Motor imagery electroencephalogram signal classification method based on parallel CNN-Transform neural network

Abstract

The invention discloses a motor imagery electroencephalogram signal classification method based on a parallel CNN-Transform neural network. The motor imagery electroencephalogram signal classification method comprises the steps of S1, preprocessing motor imagery electroencephalogram signals; S2, adding noise into the preprocessed motor imagery electroencephalogram signals to expand data; S3, performing time-frequency analysis on the motor imagery electroencephalogram signals processed in the step S1 and the step S2 to generate a two-dimensional feature map containing time features, frequency features and position information; S4, constructing a CNN model, setting network parameters, and extracting frequency features and position information in the two-dimensional feature map; S5, constructing a Transform model, setting network parameters, and extracting time features in the two-dimensional feature map; and S6, connecting the features extracted in the step S4 and the step S5 in series, and inputting the features into a classifier to obtain a motor imagery classification result. Through verification on a data set BCI complex IV dataset 2b, compared with a motor imagery classification method with good performance in recent years, an experimental result shows that the motor imagery electroencephalogram signal classification method has better classification performance.

Description

technical field [0001] The invention belongs to the field of signal processing and pattern recognition, in particular to a motor imagery EEG signal classification method based on a parallel CNN-Transformer neural network. Background technique [0002] Brain-computer interface (Brain-computer Interface, BCI) controls external equipment through the conscious activity of human brain, and realizes the communication between brain and equipment. EEG signals are widely used in BCI due to their high temporal resolution, low cost, and non-invasiveness. Motor Imagery Electroencephalogram (MI EEG) is a kind of EEG signal that can be generated spontaneously without external stimulation. The characteristics of MI EEG such as nonlinearity, non-stationary, and low signal-to-noise ratio have brought great challenges to decoding. The key issues in brain information decoding are feature extraction and classification recognition. [0003] Time domain and frequency domain analysis methods ar...

AI Technical Summary

Problems solved by technology

The sequential input method adopted by RNN makes it difficult for the model to have efficient parallel computing capabilities, and it is difficult for RNN to establish global dependencies

Images