Multi-Scale BiMamba with Test-Time Adaptation for Motor Imagery Classification
ACM Transactions on Autonomous and Adaptive Systems · 04.08.2026
DOI: 10.1145/3833427 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Autonomous and Adaptive Systems, online erschienen am 04.08.2026. Verfasst von Ziyang Bao und 7 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben.
Abstract (Originalsprache)
Hybrid brain-computer interfaces combining electroencephalography and functional near-infrared spectroscopy utilize neurovascular coupling to improve decoding. Current fusion strategies rely on shallow aggregation or complex attention, which struggle to capture complex temporal dynamics and complex dependencies in long sequences. Moreover, static models lack online calibration for sensor failures or non-stationary noise, causing significant performance drops. We propose the Multi-Scale Bidirectional Mamba with Test-Time Adaptation (MS-BiM-TTA) framework. The architecture employs a multi-scale frontend for heterogeneous feature extraction and bidirectional state-space models for efficient long-range intra-modal and inter-modal modeling with linear complexity. To ensure robustness, a customized test-time adaptation workflow utilizes two-level entropy filtering for update safety and mutual information sharing for autonomous representation reconstruction. Results show that MS-BiM-TTA significantly enhances accuracy and demonstrates superior resilience to modality missingness in both binary and fine-grained tasks.
Zitieren
APA
Bao, Z., Guo, M., Jin, B., Zhao, Y., Yang, B., Wu, Y., Wang, K., & Liu, C. (2026). Multi-Scale BiMamba with Test-Time Adaptation for Motor Imagery Classification. ACM Transactions on Autonomous and Adaptive Systems. https://doi.org/10.1145/3833427
Vancouver
Bao Z, Guo M, Jin B, Zhao Y, Yang B, Wu Y, et al. Multi-Scale BiMamba with Test-Time Adaptation for Motor Imagery Classification. ACM Transactions on Autonomous and Adaptive Systems. 2026. doi:10.1145/3833427
BibTeX
@article{Bao2026,
author = {Bao, Ziyang and Guo, Mingseng and Jin, Botao and Zhao, Yingjie and Yang, Benyuan and Wu, Yanhong and Wang, Kesheng and Liu, Chenyu},
title = {Multi-Scale BiMamba with Test-Time Adaptation for Motor Imagery Classification},
journal = {ACM Transactions on Autonomous and Adaptive Systems},
year = {2026},
doi = {10.1145/3833427}
}
EUVIMED