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 Experiment Video

Updated: Aug 29, 2025

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

1.7K

EMG Data Augmentation for Grasp Classification Using Generative Adversarial Networks.

V Mendez, C Lhoste, S Micera

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |September 10, 2022
    PubMed
    Summary

    Generative adversarial networks (GANs) create synthetic electromyography (EMG) data to improve robotic hand control. This deep learning approach overcomes challenges of data collection for enhanced grasp classification performance.

    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

    An Investigation of Manifold-Based Direct Control for a Brain-to-Body Neural Bypass.

    IEEE open journal of engineering in medicine and biology·2024
    Same author

    First-passage time of a Brownian searcher with stochastic resetting to random positions.

    Physical review. E·2024
    Same author

    Implementation of an epicardial implantable MEMS sensor for continuous and real-time postoperative assessment of left ventricular activity in adult minipigs over a short- and long-term period.

    APL bioengineering·2024
    Same author

    Ergodic properties of Brownian motion under stochastic resetting.

    Physical review. E·2024
    Same author

    Cardiovascular response to closed-loop intraneural stimulation of the right vagus nerve: a proof-of-concept study.

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2023
    Same author

    Neural Stimulation Hardware for the Selective Intrafascicular Modulation of the Vagus Nerve.

    IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2023

    Area of Science:

    • Biomedical Engineering
    • Machine Learning
    • Rehabilitation Robotics

    Background:

    • Electromyography (EMG) signals are crucial for controlling robotic prosthetics.
    • Deep learning enhances EMG-based control but requires extensive training data.
    • Collecting large EMG datasets is challenging due to time constraints and muscle fatigue.

    Purpose of the Study:

    • To investigate a deep learning data augmentation strategy for EMG signal processing.
    • To utilize generative adversarial networks (GANs) for synthetic EMG data generation.
    • To improve the performance of grasp classification in EMG-controlled robotic hands.

    Main Methods:

    • Exploration of a deep learning-based data augmentation technique.
    • Implementation of generative adversarial networks (GANs) to synthesize high-quality EMG data.

    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

    714

    Related Experiment Videos

    Last Updated: Aug 29, 2025

    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

    1.7K
    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

    714
  • Evaluation of synthetic data's impact on grasp classification accuracy.

    • Main Results:

    • Generated synthetic EMG data using GANs demonstrated high fidelity.
    • Data augmentation with synthetic data led to improved grasp classification performance.
    • The proposed method effectively addresses the data scarcity issue in EMG-based control.

    Conclusions:

    • Generative adversarial networks offer a viable solution for augmenting EMG datasets.
    • Synthetic data generation can significantly enhance the capabilities of deep learning models for robotic hand control.
    • This approach holds promise for advancing the development of more responsive and intuitive prosthetic devices.