CN-116738316-B - Electroencephalogram classification method for unilateral limb motor imagery tasks

CN116738316BCN 116738316 BCN116738316 BCN 116738316BCN-116738316-B

Abstract

The invention discloses a single-side limb motor imagery task electroencephalogram classification method which sequentially comprises the following steps of A, constructing a single-side limb motor imagery data set, preprocessing to obtain motor imagery electroencephalograms, B, carrying out feature extraction and classification on the motor imagery electroencephalograms by using a deep neural network model to obtain a probability distribution matrix of the electroencephalograms, C, processing the motor imagery electroencephalograms by using a CSP method to obtain a time-frequency diagram data set, carrying out feature extraction and classification on the time-frequency diagram data set by using the deep neural network model to obtain a probability distribution matrix of the time-frequency diagram signals, D, calculating an average clustering coefficient, optimizing the two probability distribution matrices, and carrying out fusion decision by using the two optimized probability distribution matrices based on a D-S evidence theory to obtain a final classification result. The invention can effectively improve the classification accuracy of unilateral limb movement information tasks and provides a data basis for the development of brain-computer interface technology.

Inventors

ZHANG RUI
CHEN YADI
ZHANG LIPENG
HU YUXIA

Assignees

郑州大学

Dates

Publication Date: 20260512
Application Date: 20230617
Priority Date: 20230206

Claims (9)

