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

Fulzerasib plus cetuximab in first-line KRAS<sup>G12C</sup>-mutated non-small-cell lung cancer (KROCUS): a single-arm, multicentre, phase 1b/2 trial.

The Lancet. Oncology·2026
Same author

Tetrastigma hemsleyanum alleviates febrile seizures by inhibiting HSPB1/Akt/NF-κB signaling via small extracellular vesicle-mediated astrocyte-microglia crosstalk.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026
Same author

Dynamic Covalent Surface Engineering of Highly Reactive Al-Li Alloy Powders for Propellant Application.

ACS applied materials & interfaces·2026
Same author

Clinicopathological characteristics and treatment outcomes of biliary neuroendocrine carcinoma: a single-center case series and literature review.

Frontiers in oncology·2026
Same author

Inhibition of ventral tegmental area projections to the paraventricular thalamus attenuates conditioned cues-induced heroin seeking behavior in rats.

Metabolic brain disease·2025
Same author

Risk factors and predictive model for postoperative pulmonary complications following pancreaticoduodenectomy: a retrospective cohort study.

Langenbeck's archives of surgery·2025

Related Experiment Video

Updated: Aug 22, 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

704

MSFF-Net: Multi-Stream Feature Fusion Network for surface electromyography gesture recognition.

Xiangdong Peng1, Xiao Zhou1, Huaqiang Zhu1

  • 1School of Software and Internet of Things Engineering, Jiangxi University of Finance and Economics, Nanchang, Jiangxi, China.

Plos One
|November 7, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces a new deep learning model, MSFF-Net, for surface electromyography (sEMG) gesture recognition. The novel approach enhances accuracy by integrating spatial and temporal features from sEMG signals.

More Related Videos

Multifunctional Setup for Studying Human Motor Control Using Transcranial Magnetic Stimulation, Electromyography, Motion Capture, and Virtual Reality
08:09

Multifunctional Setup for Studying Human Motor Control Using Transcranial Magnetic Stimulation, Electromyography, Motion Capture, and Virtual Reality

Published on: September 3, 2015

11.0K
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

43.5K

Related Experiment Videos

Last Updated: Aug 22, 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

704
Multifunctional Setup for Studying Human Motor Control Using Transcranial Magnetic Stimulation, Electromyography, Motion Capture, and Virtual Reality
08:09

Multifunctional Setup for Studying Human Motor Control Using Transcranial Magnetic Stimulation, Electromyography, Motion Capture, and Virtual Reality

Published on: September 3, 2015

11.0K
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

43.5K

Area of Science:

  • Biomedical Engineering
  • Machine Learning
  • Human-Computer Interaction

Background:

  • Surface electromyography (sEMG) gesture recognition is crucial for human-computer interaction.
  • Current deep learning methods often focus on either spatial or temporal features, neglecting comprehensive spatial-electrode relationships.
  • Improving sEMG gesture recognition accuracy remains a significant research challenge.

Purpose of the Study:

  • To propose a novel multi-stream feature fusion network (MSFF-Net) for enhanced sEMG gesture recognition.
  • To effectively integrate multi-dimensional spatial and temporal features from sEMG signals.
  • To improve the accuracy of sEMG-based gesture recognition by considering electrode distribution and signal morphology.

Main Methods:

  • Developed a Multi-stream CNN and ResCBAM for extracting multi-dimensional spatial features (signal morphology, electrode space, feature map space).
  • Implemented a view aggregation network (early and late fusion) to fuse multi-view depth features.
  • Utilized a divide-and-conquer strategy to learn relationships between muscle regions and gestures.

Main Results:

  • The MSFF-Net model demonstrated superior performance in gesture recognition accuracy across multiple subjects.
  • Experiments were conducted using sEMG data from 12 sensors from NinaPro's DB2 and DB4 sub-databases.
  • The proposed model outperformed existing methods in validation experiments.

Conclusions:

  • The MSFF-Net model offers a significant advancement in sEMG gesture recognition accuracy.
  • Comprehensive feature fusion, considering spatial and temporal aspects, is key to improving performance.
  • This approach holds promise for more sophisticated human-computer interfaces.