Residual GCB-Net: Residual Graph Convolutional Broad Network on Emotion Recognition

Electroencephalogram (EEG) data are commonly applied in the emotion recognition research area. It can accurately reflect the emotional changes of the human body by applying graphical-based algorithms or models. EEG signals are nonlinear signals. Biological tissues' adjustment and adaptive ability will inevitably affect electrophysiological signals, making EEG have the typical nonlinear characteristics. The graph convolutional broad network (GCB-net) extracted features from nonlinear signals and abstract features via a stacked convolutional neural network. It adopted the broad concept and enhanced the feature by the broad learning system (BLS), obtaining sound results. However, it performed poorly with the increasing network depth, and the accuracy of some features decreased with BLS. This article proposed a residual graph convolutional broad network (Residual GCB-net), which promotes the performance on a deeper layer network and extracts higher level information. It substitutes the original convolutional layer with residual learning blocks, which solves the deep learning network degradation and extracts more features in deeper networks. In the SJTU emotion EEG data set (SEED), GCB-Res net could obtain the best accuracy (94.56%) on the all-frequency band of differential entropy (DE) and promote much on another feature. In Dreamer, it obtained the best accuracy (91.55%) on the dimension of Arousal. The result demonstrated the excellent classification performance of Residual GCB-net in EEG emotion recognition.