1. The electroencephalogram classification method for the unilateral limb motor imagery task is characterized by comprising the following steps in sequence: A, constructing a single-side limb motor imagery data set, and preprocessing data of motor imagery electroencephalogram signals in the single-side limb motor imagery data set to obtain preprocessed motor imagery electroencephalogram signals; B, extracting and classifying characteristics of the preprocessed motor imagery electroencephalogram signals obtained in the step A by using a deep neural network model to obtain a probability distribution matrix of the electroencephalogram signals Probability distribution matrix The probability that the preprocessed motor imagery electroencephalogram signal belongs to the corresponding action category is included; c, performing spatial filtering on the preprocessed motor imagery electroencephalogram signal obtained in the step A by using a CSP method to obtain a feature matrix of the electroencephalogram signal, then obtaining a time-frequency diagram data set by selecting the feature matrix and performing continuous wavelet transformation, and finally performing feature extraction and classification on the time-frequency diagram data set by using a deep neural network model to obtain a probability distribution matrix of the time-frequency diagram signal Probability distribution matrix The time-frequency diagram signal comprises the probability of belonging to the corresponding action category; D, utilizing the probability distribution matrix of the EEG signals obtained in the step B And the probability distribution matrix of the time-frequency diagram signals obtained in the step C Respectively calculating the clustering coefficient of each action category, and according to the average clustering coefficient pair probability distribution matrix obtained by calculation And Optimizing to obtain an optimized probability distribution matrix And Based on D-S evidence theory and using probability distribution matrix And Performing fusion decision to obtain a final classification result; Wherein, the step D comprises the following specific steps: d1 based on probability distribution matrix And The probability of each action category contained in the two probability distribution matrixes is calculated respectively, and the clustering coefficient of each action category data in the two probability distribution matrixes is calculated Obtaining average clustering coefficients by averaging the clustering coefficients of all nodes of the motion class data ; Wherein, the ; Representing the number of neighbors of the node; representing the number of interconnected edges between all adjacent nodes of a node; d2, the probability distribution matrix to be obtained And Taking the average cluster coefficient of (2) as a weight value, re-optimizing the two probability distribution matrixes to obtain an optimized probability distribution matrix And ; = , * = ; D3, optimizing probability distribution matrix by D-S fusion rule And Performing fusion decision to obtain a new probability distribution matrix P, and accordingly obtaining a final classification result; ; where k is the evidence conflict factor, A, B and C represent a probability distribution matrix P, And Is a three-way action category.
2. The method of claim 1, wherein in the step A, the data preprocessing includes bandpass filtering, downsampling, channel selection, independent component analysis and artifact removal, and data selection of motor imagery electroencephalogram signals.
3. The method of classifying motor imagery task brain waves of a single-sided limb according to claim 1, wherein in the step A, only motor imagery brain waves under three actions of stretching arms forwards, rotating wrists leftwards and grabbing a water cup are selected from the motor imagery data set of the single-sided limb; In the step B of the process, , wherein, The probability that the sample results belong to the corresponding action categories in the electroencephalogram signal three-classification experiment is respectively; in the step C, the step of, in the step C, , wherein, And the probabilities that the sample results belong to the corresponding action categories in the time-frequency diagram three-classification experiment are respectively.
4. The method for classifying the brain waves of the motor imagery task of a single-sided limb according to claim 1, wherein the step C comprises the following specific steps: C1, performing spatial filtering on the preprocessed motor imagery electroencephalogram by using a CSP algorithm; when spatial filtering is performed, a CSP projection matrix is obtained by calculation Followed by projection matrix using CSP And the preprocessed motor imagery electroencephalogram signals obtained in the step A are calculated to obtain a feature matrix The calculation formula is as follows: Wherein, the method comprises the steps of, In the form of a CSP projection matrix, For the number of channels of the preprocessed electroencephalogram data, For the length of the data to be the same, The size formed by converting the preprocessed motor imagery electroencephalogram signals is Is a brain electrical data matrix; C2, selecting a feature matrix extracted from CSP features ; C3, according to the feature matrix obtained in the step C2 Performing time-frequency feature extraction by using a CWT algorithm, converting the time-frequency feature extraction into a two-dimensional time-frequency diagram, selecting Morlet wavelets as a basis function to perform wavelet transformation, and finally obtaining a motor imagery time-frequency diagram data set; the formula of the wavelet transform is as follows: ; ; ; The Morlet is a basis function commonly used in wavelet transformation and is used for carrying out decomposition operation on signals to be processed in the wavelet transformation process; Represents a basis function, ω represents a wavelet center frequency, t represents time, i represents a time-varying sequence; represents the basis function after the scale transformation and the translation transformation, alpha represents the scale transformation factor, beta represents the time translation factor, Representing the result after performing a wavelet transform on the signal, Representing an electroencephalogram signal; C4, according to the acquired motor imagery time-frequency diagram data set, performing feature extraction and classification in an image processing mode by using a convolutional neural network to obtain a probability distribution matrix of time-frequency diagram signals , , And the probabilities that the sample results belong to the corresponding action categories in the time-frequency diagram three-classification experiment are respectively.
5. The method for classifying brain waves of a unilateral limb motor imagery task according to claim 4, wherein in the step C2, a feature matrix is selected The first m rows and the last m rows of the data are used as feature matrixes for CSP feature extraction Wherein 2m < 。
6. The single-side limb motor imagery task electroencephalogram classification method according to claim 2 is characterized by comprising the steps of selecting a 4-order Butterworth band-pass filter to conduct 8-30 Hz filtering processing on original electroencephalogram data to obtain a frequency band of electroencephalogram related to movement, downsampling the electroencephalogram to 250 Hz when downsampling is conducted, selecting 20 EEG channels of a cerebral sensorimotor cortex to classify when channel selection is conducted, and conducting ICA calculation and artifact removal on the electroencephalogram by using EEGLAB when independent component analysis and artifact removal are conducted.
7. The method for classifying the brain waves of the single-sided limb motor imagery task according to claim 1, wherein in the step B, the used convolutional neural network structure is EEG-CNN and comprises a convolutional layer, a pooling layer and a full-connection layer, wherein the two convolutional layers and the maximum pooling layer form a feature extraction module, and a one-dimensional convolutional kernel in the convolutional layer is used for extracting features of each channel as a feature map output by the layer.
8. The method for classifying the brain waves of the motor imagery task of the unilateral limb according to claim 1, wherein in the step C, the convolutional neural network structure is TF-CNN, and VGG16 is adopted as a basic network frame to extract characteristic information of the time-frequency diagram.
9. The method for classifying brain waves of a unilateral limb motor imagery task according to claim 1, wherein the convolutional neural network in the step B and the step C is used in training , The Adam optimizer of (c) updates the trainable parameters of each network layer with an initial learning rate set to 0.01.

