A research method for acupuncture point classification and multi-channel EEG signal correlation analysis based on convolutional networks

Abstract

The present invention discloses a research method for acupuncture point classification and multi-channel EEG signal correlation analysis based on convolutional networks, which belongs to the field of brain-computer interface and signal processing. It is specifically implemented according to the following steps: first, the required data is collected by EEG signal acquisition equipment, and the obtained EEG signals are pre-processed: filtering, segmentation; the correlation between channels is studied and visualized; the time-frequency characteristics of the EEG signals are extracted by wavelet transform: a time-frequency graph is drawn; the time-frequency graph results are then input into the SE‑ConvNeXt network training to obtain the results of acupuncture point classification; the results are analyzed, and the accuracy is intuitively expressed using a confusion matrix. The method of the present invention has important reference significance for in-depth research on the regulatory mechanism of traditional Chinese medicine of acupuncture points on the central nervous system, as well as research on the classification of acupuncture points based on EEG signals.

Description

Technical Field

[0001] The present invention belongs to the field of brain-computer interface and signal processing, and specifically relates to a research method for acupuncture point classification and multi-channel EEG signal correlation analysis based on convolutional networks. Background Art

[0002] Acupuncture, originating in traditional Chinese medicine, has a history dating back thousands of years, initially used to relieve pain and treat various ailments. With the development of modern science, acupuncture has gradually attracted the attention of researchers worldwide. In recent years, research has focused on its physiological mechanisms, its effects on the nervous system, and its clinical effectiveness in relieving pain, anxiety, and insomnia.

[0003] Acupuncture, an important traditional Chinese medicine therapy, is widely used in the clinical treatment of various diseases, with significant therapeutic effects in relieving pain, improving mood, and regulating body functions. However, the mechanism of action of acupuncture has not yet been fully revealed.

[0004] In recent years, electroencephalogram (EEG) signals have been used to study psychological processes such as emotion, attention, and memory, helping scientists gain a deeper understanding of the brain's workings and the neural basis of various psychological states. With the continuous advancement of technology, the application prospects of EEG research are becoming increasingly broad. As a noninvasive and real-time method of reflecting brain activity, EEG provides important technical support for studying the regulation of acupuncture on the central nervous system.

[0005] By combining acupuncture with modern EEG technology, we can delve deeper into the regulatory mechanisms of acupuncture on the central nervous system. These background technologies provide theoretical and technical support for experimental studies of acupuncture's effects on EEG, and serve as an important foundation for promoting the scientific and modern development of acupuncture. Summary of the Invention

[0006] To address the aforementioned issue of unclear acupuncture mechanisms, this paper proposes a convolutional network-based method for acupuncture point classification and multi-channel EEG signal correlation analysis. This approach leverages existing EEG technology to amplify the effectiveness of traditional Chinese medicine acupuncture, demonstrating that acupuncture is a response to EEG states, thereby making the practice more scientific and rational. This method uses relevant EEG data to classify the effects of acupuncture at different points, thereby verifying the effectiveness of acupuncture, confirming that acupuncture does indeed have a definite impact on the body's electrical signals.

[0007] In order to achieve the above object, the technical solution adopted by the present invention is:

[0008] A research method for acupuncture point classification and multi-channel EEG signal correlation analysis based on convolutional networks includes the following steps:

[0009] a. Use EEG signal acquisition equipment to collect the required data;

[0010] b. EEG signal preprocessing;

[0011] c. Perform correlation analysis on EEG signals and then visualize them;

[0012] d. Use wavelet transform to extract the time-frequency characteristics of EEG signals and draw time-frequency graphs;

[0013] e. Put the time-frequency graph results into SE-ConvNeXt network training to obtain the prediction results of acupuncture point effect classification;

[0014] f. Result analysis: Use confusion matrix to intuitively express the accuracy.

[0015] In step a, an electroencephalogram (EEG) device is used to collect EEG signal responses during acupuncture of different acupoints as training and test sets to train the acupuncture point classification network. The original EEG data is collected by a 32-lead device with a sampling rate of 250 Hz. The EEG data are collected before acupuncture, during acupuncture, and after needle removal. The EEG is continuously collected after needle insertion. The needle retention time is set to 25 minutes, and the needle sensation is adjusted every 5 minutes to ensure the continuity of the acupuncture stimulation. The EEG recording of the entire acupuncture process is recorded as a block. An event marker is synchronously recorded in the EEG during needle insertion and needle sensation adjustment to facilitate subsequent data collation and analysis.

