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

PD-1/PD-L1 inhibition after cryoablation is associated with improved tumor control and immunosuppressive microenvironment remodeling in Lewis lung adenocarcinoma.

Cryobiology·2026
Same author

Construction of a safe and controllable quality management model for "Internet + Nursing Services" based on HFMEA strategy.

Frontiers in medicine·2026
Same author

Predicting malignancy in solid thyroid nodules with no or punctate-linear enhancement on contrast-enhanced ultrasound: a retrospective analysis.

Quantitative imaging in medicine and surgery·2026
Same author

RHOV couples EMT-associated plasticity to cytoskeletal execution of invasion and metastasis.

Cell death discovery·2026
Same author

Genome-wide identification and functional characterization of MAPKK gene family in Zanthoxylum armatum DC. reveal its potential role in ecological adaptive evolution.

BMC genomics·2026
Same author

Prospective differentiation of difficult-to-diagnose thyroid nodules using shear wave elastography.

Journal of cancer research and therapeutics·2025

Related Experiment Video

Updated: May 30, 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

390

Gesture recognition from surface electromyography signals based on the SE-DenseNet network.

Ying Xiang1, Wei Zheng1, Jiajia Tang1

  • 1College of Ocean, Jiangsu University of Science and Technology, Zhenjiang, China.

Biomedizinische Technik. Biomedical Engineering
|January 28, 2025
PubMed
Summary

This study introduces an improved deep learning model for surface electromyography (sEMG) gesture recognition. The novel approach enhances accuracy and generalizability for human-computer interaction in rehabilitation technology.

Keywords:
DenseNetEMG signalattention mechanismdeep learninggesture recognition

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

43.2K
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: May 30, 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

390
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

43.2K
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
  • Rehabilitation Technology

Background:

  • Surface electromyography (sEMG) signals are crucial for developing natural human-computer interaction.
  • Current sEMG gesture recognition algorithms face challenges in global feature capture, computational complexity, and generalizability.
  • Advancements in machine learning and deep learning offer potential for improved sEMG-based gesture recognition.

Purpose of the Study:

  • To enhance gesture recognition using sEMG signals by improving global feature capture and model generalizability.
  • To develop a more robust and computationally efficient algorithm for personalized human-computer interaction.
  • To address limitations in existing sEMG gesture recognition models for rehabilitation applications.

Main Methods:

  • A fusion model combining Squeeze-and-Excitation Networks (SE) with DenseNet was proposed.
  • An attention mechanism was integrated between DenseBlock and Transition layers to prioritize important information.
  • The DenseNet-101 architecture was utilized as the backbone for optimal performance.

Main Results:

  • The proposed model achieved high accuracies of 85.93% on the NinaPro DB2 dataset and 82.39% on the NinaPro DB4 dataset.
  • Ablation studies confirmed that DenseNet-101 as the backbone yielded the best results.
  • The model demonstrated improved feature representation and effectively mitigated gradient vanishing.

Conclusions:

  • The developed fusion model exhibits superior robustness and generalizability compared to existing methods for sEMG gesture recognition.
  • This research offers novel insights for advancing sEMG signal-based gesture recognition applications, particularly in rehabilitation.
  • The findings pave the way for more natural and personalized human-computer interfaces.