Channel state information reconstruction method and system for channel state interference detection
Through the feature embedding and diffusion model generation of channel state information, the problem of low accuracy of reconstruction of low-sampled WiFi channel state information is solved, and the reconstruction and interference detection of high-sampling rate channel state information is realized, and the accuracy of radio frequency interference detection is improved.
Patent Information
- Application Number
- CN202410875619.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-02
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-07-02
AI Technical Summary
The accuracy of reconstruction of low-sampled WiFi channel status information in the prior art is low, and the channel status information interference detection task characteristics are not fully considered, resulting in the inability to be directly used for radio frequency interference detection.
Channel state information is used to generate effective feature embeddings, channel state information data of missing positions is generated using diffusion model, high-sampling rate channel state information is formed by combining low-sampling rate channel state information data, and spectral correlation functions are calculated for interference detection.
The channel state information reconstruction effect and interference detection accuracy are improved, and the high data loss rate can be better handled, which enhances the integrity of WiFi channel state information and the accuracy of interference detection.
Smart Images

Figure CN118972008A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of WiFi interference detection and signal processing, and in particular relates to a channel state information reconstruction method and system for channel state interference detection. Background Art
[0002] With the rapid development of wireless communication technology, wireless networks have been widely deployed in cities. Among them, WiFi networks, as the most widely used wireless communication network in life, have brought great convenience to human life. However, the frequency band in which WiFi operates is very crowded and is susceptible to radio frequency interference from devices such as Bluetooth and ZigBee, which greatly reduces the stability of communication. On the other hand, with the development of synaesthesia integration technology, WiFi is widely used in non-invasive perception. However, the channel state information (Channel State Information) used for WiFi perception carries radio frequency interference information, which seriously affects the sensitivity and accuracy of perception applications. Therefore, detecting whether there is radio frequency interference in the channel state information data is of great significance to ensuring the communication, perception performance and interference elimination of WiFi.
[0003] Existing research has proposed solutions such as the channel state information interference detection algorithm based on spectral correlation function to identify RF interference in channel state information data. Although existing methods can detect interference well, problems such as WiFi data packet loss and hardware defects are prone to occur in real applications, resulting in discontinuous channel state information data and low sampling rate, which has a negative impact on interference detection.
[0004] A common method to solve this problem is to reconstruct the complete channel state information based on the low-sampled channel state information data, and use the complete channel state information for interference detection. The existing channel state information data reconstruction method is the traditional interpolation method, which uses the adjacent known data points to infer the unknown data points within the range based on mathematical principles such as linear interpolation. This method is simple in process, but has low accuracy in the case of high data loss rate. With the development of generative artificial intelligence technology, some studies have used generative adversarial networks (GAN) to reconstruct channel state information data in the form of image restoration, achieving high accuracy and fast speed. However, the above methods all focus on channel state information data recovery, ignoring the purpose of channel state information interference detection, and cannot be directly applied to the data reconstruction problem under the channel state information interference detection task.
[0005] Therefore, it is necessary to design a high-accuracy low-sampling WiFi channel state information reconstruction method for channel state information interference detection to solve the above problems. Summary of the invention
[0006] In order to solve the problem that the low-sampling WiFi channel state information reconstruction technology in the prior art has low accuracy and does not fully consider the characteristics of the channel state information interference detection task, resulting in the WiFi channel state information cannot be directly used for radio frequency interference detection, and to achieve the purpose of improving the channel state information reconstruction effect and interference detection accuracy, the present invention proposes a channel state information reconstruction method and system for channel state interference detection.
