A multi-head residual connection GCN for EEG emotion recognition

Xiangkai Qiu, Shenglin Wang, Ruqing Wang, Yiling Zhang, Liya Huang

Abstract: Highlights•MRGCN model incorporates complex brain networks and graph neural networks (GNN) for profound EEG emotion recognition.•Use differential entropy to extract the complexity of EEG signals and to analyze the inner workings of emotion generation.•We designed a long-distance and short-distance brain network to explore complex topological characteristics.•Add residual-based architecture enhances performance and classification stability.•Visual optimal solution model was used to study connection mechanism among brain regions during production of emotions.