TY - JOUR
T1 - A Spectral-Temporal Refined Attention Network via Contrastive Mutual Learning for Closed-Loop Motor Imagery BCI
AU - Yan, Weidong
AU - Liu, Jingyu
AU - Zhang, Zeyu
AU - Zhang, Qinge
AU - Li, Yang
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2026
Y1 - 2026
N2 - The motor imagery (MI) based brain-computer interface (BCI) holds broad application prospects in human-machine interaction. However, current MI recognition approaches primarily utilize complex attention modules for higher recognition accuracy, consequently hindering real-time BCI implementation. Furthermore, existing methods often overlook inter-subject variability, leading to inadequate generalization of model. Additionally, traditional BCI systems lack closed-loop feedback from the machine to the brain. To address these limitations, we develop a novel closed-loop motor imagery BCI system, which encompasses a spectral-temporal refined attention network via contrastive mutual learning (STRA-CML) and a brain-controlled perceived hand exoskeleton. Specifically, we first design a spectral temporal refined attention block to capture the most discriminative spectral and temporal features. Second, we investigate a contrastive mutual learning strategy incorporating supervised-contrastive learning to enhance the generalization of our STRA-CML. Finally, a brain-machine closed-loop interaction platform based on perceived hand exoskeleton is developed to validate the feasibility of the proposed STRA-CML and provide kinesthetic and visual feedback synchronized with MI. Competitive experimental results on two public datasets and a self-collected dataset demonstrate the effectiveness of our STRA-CML, indicating that our STRA-CML achieves superior classification performance of 83.89% on BCI IV 2a dataset, 86.93% on BCI IV 2b dataset, and 82.79% on self-collected dataset.
AB - The motor imagery (MI) based brain-computer interface (BCI) holds broad application prospects in human-machine interaction. However, current MI recognition approaches primarily utilize complex attention modules for higher recognition accuracy, consequently hindering real-time BCI implementation. Furthermore, existing methods often overlook inter-subject variability, leading to inadequate generalization of model. Additionally, traditional BCI systems lack closed-loop feedback from the machine to the brain. To address these limitations, we develop a novel closed-loop motor imagery BCI system, which encompasses a spectral-temporal refined attention network via contrastive mutual learning (STRA-CML) and a brain-controlled perceived hand exoskeleton. Specifically, we first design a spectral temporal refined attention block to capture the most discriminative spectral and temporal features. Second, we investigate a contrastive mutual learning strategy incorporating supervised-contrastive learning to enhance the generalization of our STRA-CML. Finally, a brain-machine closed-loop interaction platform based on perceived hand exoskeleton is developed to validate the feasibility of the proposed STRA-CML and provide kinesthetic and visual feedback synchronized with MI. Competitive experimental results on two public datasets and a self-collected dataset demonstrate the effectiveness of our STRA-CML, indicating that our STRA-CML achieves superior classification performance of 83.89% on BCI IV 2a dataset, 86.93% on BCI IV 2b dataset, and 82.79% on self-collected dataset.
KW - Braina-computer interface (BCI)
KW - closed-loop braina-machine interaction
KW - contrastive mutual learning (CML)
KW - motor imagery
KW - perceived hand exoskeleton
KW - spectral-temporal refined attention (STRA)
UR - https://www.scopus.com/pages/publications/105017698638
U2 - 10.1109/TCSS.2025.3607894
DO - 10.1109/TCSS.2025.3607894
M3 - Article
AN - SCOPUS:105017698638
SN - 2329-924X
VL - 13
SP - 1614
EP - 1626
JO - IEEE Transactions on Computational Social Systems
JF - IEEE Transactions on Computational Social Systems
IS - 2
ER -