[0007] The technical solution of the method of the present invention is a channel state information reconstruction method for channel state interference detection, comprising the following steps:
[0008] Step 1: Generate effective feature embedding according to the collected channel state information, wherein the channel state information data is low sampling rate channel state information data collected by the WiFi signal receiving end;
[0009] Step 2: Generate channel state information data of the missing position using a diffusion model, wherein the channel state information data of the missing position and the low sampling rate channel state information data together constitute reconstructed high sampling rate channel state information data;
[0010] Step 3: Calculate a spectral correlation function according to the high sampling rate channel state information data, and perform interference detection;
[0011] Preferably, the channel state information collected in step 1 is specifically as follows:
[0012] For a WiFi channel with M transmitting antennas, N receiving antennas and F subcarriers, the channel state information data at T moments are collected to form the low sampling rate channel state information. Then, the low sampling rate channel state information of each transmitting and receiving antenna pair can be regarded as a three-dimensional matrix with a shape of F×T×2, which is composed of two two-dimensional matrices with a shape of F×T, respectively including the real part data and the imaginary part data of the low sampling rate channel state information of the transmitting and receiving antenna pair;
[0013] Initial channel state information
[0014] Where, C = 2 × M × N;
[0015] Among them, the channel state information value at the time when the sampled data is missing is 0, m∈{0,1} F×T×C is the channel state information data mask, the value of m is 0 when data is missing, otherwise it is 1;
[0016] Preferably, the effective feature embedding is generated in step 1 as follows:
[0017] The time series feature extraction unit uses the self-attention block to extract the time series feature s from the i-th subcarrier data of the channel state information data. i , then the time series characteristics
[0018]
[0019]
[0020] Among them, LP is the linear projection operation, Norm is the layer normalization operation, and X i,:,: represents the data of all transmitting and receiving antenna pairs at all times of the i-th subcarrier, and softmax is the softmax function:
[0021]
[0022] x n is the nth element of vector x, X i,:,: The corresponding Query, Key, Value matrix in the attention mechanism, the hyperparameter d k is the scaling factor, is the set of real numbers, represents a real matrix of size F×T×C;
[0023] The frequency domain feature extraction unit uses the self-attention block to extract the frequency domain feature s from the j-th moment data of the channel state information data. j ,
[0024]
[0025] Among them, the hyperparameter d k is the scaling factor, X :,j,: Represents the data of all subcarriers and all transmit and receive antenna pairs at the jth moment;
[0026] X :,j,: The corresponding Query, Key, and Value matrices in the attention mechanism, represents a real matrix of size (F×1×C)×T;
[0027] A cross fusion unit is used to extract features between the time domain and the frequency domain, and use a cross attention block to fuse the time series features and the frequency domain features to obtain the time-frequency features.
[0028] K 3 ,V 3 =LP(Norm(S freq ))
[0029] Q 3 =LP(Norm(S time ))
[0030]
[0031] Among them, the hyperparameter d k is the scaling factor,
[0032] K 3 and V 3 They are the Key and Value matrices in the attention mechanism corresponding to the frequency domain features, Q 3 It is the Query matrix in the attention mechanism corresponding to the temporal features;
[0033] A mask fusion unit is used to fuse the time-frequency features and the channel state information data mask to obtain effective feature embedding
[0034] S condition =SiLU(Concat(S cross ,m))
[0035] Among them, Concat represents data concatenation, the activation function SiLu(·) is a sigmoid weighted linear unit, m∈{0,1} F×T×C is the channel state information data mask. The value of m is 0 when data is missing and 1 otherwise.
[0036] Preferably, the channel state information data of the missing position is generated by using the diffusion model in step 2, specifically as follows:
[0037] Generate random Gaussian noise And add it to the missing position of the channel state information data, that is:
[0038]
[0039] in, is the bitwise inversion of mask m, ⊙ is the bitwise multiplication of elements, is the channel state information with Gaussian noise added at the data missing position, X 0 is the initial channel state information with missing data;
[0040] Select a time step t and calculate the embedding of the current time step
[0041]
[0042] S condition As a condition, and S t As input, use the neural network to predict the added noise Then the data after t steps of denoising is The distribution is:
[0043]
[0044] Where θ is the parameter of the neural network, To add noise data The distribution of It is the denoising result of the tkth time step.
