Emotion Recognition of Electromyography Based on Support Vector Machine

Recently, computer scientists have realized the importance of emotions in human interactions with the environment. Psychophysiological studies of emotion have typically used static simulation to elicit emotion. In this paper an analysis of the properties of four Electromyography (EMG) signals employed in emotion recognition is presented. Experiment analyzes wavelet transform of surface Electromyography (EMG) to extract the maximum and minimum multi-scale wavelet coefficients firstly. And then we enter the two kinds of structural feature vector classifier for emotion recognition. Class separation analysis was used for determining the best physiological parameters to use for recognizing emotional states. Experimental results showed that using Support Vector Machine (SVM) for improving cluster separation the emotional patterns provided the best results.