Weight-sharing network structure based on multi-channel EEG time-frequency map

Abstract

The brain-computer interface technology enables the disabled to control external devices through the motor imagery EEG. Due to the complex changes of EEG in the time domain and frequency domain, classifiers play an important role in EEG recognition. Convolutional neural network is an excellent deep learning method, but most papers usually use one-dimensional convolution to identify EEG. In this article, the time–frequency graphs of different EEG channels are superimposed by referring to the color dimension of the picture. A weighted shared two-dimensional convolutional CNN-LSTM network is proposed, which shares convolution kernels for feature maps of different channels. Performance of the put forward method has been estimated in the BCI competition IV dataset 2b and High Gamma Dataset. Compared with CNN and CNN-LSTM, the WS-CNN-LSTM reduces the amount of calculation, speeds up the network training and improves the classification performance, the highest accuracy rate is 82.3%. This paper also proposes a data enhancement method of randomly superimposed EEG and features, which effectively improves the classification performance.