[0045] in, Indicates and S condition The condition is the result after denoising by neural network Satisfies the conditional Gaussian distribution, that is Conditional Expectation
[0046]
[0047] Among them, := means that β k is the noise level at step k, For the neural network, S condition As a condition, and S k is the noise predicted by the input t-k+1th step, is the covariance matrix and
[0048] Reconstructed channel state information
[0049] Preferably, the neural network comprises:
[0050] The network adopts a residual structure, which consists of N residual blocks. The input of each residual block includes the time step embedding S k , the feature embedding S condition and n=1,2,…,N three parts, among which, is the output of the n-1th residual block in the denoising process of the t-k+1th step
[0051] In the denoising process of the t-k+1th step, for the nth residual block, its output for:
[0052]
[0053] in, It is the intermediate variable calculated by the nth residual block according to the input in the denoising process of the t-k+1th step, The nth residual block in the denoising process of the t-k+1th step is respectively based on the intermediate variable The Key, Query, and Value matrices in the calculated attention mechanism, Add(·) is the summation function, and Conv(·) is a 1×1 convolution operation. is the output of the nth residual block in the denoising process of the t-k+1th step; then the noise predicted in the t-k+1th step for:
[0054]
[0055] Predict the added noise, which is the network output X in the last step of denoising out for:
[0056]
[0057] Therefore, the noise at the location where the channel state information data is missing can be calculated based on the mask:
[0058]
[0059] The time series feature extraction unit, frequency domain feature extraction unit, cross fusion unit, mask fusion unit, and neural network are trained end-to-end in a self-supervised manner. The specific steps include:
[0060] Step 2.1: Collect channel state information at a high sampling rate As training data, randomly select the loss rate γ in the range of [10%, 90%] to generate a mask m∈{0,1} F×T×C , where the value of γ×T moments is 0 and the rest are 1, then the low-sampling channel state information data X 0 =X hiigh ⊙m;
[0061] Step 2.2: Calculate the feature embedding S according to the feature embedding module condition ;
[0062] Step 2.3: Randomly sample diffusion time step t and generate random Gaussian noise Add the Gaussian noise to X hiigh Get
[0063]
[0064] in, Each component of ∈ is independent and identically distributed and follows a Gaussian distribution with a mean of 0 and a variance of 1, and I is the identity matrix;
[0065] in, β iis the noise level at step i, is the bitwise inversion of mask m, and ⊙ is the bitwise multiplication of elements;
[0066] Step 2.4: Based on the current time step embedding, predict the added noise through the neural network and calculate the predicted noise
[0067] Step 2.5: Calculate the loss And using the gradient descent method to update the model parameters of the feature embedding module and the data generation module;
[0068] Said is the noise prediction loss, and its calculation expression is
[0069]
[0070] ∈ is the Gaussian noise added in step 2.3, ‖*‖ 2 For L 2 Norm
[0071] Said is the cyclic spectrum loss, and its calculation expression is
[0072]
[0073] in, and They are The spectral correlation function and The spectral correlation function, X′ high and X′ out are respectively the high sampling rate channel state information X hiigh The data generation module denoises and reconstructs the channel state information X out According to the complex matrix composed of real and imaginary data, α is the cyclic frequency;
[0074] The spectral correlation function
[0075] Among them, (X′ high ) * Represents X′ high Each element of is conjugated, (X o ' ut ) * Indicates X o ' ut Perform conjugate operation on each element of ;
[0076] Among them, X′ high [k,1:T,1] means taking X′ highThe data of the first transmitting and receiving antenna pair at the 1st to Tth time of the kth subcarrier, (X′ high ) * [k-α,1:T,1] means taking (X′ high ) * The data of the first transmitting and receiving antenna pair at the first to T time of the k-αth subcarrier, X o ' ut [k,1:T,1] means taking X o ' ut The data of the first transmitting and receiving antenna pair at the 1st to Tth time of the kth subcarrier, (X o ' ut ) * [k-α,1:T,1] means taking (X o ' ut ) * The data of the first transmitting and receiving antenna pair at the first to T moments of the k-αth subcarrier;
[0077] Step 2.6: Repeat steps 2.2 to 2.5 until the training is completed.
[0078] Preferably, in step 3, the spectral correlation function is calculated according to the high sampling rate channel state information data, and interference detection is performed, specifically as follows:
[0079] The reconstructed channel state information X is calculated according to the calculation formula of the spectral correlation function: o ' ut The spectral correlation function And calculate the magnitude of each element;
[0080] The difference between each element and the adjacent element in the spectral correlation function amplitude is calculated to obtain a gradient matrix of the spectral correlation function amplitude, and an appropriate threshold is selected to detect whether the channel state information is interfered.
[0081] Perform singular value decomposition on the gradient matrix. If the largest singular value is greater than the threshold, there is interference, otherwise there is no interference.
