Search research articles

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

Non-Adiabatic Effects on Excited States of Vinylidene Observed with Slow Photoelectron Velocity-Map Imaging.

Journal of the American Chemical Society·2016

Same author

Targeting Heparin to Collagen within Extracellular Matrix Significantly Reduces Thrombogenicity and Improves Endothelialization of Decellularized Tissues.

Biomacromolecules·2016

Same author

Association between sleep duration and the prevalence of hypertension in an elderly rural population of China.

Sleep medicine·2016

Same author

Association between passive smoking and hypertension in Chinese non-smoking elderly women.

Hypertension research : official journal of the Japanese Society of Hypertension·2016

Same author

Morphine versus methylprednisolone or aminophylline for relieving dyspnea in patients with advanced cancer in China: a retrospective study.

SpringerPlus·2016

Same author

Expression of Rab1A is upregulated in human lung cancer and associated with tumor size and T stage.

Aging·2016

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: Jan 13, 2026

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

A multi-scale dual-stream fusion network for high-accuracy sEMG-based gesture classification.

Dongyi He¹, Wei Liu², He Yan¹

¹School of Artificial Intelligence, Chongqing University of Technology, Chongqing, 400054, China.

Scientific Reports

|January 7, 2026

Summary

This study introduces a new deep learning model for surface electromyography (sEMG)-based gesture recognition. The Multi-Scale Dual-Stream Fusion Network (MSDS-FusionNet) improves accuracy by effectively combining time and frequency domain features.

Keywords:

Frequency-domain features Gesture recognition Surface electromyography (sEMG)Time-domain features

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

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jan 13, 2026

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

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Area of Science:

Biomedical Engineering
Machine Learning
Signal Processing

Background:

Deep learning is widely used for surface electromyography (sEMG)-based gesture recognition.
Existing methods struggle to fully utilize complementary information from time and frequency domains due to limitations in capturing multi-scale temporal dependencies and suboptimal fusion strategies.

Purpose of the Study:

To propose a novel deep learning framework, the Multi-Scale Dual-Stream Fusion Network (MSDS-FusionNet), for enhanced sEMG-based gesture classification accuracy and robustness.
To address limitations in current methods by effectively integrating temporal and frequency-domain features.

Main Methods:

Developed the Multi-Scale Dual-Stream Fusion Network (MSDS-FusionNet) incorporating Multi-Scale Mamba (MSM) modules for extracting multi-scale temporal features and Bi-directional Attention Fusion Module (BAFM) for feature fusion.
MSM modules utilize parallel convolutions and linear-time sequence modeling to capture diverse temporal patterns and dependencies.
BAFM employs bi-directional attention mechanisms to dynamically fuse complementary temporal and frequency-domain information.

Main Results:

MSDS-FusionNet achieved superior performance compared to state-of-the-art methods on the NinaPro dataset.
Demonstrated accuracy improvements of up to 2.41% (DB2), 2.46% (DB3), and 1.38% (DB4).
Attained final accuracies of 90.15% (DB2), 72.32% (DB3), and 87.10% (DB4).

Conclusions:

MSDS-FusionNet offers a robust and flexible solution for sEMG-based gesture recognition.
The proposed framework effectively addresses the complexities of recognizing intricate gestures.
Significant potential for applications in prosthetics, virtual reality, and assistive technologies.