Transformer-based ensemble deep learning model for EEG-based emotion recognition

Emotion recognition is one of the most important research directions in field brain–computer interface (BCI). However, to conduct electroencephalogram (EEG)-based emotion recognition, there exist difficulties regarding EEG signal processing; moreover, performance classification models this regard restricted. To counter these issues, 2022 World Robot Contest successfully held an affective BCI competition, thus promoting innovation EEG-based recognition. In paper, we propose Transformer-based ensemble (TBEM) deep learning model. TBEM comprises two models: a pure convolutional neural network (CNN) model and cascaded CNN-Transformer hybrid The proposed won abovementioned competition’s final championship Contest, demonstrating effectiveness for