[0082] The technical solution of the system of the present invention is a channel state information reconstruction system for channel state interference detection, comprising:
[0083] A feature embedding module, used to generate effective feature embedding according to the collected channel state information, wherein the channel state information data is low sampling rate channel state information data collected by the WiFi signal receiving end;
[0084] A data generation module, used to generate channel state information data of missing positions using a diffusion model based on the feature embedding, wherein the channel state information data of missing positions and the low sampling rate channel state information data together constitute reconstructed high sampling rate channel state information data;
[0085] An interference detection module, used to calculate a spectral correlation function based on the high sampling rate channel state information data and perform interference detection;
[0086] The low-sampling WiFi channel state information reconstruction method for channel state information interference detection provided by the present invention uses an end-to-end self-supervised method to train a neural network model, which can substantially reduce the workload of data collection and annotation; the present invention uses the characteristics of sampled data as a condition to guide a diffusion model for conditional data generation, which can substantially improve the channel state information data reconstruction performance; the present invention introduces cyclic spectrum loss, which can fully meet the requirements of interference detection tasks. BRIEF DESCRIPTION OF THE DRAWINGS
[0087] Figure 1 : A schematic diagram of a method flow chart of an embodiment of the present invention;
[0088] Figure 2 : Schematic diagram of a time series feature extraction unit and a frequency domain feature extraction unit according to an embodiment of the present invention;
[0089] Figure 3 : A schematic diagram of a cross-fusion unit according to an embodiment of the present invention;
[0090] Figure 4 : A schematic diagram of a neural network structure for predicting noise according to an embodiment of the present invention;
[0091] Figure 5 : System schematic diagram of an embodiment of the present invention. DETAILED DESCRIPTION
[0092] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0093] In specific implementation, the method proposed in the technical solution of the present invention can be implemented by technical personnel in this field using computer software technology to realize automatic operation process. System devices for implementing the method, such as computer-readable storage media storing the corresponding computer program of the technical solution of the present invention and computer equipment running the corresponding computer program, should also be within the scope of protection of the present invention.
[0094] In the embodiment of the present invention, the transmitter is a WiFi router device equipped with three antennas, the receiver is a desktop computer equipped with three antennas and an Intel 5300 network card, the transmitter and the receiver are 2 meters apart, and the interference signals include Bluetooth interference and ZigBee interference. The receiver end is configured with an independent physical server for running the method proposed by the technical solution of the present invention. In some embodiments, the receiving end may collect the initial channel state information data by other WiFi communication devices with the channel state information acquisition capability, and is not limited to the above configuration.
[0095] The following is combined with Figure 1-5 The specific implementation of the present invention is a channel state information reconstruction method and system for channel state interference detection, which is as follows:
[0096] Please see Figure 1 , Figure 1 1 is a flow chart of a method according to an embodiment of the present invention. The embodiment of the method according to the present invention is a channel state information reconstruction method for channel state interference detection, which is specifically as follows:
[0097] Step 1: Generate effective feature embedding according to the collected channel state information, wherein the channel state information data is low sampling rate channel state information data collected by the WiFi signal receiving end;
[0098] The channel state information collected in step 1 is as follows:
[0099] For a WiFi channel with M=3 transmitting antennas, N=3 receiving antennas and F=30 subcarriers, the channel state information data at T=1000 moments are collected to form the low sampling rate channel state information. Then, the low sampling rate channel state information of each transmitting and receiving antenna pair can be regarded as a three-dimensional matrix with a shape of F×T×2, which is composed of two two-dimensional matrices with a shape of F×T, respectively including the real data and the imaginary data of the low sampling rate channel state information of the transmitting and receiving antenna pair;
[0100] Initial channel state information
[0101] Where, C = 2 × M × N;
[0102] Among them, the channel state information value at the time when the sampled data is missing is 0, m∈{0,1} F×T×C is the channel state information data mask, the value of m is 0 when data is missing, otherwise it is 1;
[0103] Step 1 generates effective feature embedding as follows:
[0104] Temporal feature extraction unit, such as Figure 2As shown, the self-attention block is used to extract the temporal feature s of the i-th subcarrier data of the channel state information data. i , then the time series characteristics
[0105]
[0106]
[0107] Among them, LP is the linear projection operation, Norm is the layer normalization operation, and X i,:,: represents the data of all transmitting and receiving antenna pairs at all times of the i-th subcarrier, and softmax is the softmax function:
[0108]
[0109] x n is the nth element of vector x, X i,:,: The corresponding Query, Key, Value matrix in the attention mechanism, the hyperparameter d k is the scaling factor, is the set of real numbers, represents a real matrix of size F×T×C;
[0110] Frequency domain feature extraction unit, such as Figure 2 As shown, the self-attention block is used to extract the frequency domain feature s of the j-th moment data of the channel state information data. j ,
[0111]
[0112] Among them, the hyperparameter d k is the scaling factor, X :,j,: Represents the data of all subcarriers and all transmit and receive antenna pairs at the jth moment;
[0113] X :,j,: The corresponding Query, Key, and Value matrices in the attention mechanism, represents a real matrix of size (F×1×C)×T;
[0114] Cross-fusion units, such as Figure 2 As shown, it is used to extract features between the time domain and the frequency domain, and the time series features and the frequency domain features are fused using a cross attention block to obtain the time-frequency features.
