Research on genetic algorithm based on emotion recognition using physiological signals

In this paper, we first regard the discrete emotion recognition as a pattern recognition problem, the idea of combinational mode optimization is employed on emotion recognition. For collecting physiological signals in four different affective states, joy, anger, sadness, pleasure. We used a music induction method which elicits natural emotional reactions from the subject, Four-channel biosensors are used to obtain electromyogram(EMG), electrocardiogram(ECG), skinconductivit y(SC) and respiration changes. After calculating a sufficient amount of features from the raw signals, the genetic algorithm and the K-neighbor methods are tested to extract a new feature set consisting of the most significant features for improving classification performance. Finally, the numerical results show that the performance is feasible and effective. It also turned out that it was much easier to separate emotions along the arousal axis than along the valence axis.