Graph Convolutional Neural Network with Multi-Scale Attention Mechanism for EEG-Based Motion Imagery Classification

Recently, deep learning has been widely used in the classification of EEG signals and achieved satisfactory results. However, the correlation between EEG electrodes is rarely considered, which has been proved that there are indeed connections between different brain regions. After considering the connections between EEG electrodes, the graph convolutional neural network is applied to detect human motor intents from EEG signals, where EEG data are transformed into graph data through phase lag index, time-domain and frequency-domain features with different signal bands. Meanwhile, a multi-scale attention mechanism is proposed to the network to improve the accuracy of classification. By using the multi-scale attention-based graph convolutional neural network, the accuracy of 93.22% is achieved with 10-fold cross-validation, which is higher than the compared methods which ignore the spatial correlations of EEG signals.