Using GA-based feature selection for emotion recognition from physiological signals

Emotion awareness is becoming an increasingly important field for human-computer interaction. Compare to audio-visual techniques, relying on physiological signals reveals a few advantages that inspired several research studies. By using various feature selection and classification algorithms, development on physiological signals based emotion recognition has been gradually broadened. This paper employed GA-based feature set searching algorithm combining with four classification methods for physiological signal based emotion recognition. GA is an optimization tool which has been proven to be quite effective for large-scale feature selection. The results in this paper will support a successful application of using GA-based feature selection.