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

Medical Image Registration with Multi-Dilated Convolution and Quintuple Attention.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

AdaptiveEdge: Adaptive Model Update for Motor-Intent Decoding With Knowledge Distillation and Efficient EMG Sensor System.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2025
Same author

D2C-Morph: Brain regional segmentation based on unsupervised registration network with similarity analysis.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2025
Same author

CytoNet: an efficient dual attention based automatic prediction of cancer sub types in cytology studies.

Scientific reports·2024
Same author

Beyond the Microscope: A Technological Overture for Cervical Cancer Detection.

Diagnostics (Basel, Switzerland)·2023
Same author

Multiclass classification of imagined speech EEG using noise-assisted multivariate empirical mode decomposition and multireceptive field convolutional neural network.

Frontiers in human neuroscience·2023

Related Experiment Video

Updated: Jul 11, 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

546

A Novel Approach to Surface EMG-based Gesture Classification Using a Vision Transformer Integrated with Convolutive

Mustapha Deji Dere, Boreom Lee

    IEEE Journal of Biomedical and Health Informatics
    |November 6, 2023
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a new BSS-integrated convolution vision transformer (BSS-CViT) for electromyography (EMG) gesture classification. The BSS-CViT model achieved high accuracy, showing promise for real-time human-machine interface applications.

    More Related Videos

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    2.8K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    435

    Related Experiment Videos

    Last Updated: Jul 11, 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

    546
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    2.8K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    435

    Area of Science:

    • Biomedical Engineering
    • Machine Learning
    • Signal Processing

    Background:

    • Real-time human-machine interfaces (HMIs) require robust pattern recognition.
    • Electromyography (EMG) is used for gesture classification, with Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) being common, but Vision Transformers (ViTs) are less explored.
    • Preprocessing significantly impacts classification accuracy.

    Purpose of the Study:

    • To evaluate the effectiveness of a Vision Transformer (ViT) with and without an attention mechanism for motor intent decoding using EMG data.
    • To investigate the impact of various input features and convolutive blind source separation (BSS) preprocessing on ViT performance.
    • To develop and assess a BSS-integrated convolution Vision Transformer (BSS-CViT) model.

    Main Methods:

    • Utilized two open-access high-density surface EMG datasets with 34 and 21 hand gestures from 20 and 5 healthy subjects.
    • Applied various preprocessing techniques, including centering, optimal extension factors, and spatial whitening.
    • Integrated convolutive blind source separation (BSS) with a convolution Vision Transformer (CViT) architecture.

    Main Results:

    • Centering and optimal extension factors improved performance with raw input.
    • Spatial whitening increased model sensitivity to noise.
    • The best-performing BSS-CViT model achieved 96.61% and 91.98% accuracy on two test datasets.

    Conclusions:

    • The BSS-CViT model demonstrates high accuracy for EMG-based gesture classification.
    • This approach shows significant potential for advancing real-time HMI applications.
    • The study provides an open-source implementation for future research.