Comparison of cross-subject EEG emotion recognition algorithms in the BCI Controlled Robot Contest in World Robot Contest 2021. Issue 2 (June 2022)

• Record Type: Journal Article
• Authors: Tang, Chao; Li, Yunhuan; Chen, Badong
• Is Part Of: Brain science advances. Volume 8:Issue 2(2022)
• Page Start: 142
• Page End: 152
• Publication Date: 2022-06
• Subjects: electroencephalography -- emotion recognition -- online decoding -- cross-subject -- brain–computer interface; Neurosciences -- Periodicals; Medical innovations -- Periodicals; Medical innovations; Neurosciences; Periodicals; 616.8005
• DOI: 10.26599/BSA.2022.9050013
• Languages: English
• ISSNs: 2096-5958

Abstract

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