JPBS

Background: Emotion recognition is among the hot topics in the field of psychology and engineering. As a type of emotion, tension plays an important role in daily life. As such, tension intensity recognition (TIR) is of greatly value. Method: This study employed selected clips of a horror movie to elicit tension of different intensity levels, during which four types of bio-signals were collected from 4 participants. These signals included electroencephalogram (EEG), electrocardiogram (ECG), respiration (RSP) and electrodermal activity (EDA) signals. After that, a support vector machine (SVM) based classification was performed to differentiate fear tension levels, employing features extracted from multi-physiological signals.Results: EEG analysis showed that the power spectrum of EEG signals present monotonic changes with the increase of intensity at specific brain regions. The recognition accuracy using features from multiple physiology signals reached 83.33%. Conclusion: To our knowledge, this is among the first studies to evaluate emotion intensity levels using multiple electro-physiological signals. Our study demonstrated the feasibility and effectiveness of using these physiological features for the assessment of tension levels, providing further insights in the field of quantitative emotion studies.