Abstract
BACKGROUND/OBJECTIVES: Electroencephalogram (EEG) signals, which reflect brain activity, are widely used in emotion recognition. However, the variety of EEG features presents significant challenges in identifying key features, reducing redundancy, and simplifying the computational process. METHODS: To address these challenges, this paper proposes a multi-dimensional attention-based dynamic graph convolutional neural network (AttGraph) model. The model delves into the impact of different EEG features on emotion recognition by evaluating their sensitivity to emotional changes, providing richer and more accurate feature information. RESULTS: Through the dynamic weighting of EEG features via a multi-dimensional attention convolution layer, the AttGraph method is able to precisely detect emotional changes and automatically choose the most discriminative features for emotion recognition tasks. This approach significantly improves the model's recognition accuracy and robustness. Finally, subject-independent and subject-dependent experiments were conducted on two public datasets. CONCLUSIONS: Through comparisons and analyses with existing methods, the proposed AttGraph method demonstrated outstanding performances in emotion recognition tasks, with stronger generalization ability and adaptability.