Emotion detection using brain and peripheral signals

An emotion recognition system on the basis of physiological signals is proposed in this paper. The aim is to perform a multimodal fusion between electroencephalographic signals of the brain (EEG) and peripheral physiological signals. our acquisition protocol is based on a subset of pictures which correspond to three specific areas of valance-arousal emotional space (positively excited, negatively excited, and calm). Preprocessing and feature extraction methods have been set up in such away that emotion-specific characteristics can be extracted from input signals. The performance of two classifiers has been evaluated on different feature sets: peripheral signals, EEG´s, and both. A comparison among the results of different feature sets confirms the interest of using brain signals as peripherals in emotion assessment.