phase offset, δ, caused by the clock synchronization error and the carrier frequency offset, respectively k Representing measurement noise; in order to reduce random noise in the original phase, a method of performing phase calibration by linear transformation is adopted, and the calibrated phase is as follows:
θ′ k ＝θ k -αw k -β
wherein α and β are phases θ, respectively k The slope and offset which change with all subcarriers can obtain phase distribution with better aggregation after linear transformation.
Step 3, extracting characteristic clusters such as standard deviation, variation coefficient, skewness, kurtosis, phase difference factor, rician-K factor and the like from the CSI signals preprocessed in the step 2, extracting by a proper method, setting corresponding class labels of line-of-sight and non-line-of-sight conditions as 0 and 1 respectively, and constructing a data set;
the step 3 specifically comprises the following steps:
step 3.1, extracting the amplitude and phase data processed in the step 2.4 by a proper method, clustering the characteristics such as standard deviation, skewness, kurtosis, phase difference factors, rician-K factors and the like, setting corresponding class labels of line-of-sight and non-line-of-sight conditions as 0 and 1 respectively, and constructing a data set;
in the feature extraction process, the features of an amplitude type are extracted from amplitude samples [ A1, A2, \8230;, A30] of a group of CSI, and the features of a phase type are extracted from phase samples of three groups of CSI;
featrure＝[σ,S,K,ρ,K r ]
wherein, sigma is standard deviation, S is skewness, K is kurtosis, rho is phase difference factor, K is phase difference factor r Constructing a feature vector for the Rician-K factor;
the standard deviation may show the degree of dispersion of 30 subcarriers in each CSI data, and in non-line-of-sight conditions, wi-Fi signals are affected by additional noise and multipath effects, which means a larger standard deviation in non-line-of-sight conditions;
skewness S is a general measure for describing the skewness direction and degree of data distribution, skewness is used for quantifying skewness characteristics, and when the skewness value is greater than 0, the data distribution is skewed to the right; if the skewness is smaller than 0, the data distribution is deviated to the left, and the calculation formula is as follows:
kurtosis is a statistic of steepness in the distribution of recorded data, and mathematically, kurtosis is defined as:
where x, μ, σ denote our measurements, mean and standard deviation, respectively;
the formula for calculating the phase difference rho between the two antennas is as follows:
n represents the total number of measured CSI subcarriers, σ 2 For any one of all variances, | H (f) i ) | represents σ 2 The average amplitude i, j and n of the corresponding double antennas on the ith subcarrier is a positive integer;
the Rician-K factor is the ratio of line-of-sight and non-line-of-sight power, and is given by the formula:
wherein v is i Denotes the amplitude peak, σ, of the ith subcarrier i The standard deviation of the amplitude of the ith subcarrier is shown.
And 4, carrying out minimum-maximum normalization processing on the characteristic values obtained in the step 3 to obtain a normalized data set.
The step 4 specifically comprises the following steps:
step 4.1, respectively carrying out minimum-maximum normalization on the 5 characteristic values preprocessed in the step 3, and mapping the data values between [0,1 ]; the specific formula is as follows:
the CSI denoised eigenvalue signal x is normalized into an x' formula through the maximum and minimum: wherein, a represents a certain characteristic value of the current subcarrier, and minA and maxA are respectively the minimum value and the maximum value of the characteristic value of the current subcarrier.
And 5, providing an SVM classifier based on the particle swarm optimization algorithm for visual range recognition, using the training set data obtained in the step 4 as the input of the model in the step 5, performing visual range recognition by using the SVM classifier based on the particle swarm optimization algorithm, training a sampling point training set, and verifying by using a test set, so that the indoor visual range and non-visual range states can be accurately recognized.
FIG. 5 is a flow chart of an SVM classification model for establishing a particle swarm optimization algorithm.
