EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TCPL: task-conditioned prompt learning for few-shot cross-subject motor imagery EEG decoding

Pengpai Wang, Tiantian Xie, Yueying Zhou, Peiliang Gong, Rosa H M Chan

Frontiers in Neuroscience · 24.11.2025 · 19

DOI: 10.3389/fnins.2025.1689286 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Neuroscience, online erschienen am 24.11.2025. Verfasst von Pengpai Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer and Information Engineering, Nanjing Tech University, Nanjing, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motor imagery (MI) electroencephalogram (EEG) decoding plays a critical role in brain–computer interfaces but remains challenging due to large inter-subject variability and limited training data. Existing approaches often struggle with few-shot cross-subject adaptation, as they require either extensive fine-tuning or fail to capture individualized neural dynamics. To address this issue, we propose a Task-Conditioned Prompt Learning (TCPL), which integrates a Task-Conditioned Prompt (TCP) module with a hybrid Temporal Convolutional Network (TCN) and Transformer backbone under a meta-learning framework. Specifically, TCP encodes subject-specific variability as prompt tokens, TCN extracts local temporal patterns, Transformer captures global dependencies, and meta-learning enables rapid adaptation with minimal samples. The proposed TCPL model is validated on three widely used public datasets, GigaScience, Physionet, and BCI Competition IV 2a, demonstrating strong generalization and efficient adaptation across unseen subjects. These results highlight the feasibility of TCPL for practical few-shot EEG decoding and its potential to advance the development of personalized brain–computer interface systems.

Schlagwörter

Stichwörter der Autor:innen

EEG decodingfew-shot learningmeta-learningmotor imagerytask-conditioned prompttransformer

Autor:innen und Institutionen

  • College of Computer and Information Engineering, Nanjing Tech University, Nanjing, China.
  • City University of Hong Kong Shenzhen Research Institute, Shenzhen, China.
  • State Key Laboratory of Terahertz and Millimeter Waves, City University of Hong Kong, Hong Kong, China.
  • Department of Electrical Engineering, City University of Hong Kong, Hong Kong, China.
  • School of Mathematics Science, Liaocheng University, Liaocheng, China.
  • College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, China.

Zitieren

APA

Wang, P., Xie, T., Zhou, Y., Gong, P., & Chan, R. H. M. (2025). TCPL: task-conditioned prompt learning for few-shot cross-subject motor imagery EEG decoding. Frontiers in Neuroscience, 19. https://doi.org/10.3389/fnins.2025.1689286

Vancouver

Wang P, Xie T, Zhou Y, Gong P, Chan RHM. TCPL: task-conditioned prompt learning for few-shot cross-subject motor imagery EEG decoding. Frontiers in Neuroscience. 2025;19. doi:10.3389/fnins.2025.1689286

BibTeX
@article{Wang2025,
  author = {Wang, Pengpai and Xie, Tiantian and Zhou, Yueying and Gong, Peiliang and Chan, Rosa H M},
  title = {TCPL: task-conditioned prompt learning for few-shot cross-subject motor imagery EEG decoding},
  journal = {Frontiers in Neuroscience},
  year = {2025},
  volume = {19},
  doi = {10.3389/fnins.2025.1689286}
}
Kostenlos starten →