Skip to main navigation Skip to search Skip to main content

A neurophysiology-constrained joint network for multi-finger force estimation from surface electromyogram

  • Yixin Li
  • , Haixiong Zhang
  • , Lei Xia
  • , Guanghua Xu
  • , Yang Zheng
  • State Industry-Education Integration Center for Medical Innovations
  • Xi'an Jiaotong University
  • Department of Hand Surgery
  • Xi'an Jiaotong University

Research output: Contribution to journal › Article › peer-review

Abstract

Decoding multi-finger forces from surface electromyogram (sEMG) is critical for dexterous prosthetic hand control. While recent deep learning-based end-to-end decoders have shown promising performance, they often lack physiological interpretability. Conversely, motor unit (MU) firing information provides a more accurate characterization of forces but is challenging to integrate effectively. Therefore, this study proposes a neurophysiology-constrained joint network (NCJ-Net), which explicitly integrates MU firing information by coupling a gated recurrent unit (GRU)-based decomposition network that estimates MU firing-rate representations with a temporal force regression network. A stage-wise training strategy, featuring initial pretraining followed by joint fine-tuning and MU quality-aware supervision on intermediate decomposition representations, was adopted to tightly couple the two subnetworks beyond a mere structural cascade. High-density sEMG and multi-finger forces were recorded from ten healthy participants performing multi-finger, multi-level isometric force tasks. The proposed NCJ-Net achieved the best performance (root mean squared error = 3.59 ± 0.82 % MVC (maximum voluntary contraction); coefficient of determination = 0.947 ± 0.031) and significantly outperformed all other baseline methods. An additional preliminary test involving one bilateral upper-limb amputee with visually presented target trajectories as surrogate reference outputs showed that NCJ-Net achieved the best overall performance. These results demonstrate that embedding neurophysiological hierarchy into a jointly optimized architecture can improve multi-finger force estimation while preserving the network's interpretability aligned with the neurophysiology prior of descending motor control pathway. Overall, the proposed framework offers a principled route toward intelligent and physiologically grounded decoding systems for human-machine interface applications such as dexterous prosthetic hand control.

Original languageEnglish
Article number116131
JournalEngineering Applications of Artificial Intelligence
Volume183
DOIs
StatePublished - 1 Nov 2026
Externally publishedYes

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

  1. SDG 3 - Good Health and Well-being
    SDG 3 Good Health and Well-being

Keywords

  • Electromyogram signal decomposition
  • High-density electromyogram
  • Multi-finger force estimation
  • Neural network

Fingerprint

Dive into the research topics of 'A neurophysiology-constrained joint network for multi-finger force estimation from surface electromyogram'. Together they form a unique fingerprint.

Cite this