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

Bouncing back from stress: objective markers of expressive flexibility and resilience in emergency healthcare workers using computer vision.

NPP - digital psychiatry and neuroscience·2026
Same author

Prevalence and determinants of academic burnout among undergraduates in a traditional Chinese medicine university: a cross-sectional study.

Frontiers in psychology·2026
Same author

Theoretical prediction of semiconductors by data driven light-element substitution in topological materials.

Science bulletin·2026
Same author

Efficacy of scapular-focused rehabilitation protocol on shoulder function following Proximal Humeral Internal Locking System fixation for proximal humeral fractures: a randomized controlled trial.

International orthopaedics·2026
Same author

Detection of Microbehavior Intervals for Predicting Mental Health: Clinically Relevant and Advanced Multimodal Temporal Analysis.

Journal of medical Internet research·2026
Same author

Dielectric-Confinement-Induced in-Plane Photoelectric Anisotropy in Isotropic Quasi-1D γ-GaS Nanoribbon.

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

Related Experiment Video

Updated: Sep 21, 2025

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
07:05

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Published on: October 27, 2016

9.3K

Learning Non-Euclidean Representations With SPD Manifold for Myoelectric Pattern Recognition.

Dezhen Xiong, Daohui Zhang, Xingang Zhao

    IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society
    |May 27, 2022
    PubMed
    Summary

    This study introduces a novel method for extracting spatial information from Electromyography (EMG) signals using symmetric positive definite (SPD) manifolds. This approach enhances myoelectric control accuracy by learning non-Euclidean representations, outperforming traditional methods.

    More Related Videos

    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

    766
    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

    9.6K

    Related Experiment Videos

    Last Updated: Sep 21, 2025

    Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
    07:05

    Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

    Published on: October 27, 2016

    9.3K
    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

    766
    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

    9.6K

    Area of Science:

    • Biomedical Engineering
    • Signal Processing
    • Machine Learning

    Background:

    • Myoelectric control systems rely on Electromyography (EMG) signals for accurate pattern recognition.
    • Traditional methods often use hand-crafted features and overlook spatial information between EMG channels.
    • Learning informative representations from EMG is crucial for advancing prosthetic and assistive technologies.

    Purpose of the Study:

    • To develop a novel approach for extracting spatial structural information from EMG signals.
    • To learn non-Euclidean representations within EMG data for improved myoelectric pattern recognition.
    • To evaluate the proposed method against classical feature sets in terms of accuracy and computational cost.

    Main Methods:

    • Utilized symmetric positive definite (SPD) manifolds to extract spatial structural information from diverse EMG channels.
    • Learned non-Euclidean representations directly from EMG signals.
    • Compared the proposed method's performance (accuracy, F1-score) against two classical feature sets.
    • Validated the algorithm on eleven gestures from ten subjects and three public databases (Ninapro DB2, DB4, DB5).

    Main Results:

    • Achieved a best accuracy of 84.85%±5.15%, an improvement of 4.04%–20.25% over contrast methods.
    • Demonstrated statistically significant improvement using the Wilcoxon signed-rank test.
    • Observed superior performance on public EMG databases (Ninapro DB2, DB4, DB5).
    • Showcased reduced computational cost compared to traditional methods, enhancing suitability for low-cost systems.

    Conclusions:

    • The SPD manifold approach effectively extracts spatial structural information from EMG signals.
    • This novel method provides a significant advancement in myoelectric pattern recognition.
    • The approach offers a more efficient and accurate alternative for myoelectric control systems.