[0016] In step b, a Butterworth bandpass filter is selected to filter out the information of the main frequency band of the EEG signal and sort it out, and only the 30 seconds after the stimulation is taken as the valid data as the content of the subsequent data set.

[0017] In step c, in order to explore the response patterns of signals in different brain regions (channels) during acupuncture, that is, whether the amplitudes of any two signal bands have the same or different change patterns during stimulation; any two channels and any frequency bands are subjected to cross-correlation analysis and a correlation graph is drawn; the normalized cross-correlation calculation formula in the correlation analysis is:

[0018]

[0019] Among them, x(k) and y(k) are EEG signals of different channels; r(n) is the correlation between EEG signals.

[0020] In step d, the method for extracting the time-frequency characteristics of the EEG signal by wavelet transform is as follows:

[0021] Use wavelet transform to perform time-frequency analysis on the filtered signal to obtain the frequency characteristic information of each channel and each segment. The corresponding wavelet transform is:

[0022]

[0023] Among them, W fi (a, τ) is the different power density of each channel at time t = τ, f i,j (t) is the j-th segment EEG signal of channel i, is the complex conjugate of the wavelet basis function, and the wavelet basis function is expressed as:

[0024]

[0025] in, is the normalization factor, a is the scale factor, and b is the translation factor. The wavelet basis function commonly used in EEG analysis is Morlet wavelet, which is expressed as After substituting into the above formula, the specific expression is:

[0026]

[0027] Where f0 is the center frequency and σ is the standard deviation.

[0028] In the step e, the feature map extracted by wavelet transform and the sorted related data are classified, and the training set is input into the SE-ConvNeXt network for training to obtain the prediction classification results of the acupuncture points; the SE-ConvNeXt network is improved on the basis of ConvNeXt, and the SE model (Squeeze-and-Excitation Model) is added before the features are input into the network to improve the representation ability of the network, and the weights of different channels are adaptively allocated and learned by the network itself; each layer of the input feature map X is convolved with a 2D spatial kernel to finally obtain C output feature maps, which constitute the feature maps U, F sq Indicates that the global pooling is reduced to a one-dimensional vector, F ex The gate mechanism consists of two fully connected layers. The first fully connected layer compresses C channels into C / r channels to reduce the amount of computation. Then, a RELU nonlinear activation layer is passed. The second fully connected layer restores the number of channels to C channels. Then, a Sigmoid activation is performed to obtain the weight s. The dimension of the final s is 1×1×C, which is used to characterize the weights of the C feature maps in the feature map U. scale The attention weights obtained previously are weighted to the features of each channel; the next layer consists of a convolutional layer, a ConvNeXt Block, a Downsample, a local pooling layer, and a fully connected layer; the activation function used in the ConvNeXt Block is GELU; the Downsample layer consists of layer normalization and a two-dimensional convolution kernel.

[0029] In step f, the model effect needs to be evaluated. First, a confusion matrix is ​​constructed for the classification effect of each acupoint category i, and the TP (true positive), FP (false positive), FN (false negative) and TN (true negative) values ​​of each category are counted. Then, the overall precision (Micro-Precision) can be calculated based on these values. The calculation formula is:

[0030]

[0031] The effectiveness of the model is judged by calculating the overall accuracy. The closer the value is to 1, the more effective the model is in predicting acupoints through EEG features; vice versa.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] 1. The method based on EEG correlation analysis of the present invention visualizes the correlation characteristics of EEG signal sequences of different channels, adding a new option for a more intuitive display of the scientific nature of the field of traditional Chinese medicine acupuncture.

[0034] 2. Subdividing EEG signals into specific frequency bands can also demonstrate the correlation analysis effect of arbitrary frequency bands in different channels and different frequency bands in the same channel during acupuncture.

[0035] 3. The present invention uses a ConvNeXt network to classify the features extracted by wavelet transform. The network increases the size of the convolution kernel and the model width, but through refined design, it maintains a high computational efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a flowchart of the program of the present invention.

[0037] Figure 2 This is the flowchart of the EEG acquisition experiment.

