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 novel TCNet for irrelevant gesture rejection based on electromyography signals.

Medical & biological engineering & computing·2026
Same author

A Deep Learning Framework for Efficient Online Decomposition of High-Density Surface Electromyogram into Motor Unit Spike Trains.

International journal of neural systems·2026
Same author

A novel approach to exercise heart rate estimation combining PPG quality assessment with DNN modeling.

Medical & biological engineering & computing·2025
Same author

Online and Cross-User Finger Movement Pattern Recognition by Decoding Neural Drive Information from Surface Electromyogram.

International journal of neural systems·2025
Same author

Preterm birth prediction from electrohysterogram using multivariate empirical mode decomposition.

Medical & biological engineering & computing·2025
Same author

A solution for co-frequency and low SNR problems in heart rate estimation based on photoplethysmography signals.

Medical & biological engineering & computing·2022

Related Experiment Video

Updated: Aug 12, 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

692

Multi-source domain generalization and adaptation toward cross-subject myoelectric pattern recognition.

Xuan Zhang1, Le Wu1, Xu Zhang1

  • 1School of Information Science and Technology, University of Science and Technology of China, Hefei 230027, People's Republic of China.

Journal of Neural Engineering
|January 31, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces a novel multi-source domain adaptation framework to improve cross-user myoelectric pattern recognition (MPR). The new method enhances model generalization by aligning individual user data, overcoming limitations of previous approaches.

Keywords:
cross-subjectdeep learningelectromyographymulti-source domain adaptationrobust EMG control

More Related Videos

Cross-Modal Multivariate Pattern Analysis
13:51

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

20.0K
Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.4K

Related Experiment Videos

Last Updated: Aug 12, 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

692
Cross-Modal Multivariate Pattern Analysis
13:51

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

20.0K
Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.4K

Area of Science:

  • Biomedical Engineering
  • Rehabilitation Engineering
  • Human-Computer Interaction

Background:

  • Myoelectric pattern recognition (MPR) shows promise but degrades with individual user variations in cross-user applications.
  • Existing domain adaptation (DA) methods for surface electromyography (sEMG) control use single-source DA, which inadequately addresses inter-user sEMG distribution differences.

Purpose of the Study:

  • To develop a multi-source synchronize domain adaptation framework for cross-user MPR.
  • To improve model generalization and performance in practical myoelectric control applications by addressing individual sEMG distribution variances.

Main Methods:

  • Proposed a multi-source synchronize domain adaptation framework with both domain adaptation (DA) and domain generalization (DG) capabilities.
  • Aligned individual source users and the new user in separate feature spaces while retaining source-combined data for SDA effectiveness.
  • Evaluated the framework on data from nine subjects performing six tasks.

Main Results:

  • The proposed multi-source framework demonstrated significant positive domain generalization (DG) and domain adaptation (DA) performance.
  • Achieved effective cross-user classification in myoelectric control applications.

Conclusions:

  • The multi-source framework effectively overcomes the performance degradation in cross-user MPR caused by individual sEMG distribution variations.
  • This work confirms the usability and feasibility of the proposed multi-source framework for practical cross-user myoelectric control.