Search papers, labs, and topics across Lattice.
The authors benchmark five-finger multilabel motor intent decoding from high-density surface electromyography (sEMG) collected from stroke patients, comparing temporal, spatial, and graph architectures. High-density models are typically impractical for wearable clinical hardware due to sensor footprint and compute limits on weak, post-stroke neuromuscular signals. To resolve this, cross-channel knowledge distillation transfers representations from high-density signals into an embedded 123K-parameter CNN operating on only four muscle channels, maintaining 76.1% finger accuracy and 0.522 subset accuracy.
Cross-channel knowledge distillation allows a tiny 123K-parameter model to decode five-finger motor intent from stroke survivors using only four surface EMG channels without sacrificing multi-label precision.
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.