Description

Electroencephalogram classification method for unilateral limb motor imagery tasks Technical Field The invention relates to the technical field of biological signal recognition, in particular to a single-side limb motor imagery task electroencephalogram classification method based on multi-mode information fusion. Background The brain-computer interface (BCI) constructs an information interaction channel between the human brain and the external environment, and can directly read and analyze the electrical signals generated by the brain to identify the intention of a user, and the brain electrical signals are used for realizing the interaction between the human and the external equipment, and the core technology is the identification of the brain electrical signals. Motor imagery tasks (MI) are psychological processes that simulate movement without actual movement, i.e. the brain imagines the whole movement without actually contracting the muscles. In the neurophysiologic field, there are many similarities between the true actions of peripheral autonomic nerves and cortical potentials and moving images. MI, an important model of spontaneous BCI, has been widely used in the field of nerve rehabilitation to provide rehabilitation and motor assistance for disabled patients suffering from dyskinesia, such as patients suffering from brain stem injury, stroke, muscle atrophy, who possess a complete brain but cannot communicate with the outside because of peripheral nerve injury. Although the MI-BCI system cannot repair the physiological nerve transmission channel of the system, the brain consciousness can be transmitted to a controlled device for control. In the research of the current motor imagery tasks, the movements of different parts of the body are often involved, the brain electrical signals generated by motor imagery of different parts of the body are identified, but compared with the motor imagery tasks among different parts of the body, the combination of the motor imagery tasks of limbs at the same part and the movements of the corresponding parts of the body can be more natural and visual, for example, in the arm rehabilitation training combined with the rehabilitation robot, the robot executes the same movements to perform the rehabilitation training after imagining the different movements of the arm, thereby being more beneficial to training and rehabilitation and being more suitable for clinical application scenes. However, classification and identification of individual limbs is more difficult and complex than identification between different parts of the body, because the brain motor cortex areas activated when the same body part performs a motor task are very similar, which brings greater difficulty to research of decoding and identification, and therefore an effective feature extraction method is very important in the classification process. The process of classifying and identifying the electroencephalogram signals comprises preprocessing of the electroencephalogram signals, feature extraction and feature classification, and in the process, effective feature extraction and a proper feature classifier are key for determining the identity recognition performance. In the process of extracting features of an electroencephalogram signal, representative feature extraction methods can be divided into time domain analysis (including amplitude, mean value and the like), frequency domain analysis (including power spectrum analysis, coherent analysis and the like), time-frequency domain analysis (including wavelet transformation, empirical mode decomposition and the like) and airspace analysis (including co-airspace mode method, independent component analysis and the like), and in order to improve accuracy of biological feature recognition, some researches combine different feature extraction methods to extract multidimensional features of an EEG signal so as to characterize the EEG from multiple domains. In the process of classifying the characteristics of the electroencephalogram signals, the deep learning method directly takes the original signals as the input of the model to carry out end-to-end training, and the characteristics of the signals do not need to be extracted any more, so that the current application is very wide. Convolutional neural networks and recurrent neural networks are commonly used as methods for biometric identification due to the temporal, frequency and spatial properties of EEG signals. At present, a deep learning algorithm is increasingly applied to a classification task of an electroencephalogram signal, in the existing motor imagery electroencephalogram signal identification, an original electroencephalogram signal or a transformed electroencephalogram frequency domain feature and the like are generally used for classification identification, and a simple deep learning model can be utilized to obtain better performance, so that the deep learning algorithm is paid more attent