Multi-source Selective Graph Domain Adaptation Network for cross-subject EEG emotion recognition

• Published in: Neural networks Vol. 180; p. 106742
• Main Authors: Wang, Jing, Ning, Xiaojun, Xu, Wei, Li, Yunze, Jia, Ziyu, Lin, Youfang
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.12.2024
• Subjects: Brain - physiology; Brain-Computer Interfaces; Domain adaptation; Domain selection; Electroencephalogram (EEG); Electroencephalography - methods; Emotion recognition; Emotions - physiology; Graph neural network; Humans; Neural Networks, Computer; Domain adaptation; Emotion recognition; Electroencephalogram (EEG); Graph neural network; Domain selection
• ISSN: 0893-6080; 1879-2782; 1879-2782
• DOI: 10.1016/j.neunet.2024.106742

Affective brain-computer interface is an important part of realizing emotional human–computer interaction. However, existing objective individual differences among subjects significantly hinder the application of electroencephalography (EEG) emotion recognition. Existing methods still lack the complete extraction of subject-invariant representations for EEG and the ability to fuse valuable information from multiple subjects to facilitate the emotion recognition of the target subject. To address the above challenges, we propose a Multi-source Selective Graph Domain Adaptation Network (MSGDAN), which can better utilize data from different source subjects and perform more robust emotion recognition on the target subject. The proposed network extracts and selects the individual information specific to each subject, where public information refers to subject-invariant components from multi-source subjects. Moreover, the graph domain adaptation network captures both functional connectivity and regional states of the brain via a dynamic graph network and then integrates graph domain adaptation to ensure the invariance of both functional connectivity and regional states. To evaluate our method, we conduct cross-subject emotion recognition experiments on the SEED, SEED-IV, and DEAP datasets. The results demonstrate that the MSGDAN has superior classification performance. [Display omitted] •A novel selective domain adaption framework for cross-subject EEG emotion recognition.•Simultaneously considering functional connectivity and features in domain adaptation.•Adaptively select the most valuable source domain with the target domain for transfer.