Enhancing EEG-based emotion recognition using PSD-Grouped Deep Echo State Network

Emotions are a crucial aspect of daily life and play a vital role in shaping human inter-actions. The purpose of this paper is to introduce a novel approach to recognize human emotions through the use of electroencephalogram (EEG) signals. To recognize these signals for emotion prediction, we employ a paradigm of Reservoir Computing (RC), called Echo State Network (ESN). In our analysis, we focus on two specific classes of emotion recognition: H/L Arousal and H/L Valence. We suggest using the Deep ESN model in conjunction with the Welch Power Spectral Density (Wlech PSD) method for emotion classification and feature extraction. Furthermore, we feed the selected features to a grouped ESN for recognizing emotions. Our approach is validated on the well-known DEAP benchmark, which includes the EEG data from 32 participants. The proposed model achieved 89.32% accuracy for H/L Arousal and 91.21% accuracy for H/L Valence on the DEAP dataset. The obtained results demonstrate the effectiveness of our approach, which yields good performance compared to existing models of emotion analysis based on EEG.

Automated summary

This paper introduces a novel approach to recognize human emotions using electroencephalogram (EEG) signals, employing Echo State Network (ESN) in the paradigm of Reservoir Computing (RC) for emotion prediction. The study focuses on two specific classes of emotion recognition: H/L Arousal and H/L Valence, and suggests using Deep ESN model and Welch Power Spectral Density (Wlech PSD) method for emotion classification and feature extraction. The approach is validated on the well-known DEAP benchmark, achieving an accuracy of 89.32% for H/L Arousal and 91.21% for H/L Valence.