A novel approach of emotion recognition based on selective ensemble

摘要

Emotion recognition is an important module in affective computing. It is usually studied based on facial and audio information with methodologies such as ANN, fuzzy set, SVM, HMM, etc. In this paper, a novel approach based on selective ensemble is proposed for emotion recognition. Simulation experiments prove that the proposed method has better performance than the method of single classifier, even better than bagging. In the end, further research works is discussed.