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

The disease burden of gastric cancer in China, 1990-2023: A comprehensive analysis and projections to 2035.

Clinics and research in hepatology and gastroenterology·2026
Same author

Integrative Multi-Omics Analysis Reveals Nutritional Metabolite Diversity and Regulatory Mechanisms in <i>Ocimum basilicum</i>.

Life (Basel, Switzerland)·2026
Same author

Terahertz Dielectric Characterization and Hybrid Debye-Lorentz Modeling of Silicone Rubber Composites for Composite Insulators.

Polymers·2026
Same author

Dietary fructose promotes MASH/HCC progression through enhanced intestinal HIF-2α-dependent iron absorption.

bioRxiv : the preprint server for biology·2026
Same author

Expansion and CAR engineering of granulocyte-monocyte progenitors for cellular immunotherapy.

Cell·2026
Same author

ENPP1 blockade with a humanized monoclonal antibody enhances renal repair after acute kidney injury.

Cell stem cell·2026

Related Experiment Video

Updated: Oct 14, 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

836

Dynamic Gesture Recognition Using Surface EMG Signals Based on Multi-Stream Residual Network.

Zhiwen Yang1,2, Du Jiang1,3,4, Ying Sun1,3,4

  • 1Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education, Wuhan University of Science and Technology, Wuhan, China.

Frontiers in Bioengineering and Biotechnology
|November 8, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces a new MResLSTM algorithm for dynamic gesture recognition using surface EMG signals. Combining EMG and acceleration data significantly improves artificial hand control accuracy and fluency in medical applications.

Keywords:
MResLSTMdeep neural networkdynamic gesture recognitionsEMGsignal fusion

More Related Videos

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.6K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

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

Published on: December 15, 2023

4.4K

Related Experiment Videos

Last Updated: Oct 14, 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

836
Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.6K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

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

Published on: December 15, 2023

4.4K

Area of Science:

  • Biomedical Engineering
  • Human-Computer Interaction
  • Robotics

Background:

  • Current gesture recognition for medical manipulators often focuses on static gestures, limiting natural human-computer interaction.
  • Existing methods using surface electromyography (sEMG) struggle with the dynamic movements required for dexterous manipulator control.

Purpose of the Study:

  • To develop a robust algorithm for accurate and stable dynamic hand gesture recognition.
  • To enhance the fluency and flexibility of manipulator control in assisted medical fields.
  • To improve human-computer interaction through advanced gesture decoding.

Main Methods:

  • A multi-stream residual network (MResLSTM) combining residual and convolutional long short-term memory (ConvLSTM) models was developed.
  • The architecture extracts global and deep spatiotemporal features, employing feature fusion for essential information retention.
  • Pointwise group convolution and channel shuffle strategies were utilized to optimize computational efficiency.

Main Results:

  • Fusion of sEMG and acceleration signals yielded superior gesture recognition compared to using sEMG alone.
  • The proposed MResLSTM algorithm achieved 93.52% accuracy on a custom dataset of six dynamic gestures.
  • State-of-the-art performance was demonstrated on the Ninapro DB1 dataset with 89.65% precision.

Conclusions:

  • The MResLSTM algorithm effectively performs dynamic gesture recognition, advancing manipulator control in healthcare.
  • The bionic calculation method enables continuous human-computer interaction and flexible manipulator control.
  • This research contributes to more natural and dexterous control of assistive devices.