Neuromotor hierarchy network improves muscle signal decoding accuracy
Neuromotor Hierarchy Network: Physiological Inductive Biases for Robust Generalization in sEMG Decoding
Machine Learning
Summary
Decoding muscle signals from the skin is tricky because signals change between people and over time. The authors introduce a new neural network called the Neuromotor Hierarchy Network that learns important muscle coordination patterns to better interpret these signals. Their method uses a layered design mimicking how muscles work together and adjusts to different recording conditions. Tests show it achieves more accurate and efficient movement and typing predictions than earlier methods.
What this means in practice
- •For wearable device developers: Develop improved muscle-signal decoding for wearable interfaces enabling more accurate movement tracking with fewer model parameters.$Commercial implications: Enables the creation of lightweight, power-efficient wearable devices with better muscle signal interpretation for user control.
- •For assistive technology engineers: Build advanced input systems for users with motor impairments that decode hand poses and typing from muscle signals more reliably.
Authors
He Wang, Hongyuan Qi, Zhaoxian Zhang, Jinbin Luo, Linyi He, Mehul Motani, Changsheng Wu
Abstract
Surface electromyography (sEMG) provides a wearable, noninvasive interface to neuromuscular activity for movement decoding and human-computer interaction. Population-scale decoding remains difficult because the relationship between sEMG and neuromuscular activity varies across users and sessions, while task-relevant dynamics span channels and multiple timescales. Learning waveform-to-output mappings from task labels leaves the distinction between recording variability and coordinated motor activity implicit. We introduce the Neuromotor Hierarchy Network (NHN), which learns a compact latent neuromotor state from task supervision to represent task-relevant neuromuscular coordination. NHN constructs this latent state through a hierarchy inspired by neuromotor organization.It adapts recording statistics while preserving relative intensity.Its spatiotemporal encoder uses parameter-efficient channel interactions and modulates features with multi-timescale history. The resulting features yield candidate activations of learned motor primitives, which are temporally integrated and continuously weighted to form the state. Theoretical analysis characterizes the efficiency, temporal behavior, and optimization of NHN's core mechanisms. We evaluate the architecture for both continuous hand-pose estimation on emg2pose and touch-typing recognition on emg2qwerty. On emg2pose, NHN reduces user-averaged angular error by 0.52% to 2.84% across all three generalization splits in both Regression and Tracking relative to Hadidi et al.'s best task-specific variants, using 48.42% to 48.51% fewer parameters. On emg2qwerty, NHN reduces beam-search character error rate by 19.40% zero-shot and 30.42% after fine-tuning relative to SplashNet-Upscale, using 65.86% fewer parameters. Physiology-guided inference of a latent neuromotor state supports parameter-efficient sEMG decoding.