PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 9, 2026Computer Methods in Biomechanics & Biomedical Engineering2 citations

Cross-subject motor imagery EEG signal classification based on meta-transfer learning

View Full Paper
HLHui LiJLJiayi LiuJLJiayu Li

Key Points

  • To improve motor imagery EEG classification accuracy across subjects using meta-transfer learning techniques.
  • Developed a novel CNN architecture called CMHA-Net optimized for motor imagery EEG classification.
  • Utilized depthwise separable convolution and multi-head attention mechanisms.
  • Implemented a Meta-SGD-based meta-transfer learning framework for training across different subjects.
  • Achieved classification accuracies of 81.61% and 88.15% on BCI-IV-2a and High Gamma datasets, respectively.
  • Outperformed existing models by 4-15% in accuracy, particularly in small-sample conditions.
  • Demonstrated the potential for enhanced clinical and real-world BCI applications.

Abstract

Motor imagery (MI) EEG classification, a core BCI task, faces challenges due to EEG's low signal-to-noise ratio and non-stationarity. Traditional supervised learning methods perform poorly in cross-subject and small-sample scenarios, limiting practical use. We propose CMHA-Net, a MI-EEG-optimized CNN integrating depthwise separable convolution, deep convolution and multi-head attention, combined with a Meta-SGD-based meta-transfer learning framework. Experiments on BCI-IV-2a and High Gamma datasets show 81.61% and 88.15% accuracy, outperforming existing models by 4-15% and excelling in small-sample cases, advancing clinical and real-world BCI applications.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Li et al. (2026) studied this question.

synapsesocial.com/papers/69897996f0ec2af6756e768ahttps://doi.org/10.1080/10255842.2026.2626477
Ask AI
Helpful
Bookmark
Share
View Full Paper