A Lightweight Dual-Attention Neural Network for Robust and Efficient EEG Motor Imagery Decoding
- 19 March 2026
- journal article
- research article
- Published by World Scientific Pub Co Pte Ltd in International Journal of Neural Systems
- Vol. 36 (07) , 2650026
Abstract
Motor imagery-based brain–computer interface (MI-BCI) faces a critical challenge in achieving effective spatial-temporal feature modeling while maintaining a compact model parameterization. Herein, a lightweight model was proposed, termed as Dual-Attention-EEGNet (DA-EEGNet), which extends the EEGNet backbone by integrating a channel attention module and a depth attention module to selectively emphasize informative electrodes and temporally discriminative features. Two widely used MI benchmark datasets and three evaluation strategies, i.e. subject-dependent scenario, subject-independent scenario, and dataset-independent classification scenario, were utilized to verify the model’s performance. Despite its compact design, DA-EEGNet contains merely 3.97[ ]k trainable parameters and achieves average classification accuracies of [ ] and [ ], outperforming or matching existing deep learning approaches that rely on substantially larger parameter counts. Ablation studies further confirm the complementary contributions of the channel and depth attention modules. In addition, visualization analyses, including temporal attention heatmaps and motor-area topographies, demonstrate that DA-EEGNet captures neurophysiologically meaningful spatial-temporal patterns consistent with MI-related brain activity. These results indicate that DA-EEGNet provides a favorable parameter-accuracy trade-off and serves as an efficient and interpretable baseline for MI-BCI applications.Keywords
Funding Information
- STI 2030-Major Projects (#2022ZD0208901)
- National Natural Science Foundation of China (#82372084)
- Key R&D projects of the Science and Technology Department of Chengdu (#2024-YF08-00072-GX)
This publication has 51 references indexed in Scilit:
- Upper Limb Movement Classification Via Electromyographic Signals and an Enhanced Probabilistic NetworkJournal of Medical Systems, 2020
- Classification of multiple motor imagery using deep convolutional neural networks and spatial filtersApplied Soft Computing, 2019
- A Novel Methodology for Extracting and Evaluating Therapeutic Movements in Game-Based Motion Capture Rehabilitation SystemsJournal of Medical Systems, 2018
- CBAM: Convolutional Block Attention Module2018
- Deep learning with convolutional neural networks for EEG decoding and visualizationHuman Brain Mapping, 2017
- Gross motor ability predicts response to upper extremity rehabilitation in chronic strokeBehavioural Brain Research, 2017
- Computer-aided prediction of extent of motor recovery following constraint-induced movement therapy in chronic strokeBehavioural Brain Research, 2017
- EEG-driven RNN Classification for Prognosis of Neurodegeneration in At-Risk PatientsLecture Notes in Computer Science, 2016
- Brain–computer interface boosts motor imagery practice during stroke recoveryAnnals of Neurology, 2015
- The neurophysiological basis of motor imageryBehavioural Brain Research, 1996