Human Emotion Estimation from EEG and Face Using Statistical Features and SVM

摘要

An approach is presented in this paper for automated estimation of human emotions fromcombination of multimodal data: electroencephalogram and facial images. The used EEGfeatures are the Hjorth parameters calculated for theta, alpha, beta and gamma bands takenfrom pre-defined channels. For face emotion estimation PCA feature are selected. Classificationis performed with support vector machines. Since the human emotions are modelled ascombinations from physiological elements such as arousal, valence, dominance, liking, etc.,these quantities are the classifier’s outputs. The best achieved correct classificationperformance for EEG is about 76%. Classifier combination is used to return the final score forthe particular subject.