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 Experiment Videos

Signal-dependent wavelets for electromyogram classification.

A Maitrot1, M F Lucas, C Doncarli

  • 1Institut de Recherche en Communication et Cybernétique de Nantes, France.

Medical & Biological Engineering & Computing
|November 1, 2005
PubMed
Summary
This summary is machine-generated.

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

Multiparametric assessment of bone health in metastatic hormone-sensitive prostate cancer patients receiving androgen deprivation + enzalutamide ± zoledronic acid (BonEnza study).

Bone·2026
Same author

A multiomic framework for predicting laryngo-esophageal dysfunction following induction chemotherapy in hypopharyngeal-laryngeal carcinoma.

ESMO open·2025
Same author

A Biophysical-Model-Informed Source Separation Framework For EMG Decomposition.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Neural determinants of the increase in muscle strength and force steadiness of the untrained limb following a 4 week unilateral training.

The Journal of physiology·2025
Same author

NeuroNella: Automatic identification of neural activity from multielectrode arrays with blind source separation.

Journal of neural engineering·2025
Same author

Changes in body composition in early breast cancer patients treated with aromatase inhibitors.

Journal of endocrinological investigation·2024

This study introduces an optimized wavelet transform for classifying surface electromyogram (EMG) signals. The novel method accurately distinguishes EMG signals with varying motor unit synchronisation, outperforming existing techniques.

Area of Science:

  • Biomedical Engineering
  • Signal Processing
  • Neuroscience

Background:

  • Surface electromyogram (EMG) signals are complex and require robust classification methods.
  • Accurate EMG signal classification is crucial for various applications, including diagnostics and prosthetics.
  • Existing methods often struggle with subtle variations in signal characteristics like motor unit synchronisation.

Purpose of the Study:

  • To propose an efficient supervised classification method for surface EMG signals.
  • To develop an optimized representation space for EMG signal analysis.
  • To enhance the accuracy of distinguishing EMG signals based on motor unit synchronisation.

Main Methods:

  • Utilized the discrete dyadic wavelet transform for EMG signal representation.

Related Experiment Videos

  • Developed a feature space from the marginals of the wavelet decomposition.
  • Designed a mother wavelet optimized to minimize classification error on a training set.
  • Applied the method to simulated surface EMG signals with varying degrees of short-term synchronisation.

    • Main Results:

    • The proposed method achieved an 8% misclassification rate in distinguishing EMG signals with a 10% difference in synchronisation.
    • Demonstrated superior performance compared to spectral-based classification (approx. 33% error) and standard Daubechies wavelet classification (21% error).
    • The optimized feature space effectively captured signal characteristics relevant for classification.

    Conclusions:

    • The optimized wavelet-based approach provides an efficient and accurate method for supervised surface EMG classification.
    • This technique offers significant improvements over conventional methods, particularly for signals with subtle synchronisation differences.
    • The adaptable feature space makes the method broadly applicable across diverse surface EMG classification tasks.