[0115] K 3 ,V 3 =LP(Norm(Sfreq ))
[0116] Q 3 =LP(Norm(S time ))
[0117]
[0118] Among them, the hyperparameter d k is the scaling factor,
[0119] K 3 and V 3 They are the Key and Value matrices in the attention mechanism corresponding to the frequency domain features, Q 3 It is the Query matrix in the attention mechanism corresponding to the temporal features;
[0120] A mask fusion unit is used to fuse the time-frequency features and the channel state information data mask to obtain effective feature embedding
[0121] S condition =SiLU(Concat(S cross ,m))
[0122] Among them, Concat represents data concatenation, the activation function SiLu(·) is a sigmoid weighted linear unit, m∈{0,1} F×T×C is the channel state information data mask. The value of m is 0 when data is missing and 1 otherwise.
[0123] Step 2: Generate channel state information data of the missing position using a diffusion model, wherein the channel state information data of the missing position and the low sampling rate channel state information data together constitute reconstructed high sampling rate channel state information data;
[0124] Step 2 uses the diffusion model to generate the channel state information data of the missing position, as follows:
[0125] Generate random Gaussian noise And add it to the missing position of the channel state information data, that is:
[0126]
[0127] in, is the bitwise inversion of mask m, ⊙ is the bitwise multiplication of elements, is the channel state information with Gaussian noise added at the data missing position, X 0 is the initial channel state information with missing data;
[0128] Select a time step t=50 and calculate the embedding of the current time step
[0129]
[0130] S condition As a condition, and S t As input, use the neural network to predict the added noise Then the data after t steps of denoising is The distribution is:
[0131]
[0132] Among them, θ is the parameter of the neural network, To add noise data The distribution of It is the denoising result of the tkth time step.
[0133] in, Indicates and S condition The condition is the result after denoising by neural network Satisfies the conditional Gaussian distribution, that is Conditional Expectation
[0134]
[0135] Among them, := means that β k is the noise level at step k, For the neural network, S condition As a condition, and S k is the noise predicted by the input t-k+1th step, is the covariance matrix and
[0136] Reconstructed channel state information
[0137] The neural network comprises:
[0138] The network adopts a residual structure, such as Figure 4 As shown, it consists of N = 4 residual blocks, and the input of each residual block includes the time step embedding S k , the feature embedding S condition and n=1,2,...,N three parts, among which, is the output of the n-1th residual block in the denoising process of the t-k+1th step
[0139] In the denoising process of the t-k+1th step, for the nth residual block, its output for:
[0140]
[0141]
[0142]
[0143] in, It is the intermediate variable calculated by the nth residual block according to the input in the denoising process of the t-k+1th step, The nth residual block in the denoising process of the t-k+1th step is respectively based on the intermediate variable The Key, Query, and Value matrices in the calculated attention mechanism, Add(·) is the summation function, and Conv(·) is a 1×1 convolution operation. is the output of the nth residual block in the denoising process of the t-k+1th step; then the noise predicted in the t-k+1th step for:
[0144]
[0145] Predict the added noise, which is the network output X in the last step of denoising out for:
[0146]
[0147] Therefore, the noise at the location where the channel state information data is missing can be calculated based on the mask:
[0148]
[0149] The time series feature extraction unit, frequency domain feature extraction unit, cross fusion unit, mask fusion unit, and neural network are trained end-to-end in a self-supervised manner. The specific steps include:
[0150] Step 2.1: Collect channel state information at a high sampling rate As training data, randomly select the loss rate γ in the range of [10%, 90%] to generate a mask m∈{0,1} F×T×C , where the value of γ×T moments is 0 and the rest are 1, then the low-sampling channel state information data X 0 =X high ⊙m;
[0151] Step 2.2: Calculate the feature embedding S according to the feature embedding module condition ;
[0152] Step 2.3: Randomly sample diffusion time step t and generate random Gaussian noise Add the Gaussian noise to X high Get
[0153]
[0154] in, Each component of ∈ is independent and identically distributed and follows a Gaussian distribution with a mean of 0 and a variance of 1, and I is the identity matrix;
[0155] in, β i is the noise level at step i, is the bitwise inversion of mask m, and ⊙ is the bitwise multiplication of elements;
[0156] Step 2.4: Calculate the predicted noise through the neural network according to the current time step embedding, calculate the predicted noise
[0157] Step 2.5: Calculate the loss And using the gradient descent method to update the model parameters of the feature embedding module and the data generation module;
[0158] Said is the noise prediction loss, and its calculation expression is
[0159]
[0160] ∈ is the Gaussian noise added in step 2.3, ‖*‖ 2 For L 2 Norm
[0161] Said is the cyclic spectrum loss, and its calculation expression is
[0162]
[0163] in, and They are The spectral correlation function and The spectral correlation function, X′ high and X′ out are respectively the high sampling rate channel state information X high The data generation module denoises and reconstructs the channel state information X out According to the complex matrix composed of real and imaginary data, α is the cyclic frequency;