[0038] Figure 3 Cross-correlation analysis of channels C3 and Cz.

[0039] Figure 4 This is the network architecture diagram of the classification network SE-ConvNeXt proposed in this invention. DETAILED DESCRIPTION

[0040] The present invention provides a research method for acupuncture point classification and multi-channel EEG signal correlation analysis based on convolutional networks, which can not only visualize the correlation between each channel of the control and experimental groups, but also serve as a verification of the effectiveness of acupuncture points. Figure 1 , which includes the following steps:

[0041] a. Use EEG signal acquisition equipment to collect the required data.

[0042] Use EEG equipment to collect relevant data information, specify the experimental plan, connect to the computer, and prepare for the experiment.

[0043] An acupuncture EEG acquisition experiment was designed. The purpose of the experiment was to collect EEG signal responses during acupuncture at different acupoints as training and test sets to train the acupuncture point classification network. The original EEG data of the experiment was collected by a 32-lead device with a sampling rate of 250 Hz. The experimental content included baseline acquisition (5 minutes before acupuncture), during acupuncture (continuous EEG acquisition after needle insertion, setting the needle retention time to 25 minutes, and adjusting the needle sensation every 5 minutes (such as slight twisting) to ensure the continuity of acupuncture stimulation), and after needle removal (5 minutes). The EEG recording of the entire acupuncture process was a block. An event marker (see Figure 2 ) for subsequent data collation and analysis.

[0044] Acupoints with clear therapeutic effects and research foundations were selected based on the experimental purpose. For example: Shenmen (HT7): Located on the ulnar side of the wrist crease, in the radial depression of the flexor carpi ulnaris tendon, Shenmen acupoint has calming and tranquilizing effects in Traditional Chinese Medicine. Neiguan (PC6): Located on the inner side of the forearm, it is often used to relieve anxiety and improve sleep, and its regulatory effect on EEG has been studied. Jianjing (GB21): Located at the highest point of the shoulder, it is often used to treat pain and stiffness in the shoulder and neck area. Hegu (LI4): Located on the back of the hand, it is used for analgesia and mood regulation.

[0045] The operator must have extensive clinical experience to ensure the accuracy and consistency of the technique. The number of acupoints selected should be one to avoid interference with the research results due to excessive acupoints. To ensure that the number of subjects meets statistical requirements, at least 30-50 volunteers should be included to ensure the reliability and representativeness of the data. Acupuncture frequency should be selected once a day or every other day for 2-4 weeks to ensure the accumulation and stability of the therapeutic effect. Acupuncture operation safety records should be established to observe the subjects' reactions at all times to ensure their safety and comfort. Any discomfort or abnormal reactions should be promptly addressed and recorded.

[0046] b. EEG signal preprocessing.

[0047] A Butterworth bandpass filter (0.5-40Hz) was selected to filter out and organize the information of the main frequency bands of the EEG signal. Since a single piece of data is too long, it is not conducive to accurate feature extraction and subsequent calculations. Therefore, the data is segmented at the marked points and divided into 7 segments. At this time, the length of each time segment is 5 minutes. In terms of the effect of acupuncture points, most of the data is still invalid and lengthy, so for the acupuncture part, only the 30 seconds after stimulation is taken as valid data for the subsequent data set content.

[0048] c. Perform correlation analysis on EEG signals and then visualize them.

[0049] To explore the patterns of acupuncture response in different brain regions (channels), that is, whether the amplitudes of any two signal bands have the same or different patterns of change during stimulation, we performed cross-correlation analysis on any two channels at any frequency band and plotted the correlation graph. The normalized cross-correlation calculation formula in the correlation analysis is:

[0050]

[0051] Among them, x(k) and y(k) are EEG signals of different channels; r(n) is the correlation between EEG signals.

[0052] The cross-correlation function is calculated by moving a time series vector step by step and repeatedly calculating the correlation between the two signals. If the peak of the correlation is at the center (offset = 0), it means that the two time series are most correlated at this time. However, if one signal is leading the other, the peak of the correlation may be at different coordinates. Using channels C3 and Cz as an example, draw a cross-correlation graph (see Appendix Figure 3 As can be seen from the figure, the maximum correlation value exceeds 0.8, and the peak of the correlation is located in the center. Generally speaking, a correlation coefficient exceeding 0.75 is considered to be a strong correlation.

