August 2026
CLMT-Net Decodes Fine-Grained Within-Limb Motor Imagery EEG
Researchers propose CLMT-Net, a contrastive learning network based on a multi-scale Transformer, for fine-grained within-limb MI decoding, achieving 76.13% accuracy on the MI-2 dataset.
March 2025
DGPDR: Discriminative Geometric Perception Dimensionality Reduction on the Riemannian Manifold for EEG Classification
The study proposes a discriminative, geometry-aware dimensionality reduction method on the Riemannian manifold for symmetric positive definite (SPD) matrices in EEG classification, aimed at boosting discrimination while reducing information loss. On BCI Competition IV Dataset 1 and Dataset 2a, the method improved classification accuracy by 5.0% and 19.38% respectively, indicating robust performance is retained after dimensionality reduction.