Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Dec 10, 2025

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

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

Published on: March 28, 2025

Data Augmentation of Surface Electromyography for Hand Gesture Recognition.

Panagiotis Tsinganos^1,2, Bruno Cornelis^2,3, Jan Cornelis²

¹Department of Electrical and Computer Engineering, University of Patras, 26504 Patras, Greece.

Sensors (Basel, Switzerland)

|September 3, 2020

Summary

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

Do deep learning models learn beyond average gait? A comparison of architectures, kinematic representations, and marker sparsity for vertical ground reaction force prediction.

Gait & posture·2026

Same author

Construct validation of the vitality capacity domains 'energy and metabolism' and 'neuromuscular function' in relation to locomotor capacity and quality of life in community-dwelling middle-aged and older adults.

GeroScience·2026

Same author

Dynamics of brain-muscle interaction with neuromuscular fatigability: systematic review.

Frontiers in physiology·2026

Same author

Fractured Full-Arch Tooth-Supported Zirconia Bridge: Thin Design, Surface Damage, and Excessive Cement Layer Thickness.

Reports (MDPI)·2026

Same author

Evaluating the Accuracy and Repeatability of Mobile 3D Imaging Applications for Breast Phantom Reconstruction.

Sensors (Basel, Switzerland)·2025

Same author

Insights on the User Experience and Feasibility of an Electromyography-Driven Exergame Combined With Blood Flow Restriction for Strength Training in Hospitalized Older Adults: Mixed Methods Randomized Controlled Feasibility Study.

JMIR serious games·2025

Data augmentation techniques like signal magnitude warping and wavelet decomposition significantly improve electromyography (EMG) signal classification accuracy. These methods address data scarcity in EMG-based gesture recognition, enhancing model performance.

Area of Science:

Biomedical Engineering
Signal Processing
Machine Learning

Background:

Electromyography (EMG)-based gesture recognition applications are expanding.
Limited data availability is a persistent challenge in EMG research.
Data augmentation is crucial for improving model performance with scarce data.

Purpose of the Study:

To evaluate existing and novel data augmentation strategies for surface electromyography (sEMG) signals.
To compare the effectiveness of different augmentation methods using various metrics.
To identify optimal augmentation techniques for enhancing EMG-based gesture recognition.

Main Methods:

Evaluation of existing augmentation methods: additive noise, overlapping windows.
Assessment of novel augmentation techniques: magnitude warping, wavelet decomposition, synthetic sEMG models.

Keywords:

CNN data augmentation deep learning electromyography hand gesture recognition sEMG

More Related Videos

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

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

Published on: April 21, 2023

Extraction of the EPP Component from the Surface EMG

Extraction of the EPP Component from the Surface EMG

Published on: December 16, 2009

Related Experiment Videos

Last Updated: Dec 10, 2025

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

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

Published on: March 28, 2025

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

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

Published on: April 21, 2023

Extraction of the EPP Component from the Surface EMG

Extraction of the EPP Component from the Surface EMG

Published on: December 16, 2009

Performance metrics included classification accuracy, silhouette score, and Davies-Bouldin index.

Main Results:

Signal magnitude warping and wavelet decomposition increased classification accuracy by up to 16% on benchmark datasets.
These methods demonstrated significant improvements in distinguishing between different gestures.
A 1% increase in classification accuracy was achieved for a state-of-the-art hand gesture recognition model.

Conclusions:

Novel data augmentation methods, particularly signal magnitude warping and wavelet decomposition, are effective for sEMG data.
These techniques substantially improve the accuracy of EMG-based gesture recognition systems.
Addressing data scarcity through advanced augmentation is key to advancing EMG applications.