DSP-MCF: dual stream pre-training and multi-view consistency fine-tuning for cross-subject EEG emotion recognition
The findings indicate that the DSP-MCF framework effectively addresses individual variability and maintains robust performance even under channel loss. By integrating spatiotemporal reconstruction with multi-view consistency, the model provides a reliable solution for handling incomplete or degraded EEG signals in practical BCI applications.
Authors
- Xin Huang (ORCID: https://orcid.org/0000-0002-2313-8104)
- Xiong Liu (ORCID: https://orcid.org/0000-0003-2939-574X)
- Wang Ya (ORCID: https://orcid.org/0009-0008-2900-2807)
- Jinɡjinɡ Li (ORCID: https://orcid.org/0000-0002-7526-5308)
- Xia Wu
Institutions
- Guiyang College of Traditional Chinese Medicine (CN)
- Guizhou University (CN)
- Nanyang Normal University (CN)
Publication Details
- Journal
- Frontiers in Human Neuroscience
- Published
- 2026-02-18
- DOI
- https://doi.org/10.3389/fnhum.2026.1723907
- Primary Topic
- Emotion and Mood Recognition
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Ministry of Education of the People's Republic of China
- Nanyang Normal University
- Humanities and Social Sciences Youth Foundation, Ministry of Education of the People's Republic of China