Physiological Angry Emotion Detection Using Support Vector Regression

Physical and mental diseases caused by stress and negative emotions have increased in recent years. Emotion can be roughly recognized by facial expressions. However, facial expressions may be controlled and expressed differently by different people subjectively, inaccurate results are unavoidable. On the contrary, physiological responses and the corresponding signals are hardly to control while emotions are excited. Therefore, a physiological angry emotion detection method is proposed in this paper. A specific designed emotion induction experiment is performed to collect four physiological signals of subjects including electrocardiogram, galvanic skin responses (GSR), blood volume pulse, and pulse. The Support Vector Regression (SVR) is used to train the trend curves of angry emotion. Experimental results show that the proposed method achieves high recognition rate.