Emotional Stress Recognition System Using EEG and Psychophysiological Signals: Using New Labelling Process of EEG Signals in Emotional Stress State

This paper proposes a new emotional stress recognition system using multi-modal bio-signals. Since electroencephalogram (EEG) is the reflection of brain activity and is widely used in clinical diagnosis and biomedical research, it is used as the main signal. In order to choose the proper EEG channels we used the cognitive model of the brain under emotional stress. We designed an efficient acquisition protocol to acquire the EEG and psychophysiological signals under pictures induction environment (calm-neutral and negative-excited) for participants. Qualitative and quantitative evaluation of psychophysiological signals have been tried to select suitable segments of EEG signal for improving efficiency and performance of emotional stress recognition system. After pre-processing the signals, both Linear and nonlinear features were employed to extract the EEG parameters. Wavelet coefficients and chaotic invariants like fractal dimension by Higuchi´s algorithm and correlation dimension were used to extract the characteristics of the EEG signal which showed that the classification accuracy in two emotional states was 82.7% using the Elman classifier. This is a great improvement in results compared with other similar published work.