As shown in fig. 5, step 5 specifically includes:
step 5.1, randomly generating n particles with parameter sets (c, g) in a support vector machine; wherein c represents a penalty parameter, and g represents a parameter of a kernel function;
wherein the particles have two attributes, velocity and position respectively; the velocity represents the direction and distance that the particle moves when iterating next, and the position is a solution of the solved problem;
step 5.2, determining iterative areas of particle positioning based on the characteristics of c and g, and determining corresponding correction steps based on the respective characteristics of the iterative areas;
step 5.3, inputting the positioning of the particles into a Support Vector Machine (SVM) model to solve the fitness of the particles; the value is used for evaluating the quality degree of the particle position, determining whether to update the historical optimal position of the particle individual and the historical optimal position of the group, and ensuring that the particle is searched towards the direction of the optimal solution;
step 5.4, taking a proper numerical value as a judgment criterion, storing the optimal particles into V, correcting U, and stopping searching for optimal parameters when the requirement is met; instead, the process then starts with step 5.3; wherein V represents the current optimal state of each particle, and U is the position of the optimal particle; continuously updating the particle speed and the particle position for the particles which do not meet the requirements;
the particle update rate formula is:
n is the particle swarm size; i-particle number, i =1,2, \ 8230;, n; d-particle dimension; d-particle dimension number, D =1,2.., D; k is the number of iterations; w-inertial weight; c. C 1 -an individual learning factor; c. C 2 -a population learning factor; r is 1 、r 2 The interval [0,1]Random number in the search table, and the randomness of the search is increased;
-the velocity vector of particle i in dimension d in the kth iteration;
-the position vector of particle i in dimension d in the kth iteration;
the historical optimal position of the particle i in the d-dimension in the k-th iteration, namely after the k-th iteration, searching the particle i (individual) for the optimal solution;
the historical optimal position of the population in the d-th dimension in the kth iteration, i.e. the optimal solution in the whole population of particles after the kth iteration;
the particle position update formula is:
step 5.5, optimizing to obtain an optimized set of SVM;
and 5.6, training the sampling point training set by taking the training set data obtained in the step 4 as the input of the SVM classifier optimized in the step 5.6, and verifying by using the test set, so that the indoor sight distance and non-sight distance states can be accurately recognized, the performance is superior to that of the traditional sight distance method, and a good recognition effect is achieved.
FIG. 4 is a schematic diagram of particle velocity direction update.
In the particle swarm optimization, each solution of an optimized problem is regarded as a bird and is called as a particle; all particles have a fitness value (how good the solution is) determined by an optimized function, each particle also has a speed (colloquially, a coefficient for adjusting the position) to determine the flying direction of the particles, then the particles follow the current optimal particles to search in a solution space, and the current particle motion speed direction consists of three parts:
the moving direction of the next iteration of the particles = the inertial direction + the individual optimal direction + the group optimal direction inertial direction means that the moving direction is composed of inertial weight and the self speed of the particles and represents the trust of the particles on the previous self motion state; the individual optimal direction refers to a self-learning part which is a part of the self experience of the particle, and can be understood as the distance and the direction between the current position of the particle and the historical optimal position of the particle; the population optimal direction refers to information sharing and cooperation among particles, namely social cognition, and can be understood as the distance and the direction between the current position of the particles and the population historical optimal position.
FIG. 6 is a graph comparing the accuracy of the inventive method with that of the conventional method. Among them, the method proposed in LiFi is the most widely used method with skewness and kurtosis as characteristic values; the method proposed in PhaseU is a method using a dual antenna phase difference variance as an eigenvalue; rician-K is a method of modeling this factor to perform non-line-of-sight identification; pso-svm is a line-of-sight identification method based on Wi-Fi channel state information, which is provided by the invention; all features are input into the classification result of the classifier, and the method is higher in accuracy than other methods.
The present invention also provides a computer-readable storage medium for storing non-transitory computer-readable instructions which, when executed by a computer, cause the computer to perform the above-described method.
Fig. 7 is a schematic diagram of a computer-readable storage medium according to an embodiment of the present disclosure. As shown in fig. 7, a computer-readable storage medium 40, having non-transitory computer-readable instructions 41 stored thereon, in accordance with an embodiment of the present disclosure. The non-transitory computer readable instructions 41, when executed by a processor, perform all or a portion of the steps of the aforementioned access control method for a removable storage device according to embodiments of the present disclosure.
It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.
Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of a unit does not in some cases constitute a limitation of the unit itself, for example, the first retrieving unit may also be described as a "unit for retrieving at least two internet protocol addresses".
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.
