Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A Fentanyl-Responsive Microneedle Patch for Harm Reduction.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Pore structure and separation performance of macroporous agarose microspheres fabricated by calcium carbonate, starch, and double emulsion templating.

International journal of biological macromolecules·2026
Same author

Synergistic stabilization of Pickering emulsions by agar-chitosan composite particles and their potential for improving the bioavailability of lipophilic simvastatin.

International journal of biological macromolecules·2026
Same author

Harnessing thermo-hydrogen coupling with palladium hydride nanoparticles for superior antitumor therapy.

RSC advances·2026
Same author

Catalytic Asymmetric Construction of Si-Chiral Silabicyclo[3.3.1]Nonanes Using Functionalized Prochiral Silacyclohexanones.

Angewandte Chemie (International ed. in English)·2026
Same author

Genotypic and phenotypic spectrum of PRRT2-related variations: clinical analysis and treatment response in fourteen unrelated Chinese patients.

BMC medical genomics·2026

Related Experiment Video

Updated: May 7, 2025

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

279

Multi-scale attention patching encoder network: a deployable model for continuous estimation of hand kinematics from

Chuang Lin1, Qiong Xiao2, Penghui Zhao3

  • 1The School of Information Science and Technology, Dalian Maritime University, Dalian, 116026, China. linchuang_78@126.com.

Journal of Neuroengineering and Rehabilitation
|December 30, 2024
PubMed
Summary

This study introduces a new network, sMAPEN, for precise simultaneous and proportional control (SPC) using surface electromyographic (sEMG) signals. The advanced model achieves high accuracy and speed, enabling real-time human-machine interaction applications.

Keywords:
Continuous estimationHand kinematicsMulti-scale attentionPatching encoderTransformersEMG

More Related Videos

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.4K
A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study
06:58

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study

Published on: November 6, 2015

9.4K

Related Experiment Videos

Last Updated: May 7, 2025

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

279
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.4K
A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study
06:58

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study

Published on: November 6, 2015

9.4K

Area of Science:

  • Biomedical Engineering
  • Human-Machine Interaction
  • Signal Processing

Background:

  • Surface electromyographic (sEMG) signals are crucial for human-machine interaction (HMI).
  • Existing continuous motion estimation methods for sEMG-based control have limitations in accuracy and inference speed.
  • High-precision methods often exceed 200 ms inference time and support fewer than 15 hand movements, restricting HMI applications.

Purpose of the Study:

  • To develop a novel deep learning model for enhanced simultaneous and proportional control (SPC) using sEMG signals.
  • To overcome the limitations of existing methods in terms of prediction accuracy, inference speed, and the number of controllable movements.
  • To enable more sophisticated and responsive HMI applications through improved sEMG-based control.

Main Methods:

  • Proposed a smooth Multi-scale Attention Patching Encoder Network (sMAPEN).
  • sMAPEN integrates a Multi-scale Attention Fusion (MAF) module for local spatiotemporal feature extraction and a Patching Encoder (PE) module for global feature acquisition.
  • A smoothing layer was incorporated to enhance prediction stability.

Main Results:

  • The sMAPEN model achieved an average Pearson correlation coefficient (CC) of 0.9082, normalized root mean square error (NRMSE) of 0.0646°, and R² of 0.8163 on 40 hand movements from 40 subjects.
  • Performance significantly outperformed state-of-the-art methods across all metrics (p < 0.01).
  • Deployment on a portable device demonstrated a low inference delay of 97.93 ms.

Conclusions:

  • The sMAPEN model accurately predicts up to 40 hand movements, surpassing existing methods in accuracy.
  • Its lightweight design significantly improves inference speed, facilitating deployment on wearable devices.
  • These advancements indicate sMAPEN's substantial potential for advancing HMI applications.