Do Spatial Descriptors Improve Multi-DoF Finger Movement Decoding from HD sEMG?

TL;DR

This study compares a novel spatial descriptor-based method (MLD-BFM) with traditional features for decoding finger movements from HD sEMG, finding that spatial resolution preservation is crucial for accuracy, though improvements over conventional features are not statistically significant.

Contribution

The paper introduces the MLD-BFM, a multichannel spatial descriptor approach, demonstrating its effectiveness in preserving spatial information for multi-DoF finger movement decoding from HD sEMG.

Findings

MLD-BFM achieved the highest R²vw with 86.68%.

Spatial descriptors outperform dimensionality reduction methods.

Dense multichannel recordings encode spatial info through amplitude-based features.

Abstract

Restoring hand function requires simultaneous and proportional control (SPC) of multiple degrees of freedom (DoFs). This study evaluated the multichannel linear descriptors-based block field method (MLD-BFM) against conventional feature extraction approaches for continuous decoding of five finger-joint DoFs using high-density surface electromyography (HD sEMG). Twenty-one healthy participants performed dynamic sinusoidal finger movements while HD sEMG signals were recorded from the proximal forearm. MLD-BFM extracted spatial descriptors including effective field strength ($\Sigma$), field-strength variation rate ($\Phi$), and spatial complexity ($\Omega$). Performance was optimized (block size: $2\times2$; window: 0.15,s) and compared with conventional time-domain features, root mean square (RMS) and mean absolute value plus waveform length (MAV-WL), as well as dimensionality reduction methods (PCA and NMF), using multi-output regression models. MLD-BFM achieved the highest mean variance-weighted coefficient of determination ($\mathrm{R}^2_\mathrm{vw}$) across all models, with the multilayer perceptron yielding the best result ($86.68 \pm 0.33 \%$). However, the improvement was not statistically significant relative to time-domain features, suggesting that dense multichannel recordings already encode spatial information through amplitude-based descriptors. MLD-BFM significantly outperformed dimensionality reduction approaches, indicating that preserving the spatial resolution of HD sEMG is critical for accurate multi-DoF finger movement regression.