OGSSL: A Semi-Supervised Classification Model Coupled With Optimal Graph Learning for EEG Emotion Recognition

Electroencephalogram (EEG) signals are generated from central nervous system which are difficult to disguise, leading to its popularity in emotion recognition. Recently, semi-supervised learning exhibits promising emotion recognition performance by involving unlabeled EEG data into model training. However, if we first build a graph to characterize the sample similarities and then perform label propagation on this graph, these two steps cannot well collaborate with each other. In this paper, we propose an Optimal Graph coupled Semi-Supervised Learning (OGSSL) model for EEG emotion recognition by unifying the adaptive graph learning and emotion recognition into a single objective. Besides, we improve the label indicator matrix of unlabeled samples in order to directly obtain their emotional states. Moreover, the key EEG frequency bands and brain regions in emotion expression are automatically recognized by the projection matrix of OGSSL. Experimental results on the SEED-IV data set demonstrate that 1) OGSSL achieves excellent average accuracies of 76.51%, 77.08% and 81.29% in three cross-session emotion recognition tasks, 2) OGSSL is competent for discriminative EEG feature selection in emotion recognition, and 3) the Gamma frequency band, the left/right temporal, prefrontal, and (central) parietal lobes are identified to be more correlated with the occurrence of emotions.