Claims (8)
1. A line-of-sight identification method based on Wi-Fi channel state information is characterized by comprising the following steps:
step 1, building a Wi-Fi detection environment of a single transmitter-single receiver, and acquiring channel state information of different sampling points under the two conditions of line-of-sight and non-line-of-sight;
step 2, carrying out data preprocessing on the CSI signals acquired in the step 1;
step 3, extracting characteristic clusters such as standard deviation, variation coefficient, skewness, kurtosis, phase difference factor, rician-K factor and the like from the CSI signals preprocessed in the step 2, extracting by a proper method, setting corresponding class labels of line-of-sight and non-line-of-sight conditions as 0 and 1 respectively, and constructing a data set;
step 4, carrying out minimum-maximum standardization processing on the training set and the test set obtained in the step 3 to obtain a standardized data set;
and 5, taking the training set data obtained in the step 4 as the input of the model in the step 5, performing line-of-sight identification by using an SVM (support vector machine) classifier based on a particle swarm optimization algorithm, training a sampling point training set, and verifying by using a test set, so that the indoor line-of-sight and non-line-of-sight states can be accurately identified.
2. The method of claim 1, wherein the Wi-Fi channel status information is used to detect the number of people in a room,
in the step 1, the CSI original amplitude signal is obtained specifically according to the following steps:
step 1.1, the experiment platform consists of two aspects of hardware architecture and software configuration; the hardware architecture comprises: (1) Installing a Linux system on the desktop, modifying the network card into an Intel 5300, and adding three antennas to complete desktop modification; (2) The model of a commercial standard 2.4GHz Wi-Fi b/g/n router is TL-WDR4900; software configuration utilizes a Linux 802.11n CSI-Tool to perform detailed recording on CSI data packet information based on IEEE 802.11n by modifying bottom firmware and combining with open source drive;
step 1.2, designing and arranging an experimental scene, and collecting CSI channel state information of different sampling points under the two conditions of line-of-sight and non-line-of-sight.
3. The Wi-Fi channel status information-based line-of-sight identification method of claim 2,
the modified desktop and the router belong to the same local area network, the router is used as a transmitting end, the modified desktop is used as a receiving end, and the packet sending frequency of the router is set to be 100Hz.
4. The method as claimed in claim 1, wherein in step 2, the collected CSI signals comprise amplitude and phase signals.
5. The method for identifying line-of-sight based on Wi-Fi channel state information according to claim 4, wherein the step 2 specifically includes the steps of:
step 2.1, reading the CSI signals by using read _ bf _ file functions based on a Matlab software platform by using the CSI original signals of the sight distance scene and the non-sight distance scene obtained in the step 1, and calculating corresponding amplitude and phase signals; the CSI data is a two-dimensional matrix with N rows, wherein N is the number of data packets;
wherein the frequency response of the channel can be represented by the following formula:
wherein, H (f) i ) Represents a phase; h (f) i ) Is a center frequency of f i Channel state information of the subcarriers of (a); n is a radical of s The number of the subcarriers of a single antenna is 30 on the Intel 5300 wireless network card;
N tx number of antennas at transmitting end, N rx H is CSI data, which is the number of antennas at the receiving end, and is specifically expressed as:
H ij CSI data for the ith antenna of a transmit antenna (TX) to the jth antenna of a receive antenna (RX), each antenna pair data comprising N s Sub-carriers then H ij Expressed as:
each signal sample containing N tx ×N rx ×N s The received signal contains 9 data streams, and the data contained in each data packet is explained as follows:
H 1 ＝{H 1,1 ,H 1,2 ,H 1,3 ,……,H 1,29 ,H 1,30 }
H 2 ＝{H 2,1 ,H 2,2 ,H 2,3 ,……,H 2,29 ,H 2,30 }
H 3 ＝{H 3,1 ,H 3,2 ,H 3,3 ,……,H 3,29 ,H 3,30 }
H 4 ＝{H 4,1 ,H 4,2 ,H 4,3 ,……,H 4,29 ,H 4,30 }
H 5 ＝{H 5,1 ,H 5,2 ,H 5,3 ,……,H 5,29 ,H 5,30 }
H 6 ＝{H 6,1 ,H 6,2 ,H 6,3 ,……,H 6,29 ,H 6,30 }
H 7 ＝{H 7,1 ,H 7,2 ,H 7,3 ,……,H 7,29 ,H 7,30 }
H 8 ＝{H 8,1 ,H 8,2 ,H 8,3 ,……,H 8,29 ,H 8,30 }
