SFE-Net: EEG-based Emotion Recognition with Symmetrical Spatial Feature Extraction

TL;DR

This paper introduces SFE-Net, a novel EEG-based emotion recognition method that leverages symmetrical spatial features and improved interpolation to enhance accuracy and robustness in emotion detection.

Contribution

The paper proposes a new neural network architecture that incorporates symmetrical folding strategies and improved EEG channel data completion for better emotion recognition.

Findings

Achieved comparable accuracy on DEAP and SEED datasets.

Enhanced robustness and spatial feature extraction in EEG-based emotion recognition.

Utilized multi-voting ensemble learning to improve model stability.

Abstract

Emotion recognition based on EEG (electroencephalography) has been widely used in human-computer interaction, distance education and health care. However, the conventional methods ignore the adjacent and symmetrical characteristics of EEG signals, which also contain salient information related to emotion. In this paper, a spatial folding ensemble network (SFE-Net) is presented for EEG feature extraction and emotion recognition. Firstly, for the undetected area between EEG electrodes, an improved Bicubic-EEG interpolation algorithm is developed for EEG channels information completion, which allows us to extract a wider range of adjacent space features. Then, motivated by the spatial symmetric mechanism of human brain, we fold the input EEG channels data with five different symmetrical strategies, which enable the proposed network to extract the information of space features of EEG signals more effectively. Finally, a 3DCNN-based spatial, temporal extraction, and a multi-voting strategy of ensemble learning are integrated to model a new neural network. With this network, the spatial features of different symmetric folding signals can be extracted simultaneously, which greatly improves the robustness and accuracy of emotion recognition. The experimental results on DEAP and SEED datasets show that the proposed algorithm has comparable performance in terms of recognition accuracy.