Physiological Signals-based Emotion Recognition via High-order Correlation Learning



Emotion recognition by physiological signals is an effective way to discern the inner state of human beings and therefore has been widely adopted in many user-centered applications. The majority of current state-of-the-art methods focus on exploring relationship among emotion and physiological signals. Given some particular features of the natural process of emotional expression, it is still a challenging and urgent issue to efficiently combine such high-order correlations among multimodal physiological signals and subjects. To tackle the problem, a novel multi-hypergraph neural networks is proposed, in which one hypergraph is established with one type of physiological signals to formulate inter-subject correlations. Each one of the vertices in a hypergraph stands for one subject with a description of its related stimuli, and the complex correlations among the vertices can be formulated through hyperedges. With the multi-hypergraph structure of the subjects, emotion recognition is translated into classification of vertices in the multi-hypergraph structure. Experimental results with the DEAP dataset and ASCERTAIN dataset demonstrate that the proposed method outperforms the current state-of-the-art methods.

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)