Learning Dynamic Neural Evidence Representations for Time-Adaptive Brain-Computer Interfaces
Abstract
Brain-computer interfaces (BCIs) decode neural activity into commands, yet most existing systems rely on fixed-window decoding that may result in redundant observation or unreliable predictions due to insufficient evidence. Adaptive temporal decision-making (ATDM) addresses this accuracy-time trade-off by progressively accumulating EEG evidence and deciding when to stop. However, existing EEG encoders are mainly designed for fixed-window decoding and may not provide reliable state representations under variable observation lengths. In addition, current ATDM-oriented encoders are typically tailored to specific EEG paradigms, limiting their applicability across different BCI tasks. To address these limitations, we propose ProtoTrigger, a two-stage prototype learning-based EEG state encoder for ATDM. ProtoTrigger uses prototype matching to extract stable local EEG embeddings and prototype-based attention to aggregate decision-relevant temporal evidence during progressive observation. Offline evaluations across three EEG paradigms demonstrated state-of-the-art accuracy-time trade-offs and strong generalizability across different EEG paradigms. An online human-in-the-loop augmented reality-based BCI experiment further demonstrated its real-time feasibility. These results suggest that ProtoTrigger provides a general EEG state encoding framework for efficient ATDM-based BCI systems.
Related
- Assistive algorithms influence neural representations in motor brain-computer interfaces
- Clinical safety assessment of implanted brain-computer interfaces: current evidence and a pathway to standardization
- Learning Protein-Protein Interaction Interfaces from Multimodal Representations
- Real-time noise cancellation for EEG monitoring and brain-computer interfaces
- Large language models integrated into brain–computer interfaces for communication and control: a systematic review
BibTeX
@misc{cao2026learning,
title = {{Learning Dynamic Neural Evidence Representations for Time-Adaptive Brain-Computer Interfaces}},
author = {Beining Cao and Ziyi Zhao and Xiaowei Jiang and Daniel Leong and Yingtao Ren and Thomas Do and Yu-Cheng Fred Chang and Chin-Teng Lin},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.22088},
eprint = {2609.22088},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.22088},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Learning Dynamic Neural Evidence Representations for Time-Adaptive Brain-Computer Interfaces
AU - Beining Cao
AU - Ziyi Zhao
AU - Xiaowei Jiang
AU - Daniel Leong
AU - Yingtao Ren
AU - Thomas Do
AU - Yu-Cheng Fred Chang
AU - Chin-Teng Lin
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.22088
UR - https://arxiv.org/abs/2609.22088
AB - Brain-computer interfaces (BCIs) decode neural activity into commands, yet most existing systems rely on fixed-window decoding that may result in redundant observation or unreliable predictions due to insufficient evidence. Adaptive temporal decision-making (ATDM) addresses this accuracy-time trade-off by progressively accumulating EEG evidence and deciding when to stop. However, existing EEG encoders are mainly designed for fixed-window decoding and may not provide reliable state representations under variable observation lengths. In addition, current ATDM-oriented encoders are typically tailored to specific EEG paradigms, limiting their applicability across different BCI tasks. To address these limitations, we propose ProtoTrigger, a two-stage prototype learning-based EEG state encoder for ATDM. ProtoTrigger uses prototype matching to extract stable local EEG embeddings and prototype-based attention to aggregate decision-relevant temporal evidence during progressive observation. Offline evaluations across three EEG paradigms demonstrated state-of-the-art accuracy-time trade-offs and strong generalizability across different EEG paradigms. An online human-in-the-loop augmented reality-based BCI experiment further demonstrated its real-time feasibility. These results suggest that ProtoTrigger provides a general EEG state encoding framework for efficient ATDM-based BCI systems.
ER -