Combined analysis of GSR and EEG signals for emotion recognition

Abstract

An article presents the results of research related to the detection of emotions using combined analysis of galvanic skin response (GSR) and electroencephalographic (EEG) signals. Twenty seven volunteers participated in the experiment. Emotions were evoked by presentation of a set of twenty one movies. Emotions, evoked by individual movies, were later rated by participants according to valence and arousal. GSR signal was used to indicate the most stimulating movies, then features extracted from EEG signal were used to classify emotions. To determine the features EEG signal was analyzed in the frequency domain using fast Fourier transform (FFT) algorithm. For classifying emotions, according to valence and arousal, two classifiers were implemented: support vector machine (SVM) and k-nearest neighbors (k-NN).