A Complementary Dual-Branch Receptive Field Network for Cross-Channel-Density Motor Imagery EEG Decoding.
4 affiliations
- 1School of Artificial Intelligence, Guangzhou Maritime University, Guangzhou 510725, China.
- 2School of Artificial Intelligence, South China Normal University, Guangzhou 510631, China.
- 3School of Electronic and Information Engineering, Huaihua University, Huaihua 418000, China.
- 4School of Automation Science and Engineering, South China University of Technology, Guangzhou 510640, China.
Abstract
Brain-computer interfaces (BCIs) enable direct communication between the brain and external devices, providing a bio-inspired link between humans and artificial systems. However, electroencephalography (EEG)-based motor imagery (MI) decoding continues to pose challenges, due to limited temporal exploitation and insufficient spatio-temporal modeling. To alleviate these limitations, a complementary dual-branch receptive field network (DBRFNet) is proposed for cross-channel-density MI-EEG decoding. Specifically, two complementary branches with distinct temporal receptive fields are designed to capture multi-scale temporal dynamics. Each branch employs a progressive spatio-temporal module integrating temporal, depthwise spatial, and dilated convolutions for modeling short- and long-range temporal dependencies. The features from the two branches are fused using element-wise addition and further encoded for classification. The proposed method is evaluated on three public datasets representing low-, medium-, and high-density EEG configurations. DBRFNet achieves decoding accuracies of 80.48%, 84.37%, and 92.24% under cross-validation analysis, and 87.76%, 80.94%, and 94.64% under hold-out analysis, demonstrating competitive performance compared with state-of-the-art methods. Ablation studies further validate the effectiveness of each component within the proposed architecture. These results indicate that DBRFNet effectively learns discriminative spatio-temporal representations and provides a robust solution for MI-BCI systems.
Related
- Decoding motor imagery EEG signals by a deep learning network integrating multiscale filtering and temporal-channel attention mechanisms
- Evidence for decoder-label-regime-dependent effects of complementary leaky integrate-and-fire temporal-state decoding in motor-imagery EEG
- Decoding spatial attention in the cocktail party problem using whole-head high-density fNIRS
- T-SNN: Temporal Simplicial Neural Network for EEG Decoding
- Brain Decoding from a Deep Neural Network of Visual Memory Reveals the Maturation Trajectory of Memory Systems across Ages 3-7
BibTeX
@article{zhu2026complementary,
title = {{A Complementary Dual-Branch Receptive Field Network for Cross-Channel-Density Motor Imagery EEG Decoding.}},
author = {Mengnan Zhu and Kendi Li and Junbiao Zhu and Yantao Chen and Hui Cao and Jing Xiao and Zuguang Rao},
journal = {Biomimetics (Basel, Switzerland)},
year = {2026},
month = sep,
doi = {10.3390/biomimetics11100690},
url = {https://europepmc.org/article/MED/42930242},
note = {CC BY},
}
RIS
TY - JOUR
TI - A Complementary Dual-Branch Receptive Field Network for Cross-Channel-Density Motor Imagery EEG Decoding.
AU - Mengnan Zhu
AU - Kendi Li
AU - Junbiao Zhu
AU - Yantao Chen
AU - Hui Cao
AU - Jing Xiao
AU - Zuguang Rao
PY - 2026
DA - 2026/09/23
JO - Biomimetics (Basel, Switzerland)
DO - 10.3390/biomimetics11100690
UR - https://europepmc.org/article/MED/42930242
AB - Brain-computer interfaces (BCIs) enable direct communication between the brain and external devices, providing a bio-inspired link between humans and artificial systems. However, electroencephalography (EEG)-based motor imagery (MI) decoding continues to pose challenges, due to limited temporal exploitation and insufficient spatio-temporal modeling. To alleviate these limitations, a complementary dual-branch receptive field network (DBRFNet) is proposed for cross-channel-density MI-EEG decoding. Specifically, two complementary branches with distinct temporal receptive fields are designed to capture multi-scale temporal dynamics. Each branch employs a progressive spatio-temporal module integrating temporal, depthwise spatial, and dilated convolutions for modeling short- and long-range temporal dependencies. The features from the two branches are fused using element-wise addition and further encoded for classification. The proposed method is evaluated on three public datasets representing low-, medium-, and high-density EEG configurations. DBRFNet achieves decoding accuracies of 80.48%, 84.37%, and 92.24% under cross-validation analysis, and 87.76%, 80.94%, and 94.64% under hold-out analysis, demonstrating competitive performance compared with state-of-the-art methods. Ablation studies further validate the effectiveness of each component within the proposed architecture. These results indicate that DBRFNet effectively learns discriminative spatio-temporal representations and provides a robust solution for MI-BCI systems.
SN - 2313-7673
ER -