Decision fusion for EEG-based emotion recognition

The emotion recognition using the electroencephalogram (EEG) receives a lot of attentions in recent years. Various features extracted from different angles are proposed. In this paper, we propose an EEG-based emotion recognition framework based on the weighted fusion of outputs from base classifiers. Threebase classifiers based on the SVM with RBF kernel using Power Spectral, Higuchi Fractal Dimension and Lempel-Ziv Complexity features are developed, respectively. The outputs of base classifiers are integrated by the weighted fusion strategy which is based on the confidence estimation on each class by each base classifier. The evaluation on the DEAP dataset shows that our proposed decision fusion based method outperforms individual base classifiers and the feature fusion based classifier integration for EEG-based emotion recognition.