Dual-Manifold Contrastive Learning for Robust and Real-Time EEG Motor Decoding
Sensors · 12.03.2026 · 26 (6) · 1783
DOI: 10.3390/s26061783 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 12.03.2026. Verfasst von Chengsi Hu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China. Hauptthemen laut MEDLINE: Electroencephalography, Brain-Computer Interfaces, Machine Learning. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: STI2030-Brain Science and Brain-Inspired Intelligence Technology, GUANGDONG TALENTS PROGRAM, Guangdong Provincial Key Laboratory of Multimodality Non-Invasive Brain-Computer Interfaces.
Abstract (Originalsprache)
Brain–computer interfaces (BCIs) have great potential for consumer electronics, as they enable the decoding of brain activity to control external devices and assist human–computer interaction. However, current decoding methods for BCIs face several challenges, such as low accuracy, poor stability under electrode shift, and slow processing for real-time use. In this paper, we propose a hybrid decoding framework designed to address the challenges of current EEG decoding methods. Our method combines manifold learning with contrastive learning. The core of our method lies in a dual-manifold model that uses non-negative matrix factorization (NMF) and a contrastive manifold learning framework to extract clear and useful features from brain signals. To improve decoding stability, we introduce a joint training strategy that enhances feature learning. Furthermore, the system is optimized for real-time interaction, reducing the system latency to 100 ms. We collect EEG signals from 15 subjects performing motor execution tasks and 10 subjects performing motor imagery tasks to construct a motor EEG dataset. On this dataset, the proposed method achieves superior decoding performance, reaching F1-scores of 0.7382 for the motor imagery tasks and 0.8361 for the motor execution tasks. Furthermore, the method maintains robustness even with reduced electrode counts and altered spatial distributions, highlighting its potential as a decoding solution for reliable and portable BCI systems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China.
- CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences (CAS), Shenzhen 518055, China.
Förderung
- STI2030-Brain Science and Brain-Inspired Intelligence Technology
- GUANGDONG TALENTS PROGRAM
- Guangdong Provincial Key Laboratory of Multimodality Non-Invasive Brain-Computer Interfaces
- Shenzhen Strategic Emerging Industry Support Plans
- Guangdong Basic and Applied Basic Research Foundation
- Major Basic Research Project of Shandong Natural Science Foundation
- Guangdong Climbing Program Special Funds
- Ministry of Science and Technology of China
Zitieren
APA
Hu, C., Liu, Q., Xu, C., Li, G., & Li, Y. (2026). Dual-Manifold Contrastive Learning for Robust and Real-Time EEG Motor Decoding. Sensors, 26(6), 1783. https://doi.org/10.3390/s26061783
Vancouver
Hu C, Liu Q, Xu C, Li G, Li Y. Dual-Manifold Contrastive Learning for Robust and Real-Time EEG Motor Decoding. Sensors. 2026;26(6):1783. doi:10.3390/s26061783
BibTeX
@article{Hu2026,
author = {Hu, Chengsi and Liu, Qing and Xu, Chenying and Li, Guanglin and Li, Yongcheng},
title = {Dual-Manifold Contrastive Learning for Robust and Real-Time EEG Motor Decoding},
journal = {Sensors},
year = {2026},
volume = {26},
number = {6},
pages = {1783},
doi = {10.3390/s26061783}
}
EUVIMED