Multi-source domain adaptation for EEG emotion recognition based on inter-domain sample hybridization
Our proposed method aims to alleviate the difficulties of emotion recognition from the limited generalization ability of EEG features across subjects and sessions. Though adapting the multi-source domain adaptation and the sample hybridization method, the proposed method can effectively transfer the emotion-related knowledge of known subjects and achieve accurate emotion recognition on unlabeled subjects.
Authors
- Xu Wu (ORCID: https://orcid.org/0000-0002-6828-1967)
- Xiangyu Ju (ORCID: https://orcid.org/0009-0004-9028-2554)
- Sheng Dai (ORCID: https://orcid.org/0009-0008-8952-4017)
- Ming Li (ORCID: https://orcid.org/0000-0002-6406-1983)
- Xinyu Li (ORCID: https://orcid.org/0000-0002-1919-2327)
Institutions
- National University of Defense Technology (CN)
Publication Details
- Journal
- Frontiers in Human Neuroscience
- Published
- 2024-10-31
- DOI
- https://doi.org/10.3389/fnhum.2024.1464431
- Citations
- 9
- Primary Topic
- Emotion and Mood Recognition
- Type
- article
- Field-Weighted Citation Impact
- 4.57
Funders
- National Natural Science Foundation of China