[0053] d. Use wavelet transform to extract the time-frequency features of EEG signals and draw the time-frequency graph.

[0054] Use wavelet transform to perform time-frequency analysis on the filtered signal to obtain the frequency characteristic information of each channel and each segment. The corresponding wavelet transform is:

[0055]

[0056] Among them, W fi (a, τ) is the different power density of each channel at time t = τ, f i,j (t) is the jth segment EEG signal of channel i, is the complex conjugate of the wavelet basis function, which is generally expressed as:

[0057]

[0058] in, is the normalization factor, a is the scale factor, and b is the translation factor. The wavelet basis function commonly used in EEG analysis is Morlet wavelet, which is expressed as After substituting into the above formula, the specific expression is:

[0059]

[0060] Where f0 is the center frequency and σ is the standard deviation (which controls the width of the time window).

[0061] e. The time-frequency graph results are put into SE-ConvNeXt network training to obtain the prediction results of acupuncture point effect classification.

[0062] The feature map extracted from the time-frequency information collected by wavelet transform in the previous step is input into the SE-ConvNeXt network (see Figure 4 ), predicting the classification of acupuncture points.

[0063] ConvNeXt is a network based on pure convolution, which has significantly improved classification accuracy compared to traditional convolutional networks. Compared with the 3×3 convolution kernel commonly used in traditional CNN, ConvNeXt uses larger convolution kernels (such as 7×7 and 9×9), which can extract feature information more widely. In addition, ConvNeXt not only optimizes the depth of the network, but also increases the width of the network, that is, introduces more channels, which improves the model's ability to express complex features. Its network architecture also draws on ResNet's staged downsampling strategy. Each stage reduces the amount of computation by reducing the resolution of the feature map, while retaining more fine-grained features, thereby achieving higher accuracy in classification and segmentation tasks. In addition, the network has made many adjustments to the details, such as using fewer activation functions and normalization layers; using a separate downsampling layer, etc.

[0064] The SE-ConvNeXt network constructed in this paper is an improvement on ConvNeXt. It adds SE model (Squeeze-and-Excitation Model) before the features are input to the network. Its purpose is to improve the representation ability of the network. The core idea is that the weights of different channels should be adaptively allocated and learned by the network itself. Its main structure is as follows: Figure 4 As shown in the SE Model, F tr It represents the convolution operation. Each layer of the input feature map X undergoes a 2D spatial kernel convolution and finally obtains C output feature maps, which form feature maps U, F sq Indicates that the global pooling is reduced to a one-dimensional vector, F exThe gate mechanism consists of two fully connected layers. The first fully connected layer compresses C channels into C / r channels to reduce the amount of calculation. Then, through a RELU nonlinear activation layer, the second fully connected layer restores the number of channels to C channels. Then, through Sigmoid activation, the weight s is obtained. The dimension of the final s is 1×1×C, which is used to characterize the weights of the C feature maps in the feature map U. r refers to the compression ratio. Finally, F scale The attention weights obtained above are applied to the features of each channel. The next step consists of a convolutional layer, a ConvNeXt Block, a downsampling layer, a local pooling layer, and a fully connected layer. The activation function used in the ConvNeXt Block is GELU. The downsampling layer consists of layer normalization and a two-dimensional convolution kernel.

[0065] f. Result analysis: Use confusion matrix to intuitively express the accuracy.

[0066] To evaluate the model's effectiveness, we first construct a confusion matrix for each acupoint category i. Typically, in multi-classification problems, we focus on the TP (True Positives), FP (False Positives), FN (False Negatives), and TN (True Negatives) values ​​for each category. We can then calculate metrics based on these values. This method uses the Micro-Precision, which is calculated as follows:

[0067]

[0068] The effectiveness of the model is judged by calculating the overall accuracy. The closer the value is to 1, the more effective the model is in predicting acupoints through EEG features; vice versa.

[0069] The above content is merely an example and explanation of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they should all fall within the scope of protection of the present invention.