H 9 ＝{H 9,1 ,H 9,2 ,H 9,3 ,……,H 9,29 ,H 9,30 }
step 2.2, solving corresponding amplitude and phase of the CSI data collected in the step 2.1; the acquired CSI data is in a matrix form, in each CSI matrix, each subcarrier of each CSI matrix is represented in a complex form, the complex form can be represented as a + bi, and the amplitude Z and the phase theta of the CSI can be obtained by a complex calculation formula:
amplitude and phase information of each subcarrier on each link can be obtained through a complex matrix of CSI (channel state information), so that the extraction of characteristics can be carried out;
step 2.3, abnormal point detection and removal are carried out on the amplitude of the original CSI signal obtained in the step 2.2;
step 2.4, removing the CSI signals of the abnormal amplitude points in the step 2.3, and filtering noise in the original CSI observation values by using a discrete wavelet transform method;
step 2.5, carrying out phase deviation correction on the original phase of the CSI signal obtained in the step 2.4; in actual data sampling, the phase information θ actually obtained due to clock synchronization error and carrier frequency offset between signal transceivers k Can be expressed as:
θ k ＝∠H(f k )+2πw k Δt+2πΔwt+δ k
wherein, H (f) k ) Is the true CSI phase information, 2 π w k Δ t and 2 π Δ wt represent random phase shifts, δ, caused by clock synchronization errors and carrier frequency shifts, respectively k Representing measurement noise; in order to reduce random noise in the original phase, a method of performing phase calibration by linear transformation is adopted, and the phase after calibration is as follows:
θ′ k ＝θ k -αw k -β
wherein α and β are phases θ, respectively k The slope and offset which change with all subcarriers can obtain phase distribution with better aggregation after linear transformation.
6. The method for identifying a line-of-sight based on Wi-Fi channel state information according to claim 1, wherein in step 3, a data set is constructed by obtaining a feature vector and formulating a corresponding class label according to the following steps:
step 3.1, extracting features of the amplitude data and the phase processed respectively in the steps 2.4 and 2.5 by a proper method, such as standard deviation, skewness, kurtosis, a phase difference factor, a Rician-K factor and other feature clustering, formulating corresponding class labels of the line-of-sight and non-line-of-sight conditions as 0 and 1 respectively, and constructing a data set;
in the feature extraction process, the features of an amplitude type are extracted from amplitude samples [ A1, A2, \8230;, A30] of a group of CSI, and the features of a phase type are extracted from phase samples of three groups of CSI;
featrure＝[σ,S,K,ρ,K r ]
wherein σ is standard deviation, S is skewness, K is kurtosis, ρ is phase difference factor, and K is r Constructing a feature vector for the Rician-K factor;
skewness S is a general metric that describes the direction and extent of skew of a data distribution, and skewness is used to quantify skew characteristics, and the formula is as follows:
kurtosis is a statistic that records data steeply distributed, mathematically defined as:
where x, μ, σ denote our measurements, mean and standard deviation, respectively;
the formula for calculating the phase difference rho between the two antennas is as follows:
n represents the total number of measured CSI subcarriers, σ 2 For any one of all variances, | H (f) i ) | represents σ 2 The average amplitude i, j and n of the corresponding double antennas on the ith subcarrier is a positive integer;
the Rician-K factor is the ratio of line-of-sight and non-line-of-sight power, and is given by the formula:
wherein v is i Representing the amplitude peak, σ, of the ith subcarrier i The standard deviation of the amplitude of the ith subcarrier is shown.
7. The method for identifying a line-of-sight based on Wi-Fi channel state information according to claim 1, wherein the step 4 specifically includes the steps of:
step 4.1, respectively carrying out minimum-maximum normalization on the 5 characteristic values preprocessed in the step 3, and mapping the data values between [0,1], wherein a specific formula is as follows:
the CSI noise-reduced eigenvalue signal x is normalized into an x' formula through the maximum and minimum: wherein, a represents a certain characteristic value of the current subcarrier, and minA and maxA are respectively the minimum value and the maximum value of the characteristic value of the current subcarrier.
