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

One probe, two chemistries: an orthogonal fluorescent sensing platform for glutathione and hydrazine in biological fluids and food samples.

Journal of materials chemistry. BĀ·2026
Same author

Decoding structural rigidity and charge-transfer polarization in barbituric-acid-based donor-Ļ€-acceptor chromophores.

RSC advancesĀ·2026
Same author

Explainability and Trust in Deep Learning for Cancer Imaging: Systematic Barriers, Clinical Misalignment, and a Translational Roadmap.

CancersĀ·2026
Same author

Interplay of Electronic Delocalization and Aggregation Dynamics in Decoding Metabolic Disease Biomarkers: Application to Screening of Biological Fluids and Intracellular Imaging.

Langmuir : the ACS journal of surfaces and colloidsĀ·2026
Same author

Clinical feasibility of intratracheal tracheostomy sealing using a novel sealing disc prototype.

Scientific reportsĀ·2026
Same author

Bisbenzimidazoles with a benzenediyl spacer: an efficient fluorophore for dihydrogen phosphate sensing and targeted living cell imaging.

Analytical methods : advancing methods and applicationsĀ·2026

Related Experiment Video

Updated: Oct 14, 2025

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

Voting-based 1D CNN model for human lower limb activity recognition using sEMG signal.

Ankit Vijayvargiya1,2, Khimraj3, Rajesh Kumar4

  • 1Department of Electrical Engineering, Malaviya National Institute of Technology, Jaipur, India. ankitvijayvargiya29@gmail.com.

Physical and Engineering Sciences in Medicine
|November 8, 2021
PubMed
Summary

A novel voting-based 1D CNN model accurately classifies lower limb movements from surface electromyography (sEMG) signals. This technique effectively reduces artifacts and improves recognition for both healthy and knee-abnormal subjects.

Keywords:
Convolutional neural networkDiscrete wavelet denoisingHealthcare monitoringLower limb activity recognitionOverlapping windowingSurface electromyography

More Related Videos

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
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.9K

Related Experiment Videos

Last Updated: Oct 14, 2025

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
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
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.9K

Area of Science:

  • Biomedical Engineering
  • Signal Processing
  • Machine Learning

Background:

  • Surface electromyography (sEMG) signals are crucial for human-machine interaction and diagnosing neuromuscular conditions.
  • Artifacts in sEMG recordings complicate accurate signal classification.
  • Distinguishing lower limb movements is essential for clinical and assistive applications.

Purpose of the Study:

  • To propose a multi-stage classification technique for identifying distinct lower limb movements using sEMG signals.
  • To evaluate the effectiveness of the proposed method in subjects with and without knee abnormalities.
  • To develop an accurate and robust system for lower limb activity recognition.

Main Methods:

  • Acquired sEMG data from leg muscles of 22 subjects (11 healthy, 11 with knee abnormality) performing walking, sitting leg extension, and standing leg flexion.
  • Applied discrete wavelet denoising to the fourth decomposition level for artifact reduction.
  • Segmented signals using overlapping windowing and employed four 1D Convolutional Neural Network (CNN) architectures.
  • Implemented a voting mechanism combining results from all four CNN models for final prediction.
  • Utilized nested threefold cross-validation for performance evaluation.

Main Results:

  • The voting-based 1D CNN model achieved high average classification accuracies: 99.35% for healthy subjects, 97.63% for subjects with knee abnormality, and 97.14% for pooled data.
  • The discrete wavelet denoising effectively reduced artifacts in the sEMG signals.
  • The multi-stage classification approach demonstrated superior performance compared to individual models.

Conclusions:

  • The proposed voting-based 1D CNN model is highly efficient and accurate for lower limb activity recognition using sEMG signals.
  • The method demonstrates robustness in classifying movements across subjects with varying knee conditions.
  • This technique offers a promising solution for advanced human-machine interfaces and clinical diagnostics.