Comparison of cross-subject EEG emotion recognition algorithms in the BCI Controlled Robot Contest in World Robot Contest 2021

Electroencephalogram (EEG) data depict various emotional states and reflect brain activity. There has been increasing interest in EEG emotion recognition brain–computer interface systems (BCIs). In the World Robot Contest (WRC), BCI Controlled successfully staged an technology competition. Three types of emotions (happy, sad, neutral) are modeled using signals. this study, 5 methods employed by different teams compared. The results reveal that classical machine learning approaches deep perform similarly offline recognition, whereas better online cross-subject decoding.