Claims

1. A research method for acupuncture point classification and multi-channel EEG signal correlation analysis based on convolutional networks, characterized in that: The steps include: a. Use EEG signal acquisition equipment to collect the required data; b. EEG signal preprocessing; c. Perform cross-correlation analysis on any two channels of EEG signals and then visualize them; d. Use wavelet transform to extract the time-frequency characteristics of EEG signals and draw a time-frequency graph; e. Feed the time-frequency graph results into the SE-ConvNeXt network training to obtain the prediction results of acupuncture point classification; f. Result analysis: Use confusion matrix to intuitively express the accuracy.

2. The research method according to claim 1, characterized in that In step a, an electroencephalogram (EEG) device is used to collect EEG signal responses during acupuncture of different acupoints as training and test sets to train the acupuncture point classification network. The original EEG data is collected by a 32-lead device with a sampling rate of 250 Hz. The EEG data are collected before acupuncture, during acupuncture, and after needle removal. The EEG is continuously collected after needle insertion. The needle retention time is set to 25 minutes, and the needle sensation is adjusted every 5 minutes to ensure the continuity of the acupuncture stimulation. The EEG recording of the entire acupuncture process is recorded as a block. An event marker is synchronously recorded in the EEG during needle insertion and needle sensation adjustment for subsequent data collation and analysis.

3. The research method according to claim 2, characterized in that: In step b, a Butterworth bandpass filter is selected to filter out the information of the main frequency band of the EEG signal and sort it out, and only the 30 seconds after the stimulation is taken as the valid data as the content of the subsequent data set.

4. The research method according to claim 3, characterized in that In step c, in order to explore the response patterns of different channel signals during acupuncture, that is, whether the amplitudes of any two signal bands have the same or different change patterns during stimulation, cross-correlation analysis is performed on any two channel frequency bands, and a correlation graph is drawn. The normalized cross-correlation calculation formula in the correlation analysis is: in, and It is the EEG signal of different channels; is the magnitude of the correlation between EEG signals.

5. The research method according to claim 4, characterized in that: In step d, the method for extracting the time-frequency characteristics of the EEG signal by wavelet transform is as follows: Use wavelet transform to perform time-frequency analysis on the filtered signal to obtain the frequency characteristic information of each channel and each segment. The corresponding wavelet transform is: in, It is Each channel at time Different power density conditions, is the j-th segment EEG signal of channel i, is the complex conjugate of the wavelet basis function, and the wavelet basis function is expressed as: in, is the normalization factor, is the scale factor, is the translation factor; the wavelet basis function commonly used in EEG analysis is Morlet wavelet, which is expressed as , after substituting into the above formula, the specific expression is: in, is the center frequency, is the standard deviation.

6. The research method according to claim 5, characterized in that In step e, the feature maps extracted by wavelet transform and the collated related data are classified, and the training set is input into the SE-ConvNeXt network for training to obtain the predicted classification results of the acupuncture points. The SE-ConvNeXt network is an improvement on the ConvNeXt network. The SE model is added before the features are input into the network to improve the network's representation ability. The weights of different channels are adaptively allocated and learned by the network itself. Each layer of the input feature map X undergoes convolution with a 2D spatial kernel to obtain C output feature maps, forming a feature map U. Indicates that the global pooling is reduced to a one-dimensional vector, The gate mechanism consists of two fully connected layers. The first fully connected layer compresses C channels into C / r channels to reduce the amount of computation. Then, a RELU nonlinear activation layer is used. The second fully connected layer restores the number of channels to C channels. The weight s is obtained through Sigmoid activation. The dimension of the final s is 1×1×C, which is used to characterize the weights of the C feature maps in the feature map U. The attention weights obtained previously are weighted to the features of each channel; the next layer consists of a convolutional layer, a ConvNeXt Block, a Downsample, a local pooling layer, and a fully connected layer; the activation function used in the ConvNeXt Block is GELU; the Downsample layer consists of layer normalization and a two-dimensional convolution kernel.

7. The research method according to claim 6, characterized in that In step f, the model effect needs to be evaluated. First, a confusion matrix is ​​constructed for the classification effect of each acupoint category i, and the true positive TP, false positive FP, false negative FN and true negative TN values ​​of each category are counted. Then, the overall precision is calculated based on these values. The calculation formula is: The effectiveness of the model is judged by calculating the overall accuracy. The closer the value is to 1, the more it indicates that the model has the effect of predicting acupoints through EEG characteristics; vice versa.

Images