Higher Order Spectra Analysis of EEG Signals in Emotional Stress States

Abstract

This paper proposes an emotional stress recognition system with EEG signals using higher order spectra (HOS). A visual induction based acquisition protocol is designed for recording the EEG signals in five channels (FP1, FP2, T3, T4 and Pz) under two emotional stress states of participants, Calm neutral and Negatively exited. After pre-processing the signals, higher order spectra are employed to extract the features for classifying human emotions. We used Genetic Algorithm for optimum features selection for the classifier. Using the SVM classifier, our study achieved an average accuracy of 82% for the two-abovementioned emotional stress states. We concluded that HOS analysis could be an accurate tool in the assessment of human emotional stress states. We achieved to same results compared to our previous studies.