用于实时脑电图步态解码的2模块架构：一项试点研究
A 2-Block Architecture for Real-Time EEG Gait Decoding: A Pilot Study
浏览论文内容
中文总结 AI 辅助
该研究针对EEG下肢外骨骼控制的局限，提出含特征提取与PolyTVL+LSTM解码器的2模块BCI架构，经实验验证其在四态步态分类中表现优异，且具备实时可行性。
中文摘要 AI 辅助
通过脑电图（EEG）实现的闭环下肢外骨骼控制，仍受运动伪影、低信噪比及二元步态范式无法捕捉完整皮层步态复杂性的限制。我们提出一种2模块脑机接口（BCI）架构：含可训练会话特定特征提取模块，具备实时伪影抑制与多域特征提取功能，耦合基于新型多项式时变层（PolyTVL）+LSTM构建的解码器模块，用于四态步态分类（站立、启动、执行、终止）。消融实验证实v01（PolyTVL+LSTM）优于所有变体（验证马修斯相关系数MCC为0.435，差值为0.187），且各感兴趣区（ROI）与子频带的EEG特征判别力一致（p<0.05）。采用v01的闭环部署实现了55.3%（Rex辅助）与52.7%（自主）的步态启动成功率，平均预测时间为70.5毫秒（±41.5），验证了该试点研究的实时可行性。
英文摘要
Closed-loop lower-limb exoskeleton control via Electroencephalography (EEG) remains limited by motion artifacts, low signal-to-noise ratio, and binary gait formulations that fail to capture full cortical gait complexity. We propose a 2-block Brain-Computer Interface (BCI) architecture: a trainable session-specific Feature Extraction Block with real-time artifact suppression and multi-domain feature extraction, coupled with a Decoder Block built on a novel Polynomial Time-Varying Layer (PolyTVL)+LSTM for four-state gait classification (Stand, Initiate, Execute, Terminate). Ablation confirmed v01 (PolyTVL+LSTM) outperformed all variants (validation MCC: 0.435, gap: 0.187), with consistent EEG feature discriminability across ROIs and sub-bands (p<0.05). Closed-loop deployment with v01 achieved 55.3% (Rex-assisted) and 52.7% (volitional) gait initiation success, with a mean end-to-end processing time of 70.5~ms (+/-41.5), validating real-time feasibility in this pilot study.
