Individual Emotion Classification between Happiness and Sadness by Analyzing Photoplethysmography and Skin Temperature

Since emotion technology has been applied into numerous applications, the role of recognizing human emotion has become more important. In this paper, two autonomic nervous signals such as SKT and PPG were analyzed in order to extract 2D emotional feature vector (PPI and SKT amplitude) for classification between happy and sad emotions. A support vector machine was adopted for non-linear classification between happiness and sadness. We collected SKT and PPG signals from 5 undergraduates who respectively watched two different kinds of video inducing happiness and sadness. At result, the classification accuracy of 92.41% was obtained by combining two features through using support vector machine which was even more increased result compared with the results using single feature such as SKT (89.29%) and PPG (63.67%).