Multiscale spatiotemporal neural network with multi-attention mechanism using brain partitioning for motor imagery recognition
Journal of Neuroscience Methods · 2026
DOI: 10.1016/j.jneumeth.2026.110704 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Neuroscience Methods, 2026. Verfasst von Moeed Sehnan und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical and Information Engineering, Tianjin University, 300072, Tianjin, China. Hauptthemen laut MEDLINE: Brain-Computer Interfaces, Electroencephalography, Imagination, Neural Networks, Computer. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: Natural Science Foundation of Tianjin Municipality, Taishan Industry Leading Talents, National Natural Science Foundation of China.
Abstract (Originalsprache)
BACKGROUND: Motor imagery (MI)-based electroencephalogram (EEG) brain-computer interfaces (BCIs) facilitate communication for motor-impaired patients by leveraging artificial intelligence to accurately interpret brain signals. However, EEG signal classification remains challenging due to low signal-to-noise ratio (SNR) and individual variability in brain activity. NEW METHOD: We propose a novel parallel multi-depth spatial-temporal neural network aimed at enhancing the integration of spatial and temporal features from multichannel EEG signals by leveraging brain functional topography. To improve cortical representations associated with motor imagery, the model incorporates two parallel branches. One branch focuses on inter-channel differences corresponding to contralateral electrode pairs, emphasizing hemispheric disparities, while the other targets the frontal and parietal brain regions. These region-specific enhanced signal representations are then fed into the multi-depth spatial-temporal network for feature extraction and subsequent motor imagery classification. The architecture of the feature extraction network integrates four specialized blocks, ensuring the comprehensive capture of discriminative features that are particularly sensitive to task-relevant frequencies for each MI class. A multi-loss design further optimizes feature integration across networks. RESULTS: Cross-validation results on the BCI Competition IV 2a dataset and High Gamma dataset achieve accuracies of 82.14% and 95.61%, respectively, with kappa values of 0.76 and 0.93, surpassing state-of-the-art methods. CONCLUSION: These experimental results highlight the significance of parallel spatial-temporal networks based on brain partitioning for MI classification in rehabilitation engineering and real-world BCI applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electrical and Information Engineering, Tianjin University, 300072, Tianjin, China.
- Institute for Complex Systems and Mathematical Biology, King's College, University of Aberdeen, AB24 3UE, Aberdeen, UK.
- School of Electrical and Information Engineering, Tianjin University, 300072, Tianjin, China; Institute for Complex Systems and Mathematical Biology, King's College, University of Aberdeen, AB24 3UE, Aberdeen, UK. Elect…
Förderung
- Natural Science Foundation of Tianjin Municipality
- Taishan Industry Leading Talents
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
Zitieren
APA
Sehnan, M., Li, H., Li, X., Grebogi, C., Gao, Z., & Dang, W. (2026). Multiscale spatiotemporal neural network with multi-attention mechanism using brain partitioning for motor imagery recognition. Journal of Neuroscience Methods. https://doi.org/10.1016/j.jneumeth.2026.110704
Vancouver
Sehnan M, Li H, Li X, Grebogi C, Gao Z, Dang W. Multiscale spatiotemporal neural network with multi-attention mechanism using brain partitioning for motor imagery recognition. Journal of Neuroscience Methods. 2026. doi:10.1016/j.jneumeth.2026.110704
BibTeX
@article{Sehnan2026,
author = {Sehnan, Moeed and Li, Haoyu and Li, Xiaoyang and Grebogi, Celso and Gao, Zhongke and Dang, Weidong},
title = {Multiscale spatiotemporal neural network with multi-attention mechanism using brain partitioning for motor imagery recognition},
journal = {Journal of Neuroscience Methods},
year = {2026},
doi = {10.1016/j.jneumeth.2026.110704}
}
EUVIMED