SCC-MPGCN: Self-Attention Coherence Clustering Based on Multi-Pooling Graph Convolutional Network for EEG Emotion Recognition.

Researchers

Journal

Modalities

Models

Abstract

The emotion recognition with electroencephalography (EEG) has been widely studied using the deep learning methods, but the topology of EEG channels is rarely exploited completely. In this paper, we propose a self-attention coherence clustering based on multi-pooling graph convolutional network (SCC-MPGCN) model for EEG emotion recognition. locking value (PLV)The adjacency matrix is constructed based on phase- to describe the intrinsic relationship between different EEG electrodes as graph signals. The Laplacian matrix of a graph is obtained from the adjacency matrix and then is fed into the graph convolutional layers to learn the generalized features. Moreover, we propose a novel graph coarsening method called self-attention coherence clustering (SCC), using the coherence to cluster the nodes. The benefits are that the global information can be achieved from the raw data and the dimensionality of input can be reduced. Meanwhile, a multi-pooling graph convolutional network (MPGCN) block is introduced to learn the generalized emotional states features and tackle the problem of imbalanced dimensionality. The fully-connected layer and a softmax layer are adopted to drive the final prediction. We carry out the extensive experiments on DEAP dataset and the experimental results show that the proposed method has better classification results than the state-of-the-art methods with the 10-fold cross-validation. And the model achieves the emotion recognition performance with a mean accuracy of 96.37%, 97.02%, 96.72% on valence, arousal, and dominance dimension, respectively.© 2022 IOP Publishing Ltd.