Heterogeneous transfer learning model for improving the classification performance of fNIRS signals in motor imagery among cross-subject stroke patients
The model demonstrates robust cross-subject generalization by transferring task-specific knowledge from heterogeneous EEG data while addressing domain discrepancies. Its performance gains post-rehabilitation suggest clinical potential for monitoring recovery progress. CHTLM advances MI-fNIRS-based brain-computer interfaces in stroke rehabilitation by mitigating data scarcity and variability challenges.
Authors
- Yehang Chen (ORCID: https://orcid.org/0009-0002-3724-3957)
- Qinghui Hu (ORCID: https://orcid.org/0000-0002-0372-443X)
- Xinbing Wang (ORCID: https://orcid.org/0000-0002-0357-8356)
- SenLiang Lu
- Yi Li (ORCID: https://orcid.org/0000-0003-3259-3026)
- Yong Fan (ORCID: https://orcid.org/0000-0003-4813-7017)
- Feng Jin (ORCID: https://orcid.org/0000-0002-6594-9351)
- R. Lily Hu
- Yu‐Ting Chen (ORCID: https://orcid.org/0000-0001-9525-8407)
- Zijun Huang (ORCID: https://orcid.org/0000-0002-6038-4320)
- Jing He (ORCID: https://orcid.org/0000-0002-4819-0136)
Institutions
- Guilin University of Aerospace Technology (CN)
- Jiangmen Central Hospital (CN)
- Nanxi Mountain Hospital (CN)
- Guilin University of Electronic Technology (CN)
Publication Details
- Journal
- Frontiers in Human Neuroscience
- Published
- 2025-03-27
- DOI
- https://doi.org/10.3389/fnhum.2025.1555690
- Primary Topic
- EEG and Brain-Computer Interfaces
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China