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

SGM-DETR: Semantic-Guided and Feature-Refined Transformer for Pine Wilt Disease Detection in Satellite Imagery.

Plants (Basel, Switzerland)·2026
Same author

Surface Engineering of Glutamic Acid Residues to Enhance the Thermostability of GH10 Xylanases.

Journal of agricultural and food chemistry·2026
Same author

Distance-Matched Spatially Separated Bimetallic Centers in a Covalent Organic Framework Accelerate Polysulfide Conversion in Lithium-Sulfur Batteries.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Lecanemab treatment improves B cell subpopulation immune homeostasis in patients with Alzheimer's disease.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
Same author

Clinical Evaluation of the Revised Biological and Clinical Staging Criteria for Alzheimer Disease in China.

Neurology·2026
Same author

Glymphatic system bridges peripheral and central nervous system changes in classic trigeminal neuralgia.

Brain communications·2026

Related Experiment Video

Updated: Jun 4, 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

398

MS-CLSTM: Myoelectric Manipulator Gesture Recognition Based on Multi-Scale Feature Fusion CNN-LSTM Network.

Ziyi Wang1, Wenjing Huang2, Zikang Qi1

  • 1School of Materials Science and Engineering, Central South University of Forestry and Technology, Changsha 410004, China.

Biomimetics (Basel, Switzerland)
|December 27, 2024
PubMed
Summary

This study introduces a novel deep learning model, MS-CLSTM, for advanced surface electromyography (sEMG) gesture recognition. The model effectively captures multi-scale features, improving control for myoelectric manipulators and prosthetic hands.

Keywords:
deep learningmulti-scale feature fusionreal-time predictionsEMG gesture recognition

More Related Videos

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

1.5K
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

2.6K

Related Experiment Videos

Last Updated: Jun 4, 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

398
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

1.5K
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

2.6K

Area of Science:

  • Biomedical Engineering
  • Machine Learning
  • Signal Processing

Background:

  • Surface electromyography (sEMG) signals are crucial for myoelectric control.
  • Deep learning enhances sEMG gesture recognition by automating feature extraction.
  • Single-scale networks struggle to capture both local and global patterns in sEMG data.

Purpose of the Study:

  • To develop a deep learning model for comprehensive sEMG gesture recognition.
  • To address the limitations of single-scale networks in capturing multi-scale sEMG features.
  • To improve the performance of myoelectric manipulator control.

Main Methods:

  • Proposed a multi-scale feature fusion deep learning model: MS-CLSTM (MS Block-ResCBAM-Bi-LSTM).
  • The MS Block utilizes different scale convolutional kernels to extract local, global, and inter-channel features.
  • ResCBAM module integrates attention mechanisms and residual networks to focus on relevant information and prevent overfitting.

Main Results:

  • Achieved high recognition accuracies: 86.66% on Ninapro DB2 and 83.27% on Ninapro DB4 datasets.
  • Demonstrated real-time gesture prediction accuracy up to 89% for myoelectric manipulators.
  • The proposed MS-CLSTM model shows superior performance in sEMG gesture recognition.

Conclusions:

  • The MS-CLSTM model offers an effective solution for sEMG gesture recognition.
  • This approach enhances control capabilities for prosthetic hands, robotic systems, and human-computer interaction.
  • Multi-scale feature fusion is key to improving the accuracy and robustness of sEMG-based control systems.