[0164] The spectral correlation function
[0165] Among them, (X′ high ) * Represents X′ high Each element of is conjugated, (X o ' ut ) * Indicates X o ' ut Perform conjugate operation on each element of ;
[0166] Among them, X′ high [k,1:T,1] means taking X′ high The data of the first transmitting and receiving antenna pair at the 1st to Tth time of the kth subcarrier, (X′ high ) * [k-α,1:T,1] means taking (X′ high ) * The data of the first transmitting and receiving antenna pair at the first to T time of the k-αth subcarrier, X o ' ut [k,1:T,1] means taking X o ' ut The data of the first transmitting and receiving antenna pair at the 1st to Tth time of the kth subcarrier, (X o ' ut ) * [k-α,1:T,1] means taking (X o ' ut ) * The data of the first transmitting and receiving antenna pair at the first to T moments of the k-αth subcarrier;
[0167] Step 2.6: Repeat steps 2.2 to 2.5 until the training is completed.
[0168] Step 3: Calculate a spectral correlation function according to the high sampling rate channel state information data, and perform interference detection;
[0169] Step 3 calculates the spectral correlation function according to the high sampling rate channel state information data and performs interference detection, as follows:
[0170] The reconstructed channel state information X is calculated according to the calculation formula of the spectral correlation function: o ' ut The spectral correlation function And calculate the magnitude of each element;
[0171] The difference between each element and the adjacent element in the spectral correlation function amplitude is calculated to obtain a gradient matrix of the spectral correlation function amplitude, and an appropriate threshold is selected to detect whether the channel state information is interfered.
[0172] Perform singular value decomposition on the gradient matrix. If the largest singular value is greater than the threshold, there is interference, otherwise there is no interference.
[0173] The system embodiment of the present invention is a channel state information reconstruction system for channel state interference detection, comprising:
[0174] like Figure 5 As shown, the feature embedding module is used to generate effective feature embedding according to the collected channel state information, and the channel state information data is the low sampling rate channel state information data collected by the WiFi signal receiving end;
[0175] A data generation module, used to generate channel state information data of missing positions using a diffusion model based on the feature embedding, wherein the channel state information data of missing positions and the low sampling rate channel state information data together constitute reconstructed high sampling rate channel state information data;
[0176] An interference detection module, used to calculate a spectral correlation function based on the high sampling rate channel state information data and perform interference detection;
[0177] Table 1: Comparison of experimental results
[0178]
[0179] Table 1 compares the experimental results of the method proposed in the present invention with the existing technology, and respectively statistics the mean square error (MSE) of reconstructing the channel state information using linear interpolation, generative adversarial network (GAN) and the diffusion model method adopted by the present invention, and statistics the accuracy of the original low sampling rate data and the channel state information reconstructed by the three technologies for interference detection.
[0180] Experimental results show that the channel state information reconstruction method and system proposed by the present invention have lower reconstruction errors than the existing technologies and can accurately reconstruct low sampling rate channel state information. At the same time, the channel state information reconstructed by the present invention can better retain spectrum information and improve the accuracy of interference detection.
[0181] It should be understood that parts not elaborated in detail in this specification belong to the prior art.
[0182] It should be understood that the above description of the preferred embodiment is relatively detailed and cannot be regarded as limiting the scope of patent protection of the present invention. Under the enlightenment of the present invention, ordinary technicians in this field can also make substitutions or modifications without departing from the scope of protection of the claims of the present invention, which all fall within the scope of protection of the present invention. The scope of protection requested for the present invention shall be based on the attached claims.
Claims
1. A channel state information reconstruction method for channel state interference detection, characterized in that: The following steps are involved: Step 1: Generate effective feature embedding according to the collected channel state information, wherein the channel state information data is low sampling rate channel state information data collected by the WiFi signal receiving end; Step 2: Generate channel state information data of the missing position using a diffusion model, wherein the channel state information data of the missing position and the low sampling rate channel state information data together constitute reconstructed high sampling rate channel state information data; Step 3: Calculate the spectral correlation function according to the high sampling rate channel state information data and perform interference detection.
