Emotion Recognition Using Narrowband Spatial Features of Electroencephalography

Automatic recognition of human emotion has become an interesting topic among brain-computer interface (BCI) researchers. Emotion is one the most fundamental features a subject. With proper analysis emotion, inner state subject can be assessed directly. The brain response competently represented by electroencephalography (EEG). selection potential in EEG related to very important task for developing effective system. In this paper, discriminative computed from rhythmic components are used recognize emotional states. narrowband theta, alpha, beta, and gamma extracted multichannel signals using filter bank implementation. short-time entropy energy each components. spatial filtering been performed on entropy-energy space common pattern (CSP). Thus obtained employed states support vector machine (SVM) classifier. publicly available two datasets DEAP SEED evaluate performance proposed method. experimental results reflect that higher accuracy frequency subbands (beta gamma) than lower (theta alpha). combination all better individual subband signals. method outperforms recently developed algorithms recognition.