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

Using Tomoauto: A Protocol for High-throughput Automated Cryo-electron Tomography.

Journal of visualized experiments : JoVE·2016
Same author

MiR-15a contributes abnormal immune response in myasthenia gravis by targeting CXCL10.

Clinical immunology (Orlando, Fla.)·2016
Same author

Minicells, Back in Fashion.

Journal of bacteriology·2016
Same author

A new variant of rabbit hemorrhagic disease virus G2-like strain isolated in China.

Virus research·2016
Same author

Tumour-suppressive role of PTPN13 in hepatocellular carcinoma and its clinical significance.

Tumour biology : the journal of the International Society for Oncodevelopmental Biology and Medicine·2016
Same author

Gonyautoxin 1/4 aptamers with high-affinity and high-specificity: From efficient selection to aptasensor application.

Biosensors & bioelectronics·2016
Same journal

Peripheral and central vestibular neuromodulation improve postural control in adolescent idiopathic scoliosis: a randomized, sham-controlled, multi-arm intervention study.

Journal of neuroengineering and rehabilitation·2026
Same journal

Ankle-foot orthosis mechanical testing: a scoping review.

Journal of neuroengineering and rehabilitation·2026
Same journal

Neuromechanical synergy patterns explain metabolic efficiency differences during the sit-to-walk transition.

Journal of neuroengineering and rehabilitation·2026
Same journal

The classification of walking and phases of gait using EEG: a scoping review.

Journal of neuroengineering and rehabilitation·2026
Same journal

Biohybrid cochlear implants: neural interfaces, regenerative pathways, and translational benchmarks.

Journal of neuroengineering and rehabilitation·2026
Same journal

Transcutaneous spinal stimulation with upper extremity robotic training in chronic stroke and spinal cord injury: individual neurophysiological and clinical responses.

Journal of neuroengineering and rehabilitation·2026
See all related articles

Related Experiment Video

Updated: May 7, 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

279

Exploring pattern-specific components associated with hand gestures through different sEMG measures.

Yangyang Yuan1, Jionghui Liu2, Chenyun Dai3

  • 1School of Information Science and Technology, Fudan University, Shanghai, 200433, China.

Journal of Neuroengineering and Rehabilitation
|December 31, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a method to improve gesture recognition in human-machine interaction using surface electromyography (sEMG) signals. By separating individual-specific from gesture-specific patterns, the new approach enhances cross-user accuracy in recognizing intended movements.

Keywords:
Auto-encodeFeature projectionGesture recognitionSurface electromyography

More Related Videos

Author Spotlight: Deciphering the Cognitive and Neural Mechanisms of Gesture in Communication
07:18

Author Spotlight: Deciphering the Cognitive and Neural Mechanisms of Gesture in Communication

Published on: January 26, 2024

752
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

1.4K

Related Experiment Videos

Last Updated: May 7, 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

279
Author Spotlight: Deciphering the Cognitive and Neural Mechanisms of Gesture in Communication
07:18

Author Spotlight: Deciphering the Cognitive and Neural Mechanisms of Gesture in Communication

Published on: January 26, 2024

752
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

1.4K

Area of Science:

  • Biomedical Engineering
  • Human-Computer Interaction
  • Signal Processing

Background:

  • Surface electromyography (sEMG) is vital for human-machine interaction, but subject-specific signal variations hinder cross-user gesture recognition.
  • Existing models often fail with new users due to inherent individual differences in sEMG signals.

Purpose of the Study:

  • To hypothesize and validate the existence of pattern-specific components in sEMG signals, independent of individual users.
  • To develop a generalizable gesture recognition model for cross-subject scenarios by isolating these pattern-specific components.
  • To compare the efficacy of different sEMG feature types (waveform, time-domain, frequency-domain) in capturing pattern-specific information.

Main Methods:

  • Utilized an auto-encoder to disentangle subject-specific and pattern-specific components from sEMG data.
  • Developed a general gesture recognition model using the extracted pattern-specific components.
  • Analyzed and compared pattern-specific information across signal waveform, time-domain, and frequency-domain features.
  • Visualized pattern-specific components using heatmaps and explored their physiological interpretability.

Main Results:

  • Successfully validated the hypothesis of pattern-specific components in sEMG signals.
  • The combination of time- and frequency-domain features yielded the highest gesture classification accuracy (84.3%).
  • Frequency-domain features demonstrated superior performance individually and were most effective for component separation.
  • Visualizations confirmed the physiological relevance of pattern-specific components, correlating with muscle activation areas.

Conclusions:

  • The proposed method effectively separates gesture-specific patterns from individual variations in sEMG signals, enabling robust cross-subject gesture recognition.
  • Combining time- and frequency-domain features offers the most promising approach for accurate and generalizable sEMG-based gesture classification.
  • Frequency-domain features are particularly suitable for extracting generalizable gesture patterns, with potential for further physiological interpretation.