2. The channel state information reconstruction method for channel state interference detection according to claim 1, characterized in that: The channel state information collected in step 1 is as follows: Initial channel state information Where, C = 2 × M × N; Among them, the channel state information value at the time when the sampled data is missing is 0, m∈{0,1} F×T×C is the channel state information data mask. The value of m is 0 when data is missing and 1 otherwise.
3. The channel state information reconstruction method for channel state interference detection according to claim 2, characterized in that: Step 1 generates effective feature embedding as follows: The generation of effective feature embedding is achieved through a temporal feature extraction unit, a frequency domain feature extraction unit, a cross fusion unit, and a mask fusion unit.
4. The channel state information reconstruction method for channel state interference detection according to claim 3, characterized in that: The time series feature extraction unit uses the self-attention block to extract the time series feature s from the i-th subcarrier data of the channel state information data i , then the time series characteristics Among them, LP is the linear projection operation, Norm is the layer normalization operation, and X i,:,: represents the data of all transmitting and receiving antenna pairs at all times of the i-th subcarrier, and softmax is the softmax function: x n is the nth element of vector x, X i,:,: The corresponding Query, Key, Value matrix in the attention mechanism, the hyperparameter d k is the scaling factor, is the set of real numbers, represents a real matrix of size F×T×C; The frequency domain feature extraction unit uses the self-attention block to extract the frequency domain feature s from the j-th moment data of the channel state information data. j , Among them, the hyperparameter d k is the scaling factor, X :,j,: Represents the data of all subcarriers and all transmit and receive antenna pairs at the jth moment; X :,j,: The corresponding Query, Key, and Value matrices in the attention mechanism, represents a real matrix of size (F×1×C)×T; A cross fusion unit is used to extract features between the time domain and the frequency domain, and use a cross attention block to fuse the time series features and the frequency domain features to obtain the time-frequency features. K3,V3=LP(Norm(S freq )) Q3=LP(Norm(S time )) Among them, the hyperparameter d k is the scaling factor, K3 and V3 are the Key and Value matrices in the attention mechanism corresponding to the frequency domain features, respectively, and Q3 is the Query matrix in the attention mechanism corresponding to the time series features; A mask fusion unit is used to fuse the time-frequency features and the channel state information data mask to obtain effective feature embedding With condition =SiLU(Concat(S cross ,m)) Among them, Concat represents data concatenation, the activation function SiLu(·) is a sigmoid weighted linear unit, m∈{0,1} F×T×C is the channel state information data mask. The value of m is 0 when data is missing and 1 otherwise.
5. The channel state information reconstruction method for channel state interference detection according to claim 4, characterized in that: Step 2 uses the diffusion model to generate the channel state information data of the missing position, as follows: Generate random Gaussian noise And add it to the missing position of the channel state information data, that is: in, is the bitwise inversion of mask m, ⊙ is the bitwise multiplication of elements, is the channel state information with Gaussian noise added at the data missing position, and X0 is the initial channel state information with data missing; Select a time step t and calculate the embedding of the current time step S condition As a condition, and S t As input, use the neural network to predict the added noise Then the data after t steps of denoising is The distribution is: Where θ is the parameter of the neural network, To add noise data The distribution of is the denoising result of the tkth time step; in, Indicates and S condition The condition is the result after denoising by neural network Satisfies the conditional Gaussian distribution, that is Conditional Expectation Among them, := means that β k is the noise level at step k, For the neural network, S condition As a condition, and S k is the noise predicted by the input t-k+1th step, is the covariance matrix and Reconstructed channel state information 6. The channel state information reconstruction method for channel state interference detection according to claim 5, characterized in that: The neural network comprises: The network adopts a residual structure, which consists of N residual blocks. The input of each residual block includes the time step embedding S k , the feature embedding S condition and Three parts, among which, is the output of the n-1th residual block in the denoising process of the t-k+1th step In the denoising process of the t-k+1th step, for the nth residual block, its output for: in, It is the intermediate variable calculated by the nth residual block according to the input in the denoising process of the t-k+1th step, The nth residual block in the denoising process of the t-k+1th step is respectively based on the intermediate variable The Key, Query, and Value matrices in the calculated attention mechanism, Add(·) is the summation function, and Conv(·) is a 1×1 convolution operation. is the output of the nth residual block in the denoising process of the t-k+1th step; then the noise predicted in the t-k+1th step for: Predict the added noise, which is the network output X in the last step of denoising out for: Therefore, the noise at the location where the channel state information data is missing can be calculated based on the mask:
