aiqbench analysis
This research addresses a critical bottleneck in brain-computer interfaces by using reinforcement learning to optimize EEG decoding windows based on the temporal structure of motor imagery events. By enforcing physiological constraints through a finite-state machine and leveraging Transformer encoders for history dependencies, the method achieves more stable training and improved cross-subject performance compared to standard sliding window approaches. The work represents a significant step forward in aligning algorithmic decisions with neurophysiological realities for practical BCI applications.
Time Window Optimization for Motor Imagery Classification via Temporal Structure Embedded Reinforcement Learning
arXiv:2610.16921v1 Announce Type: cross Abstract: Online motor imagery-based brain-computer interfaces (MI-BCIs) typically decode continuous EEG using fixed-length sliding windows that may be misaligned with neural events. Existing window optimization methods often evaluate windows independently, overlooking temporal dependencies and potentially producing fragmented or physiologically implausible selections. We propose Temporal Structure Embedded Reinforcement Learning (TSE-RL), a framework that incorporates prior knowledge of MI event structure into a constrained Markov decision process for adaptive window optimization. First, TSE-RL assigns each window an explicit semantic role through Discard, Onset, Sustain, or Offset actions, extending binary retain/discard decisions to event-level alignment. Second, a finite-state machine masks invalid actions to enforce the temporal order of MI phases and promote physiologically plausible window sequences. Third, a Transformer-based history encoder captures dependencies across windows, improving training stability and computational efficiency compared with recurrent architectures. TSE-RL is plug-and-play and can be integrated with diverse MI classifiers. Experiments on multiple benchmark datasets demonstrate consistent improvements in decoding performance in both cross-session and cross-subject settings. Visualization analyses further suggest that the learned window selection policy aligns with neurophysiological principles.
Abstract:Online motor imagery-based brain-computer interfaces (MI-BCIs) typically decode continuous EEG using fixed-length sliding windows that may be misaligned with neural events. Existing window optimization methods often evaluate windows independently, overlooking temporal dependencies and potentially producing fragmented or physiologically implausible selections. We propose Temporal Structure Embedded Reinforcement Learning (TSE-RL), a framework that incorporates prior knowledge of MI event structure into a constrained Markov decision process for adaptive window optimization. First, TSE-RL assigns each window an explicit semantic role through Discard, Onset, Sustain, or Offset actions, extending binary retain/discard decisions to event-level alignment. Second, a finite-state machine masks invalid actions to enforce the temporal order of MI phases and promote physiologically plausible window sequences. Third, a Transformer-based history encoder captures dependencies across windows, improving training stability and computational efficiency compared with recurrent architectures. TSE-RL is plug-and-play and can be integrated with diverse MI classifiers. Experiments on multiple benchmark datasets demonstrate consistent improvements in decoding performance in both cross-session and cross-subject settings. Visualization analyses further suggest that the learned window selection policy aligns with neurophysiological principles.
12 pages, 4 figures. Code available at this https URL
Neural and Evolutionary Computing (cs.NE); Machine Learning (cs.LG)
arXiv:2610.16921 [cs.NE]
(or arXiv:2610.16921v1 [cs.NE] for this version)
https://doi.org/10.48550/arXiv.2610.16921 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 282 words
Related coverage
A Multi-Objective Optimisation Framework for Corticomuscular EEG-EMG Pair Selection in Hybrid BCI
arXiv · Sep 18, 2026
Multi-Modal Attention for Automated Disaster Damage Assessment Using Remote Sensing Imagery and Deep Learning
arXiv · Jun 16, 2026
Cracking the Data Science Case Study Interview
Analytics Vidhya · Jul 26, 2026
Presentation: From Copy-Paste to Composition: Building Agents Like Real Software
InfoQ · Jul 22, 2026