8. The method for identifying the line-of-sight based on the Wi-Fi channel state information according to claim 1, wherein an SVM classifier based on a particle swarm optimization algorithm is provided in the step 5 for identifying the line-of-sight, the training set data obtained in the step 4 is used as input of the model in the step 5, the SVM classifier based on the particle swarm optimization algorithm is used for identifying the line-of-sight, the training set of the sampling point is trained, and the test set is used for verification, so that the indoor line-of-sight and non-line-of-sight states can be accurately identified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211139741.9A CN115499912A (en) | 2022-09-19 | 2022-09-19 | Sight distance identification method based on Wi-Fi channel state information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211139741.9A CN115499912A (en) | 2022-09-19 | 2022-09-19 | Sight distance identification method based on Wi-Fi channel state information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115499912A true CN115499912A (en) | 2022-12-20 |
Family
ID=84471042
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211139741.9A Pending CN115499912A (en) | 2022-09-19 | 2022-09-19 | Sight distance identification method based on Wi-Fi channel state information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115499912A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| WO2018119949A1 (en) * | 2016-12-29 | 2018-07-05 | 深圳天珑无线科技有限公司 | Channel state information phase correction method and apparatus |
-
2022
- 2022-09-19 CN CN202211139741.9A patent/CN115499912A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| WO2018119949A1 (en) * | 2016-12-29 | 2018-07-05 | 深圳天珑无线科技有限公司 | Channel state information phase correction method and apparatus |
Non-Patent Citations (3)
| Title |
|---|
| JUNHUAI LI等: ""A Novel Device-Free Counting Method Based on Channel Status Information"", 《SENSORS》, 15 November 2018 (2018-11-15), pages 1 - 5 * |
| YUAN REN等: ""Determination of Optimal SVM Parameters by Using GA/PSO"", 《JOURNAL OF COMPUTERS》, 31 August 2010 (2010-08-31), pages 1160 - 1168 * |
| 贺宇轩: ""基于CSI的非视距识别方法研究"", 中国优秀硕士学位论文全文数据库信息科技辑, no. 3, 15 March 2020 (2020-03-15), pages 136 - 318 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hsieh et al. | Deep learning-based indoor localization using received signal strength and channel state information | |
| JP7154295B2 (en) | Motion detection based on machine learning of radio signal characteristics | |
| Zou et al. | Deepsense: Device-free human activity recognition via autoencoder long-term recurrent convolutional network | |
| CN109275095B (en) | Bluetooth-based indoor positioning system, positioning equipment and positioning method | |
| CN110475221B (en) | Personnel action identification and position estimation method based on channel state information | |
| CN115053147A (en) | Detecting a location of motion using wireless signals and a topology of wireless connections | |
| CN109490826B (en) | Ranging and position positioning method based on radio wave field intensity RSSI | |
| CN110049549B (en) | WiFi fingerprint-based multi-fusion indoor positioning method and system | |
| CN110072186B (en) | Weighted naive Bayes indoor positioning method based on independent attributes | |
| CN114359738B (en) | Cross-scene robust indoor people number wireless detection method and system | |
| CN112040400B (en) | Single-site indoor fingerprint positioning method based on MIMO-CSI, storage medium and equipment | |
| CN113453180B (en) | Intelligent detection method and system for human body tumble and information data processing terminal | |
| CN114584230B (en) | Predictive channel modeling method based on countermeasure network and long-term and short-term memory network | |
| CN111901028B (en) | Human body behavior identification method based on CSI (channel State information) on multiple antennas | |
| Fan et al. | Single-site indoor fingerprint localization based on MIMO-CSI | |
| CN108199757B (en) | A method of it is invaded using channel state information detection consumer level unmanned plane | |
| Song et al. | DuLoc: Dual-channel convolutional neural network based on channel state information for indoor localization | |
| CN114639169A (en) | Human body action recognition system based on attention mechanism feature fusion and position independence | |
| CN112954791B (en) | Channel State Information (CSI) positioning method based on subcarrier screening | |
| CN113191224A (en) | Unmanned aerial vehicle signal extraction and identification method and system | |
| CN116707675B (en) | Method and device for detecting radio signal and method and device for detecting abnormality of radio signal | |
| CN116047404B (en) | Arrival angle measurement method based on Pmatic spectrum peak diagram | |
| Wang et al. | A Framework for CSI-Based Indoor Localization with ID Convolutional Neural Networks | |
| Choi et al. | Simultaneous crowd estimation in counting and localization using WiFi CSI | |
| CN115002703A (en) | Passive indoor people number detection method based on Wi-Fi channel state information |
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 |