发表机构
University of Toronto（多伦多大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究利用深度神经网络从卒中患者sEMG信号解码五指运动意图，通过架构搜索和知识蒸馏实现紧凑模型，为硬件设备提供可复现的控制信号路径。
AI 中文摘要
针对手指的运动意图是卒中后神经康复中具有临床意义的控制信号，即使在动作微弱或不完整的情况下，残余肌肉活动仍可能可测量。我们研究了PhysioMio数据集中从受损手臂高密度表面肌电信号（sEMG）进行五指多标签意图解码，该数据集是从卒中患者收集的双侧纵向数据集。一个通用的处理流程对齐运动标签，应用20-450 Hz巴特沃斯滤波和Symlet-4小波去噪，分割重叠的200毫秒窗口，并为每个通道提取十二个时域和频域描述符。直接的LSTM、CNN和GNN基线揭示了互补行为：LSTM达到最高的子集准确率（0.545），而GNN达到最高的宏F1（0.706）和宏AUPRC（0.776）。架构搜索随后确定CNN-Large为最强的单分割CNN，具有0.593的子集准确率和0.714的宏F1，而CNN-Micro为嵌入式推理提供了紧凑的架构。为匹配四传感器硬件设计，我们使用与ECRB、ECRL、FDS和FDP相关的通道重新训练CNN-Micro，并从模型输入中排除接地电极。在五个种子上，跨通道知识蒸馏将四通道学生模型优于直接训练，达到$0.5219 \pm 0.0114$的子集准确率、$0.7612 \pm 0.0038$的手指准确率和$0.6095 \pm 0.0058$的宏F1。选定的123K参数模型接受九个窗口的48个特征，并已导出到ONNX。这些结果为从卒中后sEMG到紧凑五指意图预测建立了一条可复现的软件路径，用于后续硬件在环评估。
英文摘要
Finger-specific motor intent is a clinically meaningful control signal for post-stroke neurorehabilitation, where residual muscle activity may remain measurable despite weak or incomplete movement. We study five-finger multilabel intent decoding from impaired-arm high-density surface electromyography (sEMG) in PhysioMio, a bilateral longitudinal dataset collected from stroke patients. A common processing protocol aligns movement labels, applies 20--450 Hz Butterworth filtering and Symlet-4 wavelet denoising, segments overlapping 200 ms windows, and extracts twelve time- and frequency-domain descriptors per channel. Direct LSTM, CNN, and GNN baselines reveal complementary behavior: the LSTM attains the highest subset accuracy (0.545), whereas the GNN attains the highest macro F1 (0.706) and macro AUPRC (0.776). Architecture search then identifies CNN-Large as the strongest single-split CNN, with 0.593 subset accuracy and 0.714 macro F1, while CNN-Micro provides a compact architecture for embedded inference. To match a four-sensor hardware design, we retrain CNN-Micro using channels associated with ECRB, ECRL, FDS, and FDP and exclude the ground electrode from model input. Across five seeds, cross-channel knowledge distillation improves the four-channel student over direct training, reaching $0.5219 \pm 0.0114$ subset accuracy, $0.7612 \pm 0.0038$ finger accuracy, and $0.6095 \pm 0.0058$ macro F1. The selected 123K-parameter model accepts nine windows of 48 features and has been exported to ONNX. These results establish a reproducible software path from post-stroke sEMG to compact five-finger intent prediction for subsequent hardware-in-the-loop evaluation.
