PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 8, 2026Bioengineering3 citationsOpen Access

EEG-TriNet++: A Transformer-Guided Meta-Learning Framework for Robust and Generalizable Motor Imagery Classification

View Full Paper
ATAhmed TibermacineINIlyes NaidjiITImad Eddine Tibermacine

Key Points

  • The goal is to enhance motor imagery classification using EEG signals with improved generalization and accuracy.
  • Introduced a multi-branch deep learning model, EEG-TriNet++.
  • Incorporated convolutional encoders, bidirectional LSTMs, and a Transformer head.
  • Employed a model-agnostic meta-learning approach for user adaptation.
  • Achieved 79.1% and 78.6% accuracy in within-subject tasks.
  • Reached 72.4% and 71.3% accuracy in leave-one-subject-out settings.
  • Demonstrated efficiency and performance gains over state-of-the-art methods.

Abstract

Motor imagery (MI) classification using EEG signals is central to brain–computer interfaces but remains challenging due to low signal-to-noise ratio, non-stationarity, and high inter-subject variability. We introduce EEG-TriNet++, a multi-branch deep learning architecture that enhances both classification accuracy and cross-subject generalization. The model integrates three complementary components: convolutional spatial–spectral encoders for channel-wise and frequency-specific patterns, bidirectional LSTMs to model temporal dynamics, and a Transformer head for global relational reasoning. A patchwise tokenization strategy and neural architecture search optimize the trade-off between efficiency and representational capacity. To address individual differences, a model-agnostic meta-learning (MAML) module enables rapid adaptation to new users with limited data. Evaluated on two public MI datasets under within-subject and leave-one-subject-out (LOSO) protocols, EEG-TriNet++ achieves 79.1% and 78.6% accuracy in within-subject tasks, and 72.4% and 71.3% in LOSO settings. Ablation studies validate the contribution of each module, and comparisons with state-of-the-art methods demonstrate consistent performance gains under identical conditions.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Tibermacine et al. (2026) studied this question.

synapsesocial.com/papers/69acc5bd32b0ef16a4050765https://doi.org/10.3390/bioengineering13030307
Ask AI
Helpful
Bookmark
Share
View Full Paper