Minimal Electrode EEG for BCI Emotion Detection

Electroencephalography (EEG)-based emotion recognition is a potential research direction in the field of brain-computer interfaces (BCIs). However, its deployment on wearable devices still suffers from the challenges of low accuracy, heavy computation, and complex electrode placement. This study focuses on advancing the efficiency and cost-effectiveness of EEG-based BCIs for emotion recognition. Our approach begins with an investigation of electrode placement in relation to emotion detection, leveraging the SEED dataset to identify an optimal configuration that uses a minimal number of electrodes while maintaining high recognition accuracy. Employing a variety of machine learning and deep learning algorithms, we compare detection accuracy across different electrode combinations. Through these experiments and subsequent analysis, we identify an effective combination of two electrodes, T7 and T8, with the SVM method achieving an impressive 92.8 % accuracy. This finding laid the foundation for the design of our wearable, closed-loop BCI device with EEG-based emotion recognition capability.