RETRACTED: Emotion Recognition from EEG Based on Bayesian Networks (Retracted Article)

In this paper, we propose a recognition model of multi-emotion states from electroencephalogram (EEG) based on Bayesian Networks. The subjects' emotion states (anger, happiness, and neutral) are elicited by using emotional videos along with collecting EEG signals from fourteen channels around the scalp. We use Receiver Operating Characteristic (ROC) to select input features of this model from power spectrum values of fifty six frequency bands of fourteen-channel EEG signals with each being divided into four bands. Experimental results show that the proposed model performs well and using EEG to detect multi-emotion states is feasible. (C) 2011 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of the Organizers of 2011 International Conference on Energy and Environmental Science.