7. The channel state information reconstruction method for channel state interference detection according to claim 6, characterized in that: The time series feature extraction unit, frequency domain feature extraction unit, cross fusion unit, mask fusion unit, and neural network are trained end-to-end in a self-supervised manner. The specific steps include: Step 2.1: Collect channel state information at a high sampling rate As training data, randomly select the loss rate γ in the range of [10%, 90%] to generate a mask m∈{0,1} F×T×C , where the value of γ×T moments is 0 and the rest are 1, then the low sampling channel state information data X0=X high ⊙m; Step 2.2: Calculate the feature embedding S according to the feature embedding module condition ; Step 2.3: Randomly sample diffusion time step t and generate random Gaussian noise Add the Gaussian noise to X high Get in, Each component of ∈ is independent and identically distributed and follows a Gaussian distribution with a mean of 0 and a variance of 1, and I is the identity matrix; in, β i is the noise level at step i, is the bitwise inversion of mask m, and ⊙ is the bitwise multiplication of elements; Step 2.4: Calculate the predicted noise through the neural network based on the current time step embedding Step 2.5: Calculate the loss And using the gradient descent method to update the model parameters of the feature embedding module and the data generation module; Said is the noise prediction loss, and its calculation expression is ∈ is the Gaussian noise added in step 2.3, ‖*‖2 is the L2 norm Said is the cyclic spectrum loss, and its calculation expression is in, and They are The spectral correlation function and The spectral correlation function, X′ high and X′ out are respectively the high sampling rate channel state information X high The data generation module denoises and reconstructs the channel state information X out According to the complex matrix composed of real and imaginary data, α is the cyclic frequency; The spectral correlation function Among them, (X′ high ) * Represents X′ hugh Each element of is conjugated, (X o ' ut ) * Indicates X o ' ut Perform conjugate operation on each element of ; Among them, X′ high [k,1:T,1] means taking X′ high The data of the first transmitting and receiving antenna pair at the 1st to Tth time of the kth subcarrier, (X′ high ) * [k-α,1:T,1] means taking (X′ high ) * The data of the first transmitting and receiving antenna pair at the first to T time of the k-αth subcarrier, X o ' ut [k,1:T,1] means taking X o ' ut The data of the first transmitting and receiving antenna pair at the 1st to Tth time of the kth subcarrier, (X o ' ut ) * [k-α,1:T,1] means taking (X o ' ut ) * The data of the first transmitting and receiving antenna pair at the first to T moments of the k-αth subcarrier; Step 2.6: Repeat steps 2.2 to 2.5 until the training is completed.
8. The channel state information reconstruction method for channel state interference detection according to claim 7, characterized in that: Step 3 calculates the spectral correlation function according to the high sampling rate channel state information data and performs interference detection, as follows: The reconstructed channel state information X is calculated according to the calculation formula of the spectral correlation function: o ' ut The spectral correlation function And calculate the magnitude of each element; Calculating the difference between each element and the adjacent element in the spectral correlation function amplitude to obtain a gradient matrix of the spectral correlation function amplitude, and selecting an appropriate threshold to detect whether the channel state information is interfered; Perform singular value decomposition on the gradient matrix. If the largest singular value is greater than the threshold, there is interference, otherwise there is no interference.
9. A channel state information reconstruction system for channel state interference detection, comprising: A feature embedding module, used to generate effective feature embedding according to the collected channel state information, wherein the channel state information data is low sampling rate channel state information data collected by the WiFi signal receiving end; A data generation module, used to generate channel state information data of missing positions using a diffusion model based on the feature embedding, wherein the channel state information data of missing positions and the low sampling rate channel state information data together constitute reconstructed high sampling rate channel state information data; The interference detection module is used to calculate the spectrum correlation function according to the high sampling rate channel state information data and perform interference detection.
Citation Information
Patent Citations
Seismic data reconstruction method
CN116819615A
Radar active deception jamming signal identification method based on de-noising diffusion probability model
CN117368857A
Wirless signal monitoring and analysis, and related methods, systems, and devices
US20200007249A1
Pet image reconstruction algorithm combining filtered back-projection algorithm and neural network
WO2021232653A1
Cited By
Wireless communication channel anti-reconnaissance method and system based on known structure and expected transformation enhanced disturbance
CN121262578A
