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

Neural network analysis of the EMG interference pattern

E W Abel1, P C Zacharia, A Forster

  • 1School of Biomedical Engineering, University of Dundee, UK.

Medical Engineering & Physics
|January 1, 1996
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

Stroke recovery patterns and predictors in India: A post-hoc analysis from the ATTEND trial.

Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association·2026
Same author

In ovo sexing and genotyping using PCR techniques: a contribution to the 3R principles in chicken breeding.

Scientific reports·2026
Same author

Vaccine microarray patch self-administration: An innovative approach to improve pandemic and routine vaccination rates.

Vaccine·2023
Same author

Evaluation of the self-administration potential of high-density microarray patches to human skin: A preliminary study.

Human vaccines & immunotherapeutics·2023
Same author

Computed diffusion-weighted imaging in patients with transient neurovascular symptoms with and without ischemic infarction.

Journal of neuroradiology = Journal de neuroradiologie·2023
Same author

Awareness, attitudes and acceptability of the HPV vaccine among female university students in Morocco.

PloS one·2022
Same journal

Development and experimental characterization of a cadaveric stance simulator for residual limb biomechanics.

Medical engineering & physics·2026
Same journal

Rapid personalized computational modeling of the wrist.

Medical engineering & physics·2026
Same journal

SHAP-enabled explainable AI framework for clinical interpretation of valvular heart diseases via digital acoustic features.

Medical engineering & physics·2026
Same journal

Three-dimensional motion analysis of a total wrist prosthesis during the dart-throwing motion: a cadaveric study.

Medical engineering & physics·2026
Same journal

Patient-specific left ventricular hypertrophy under severe hypertension: mechanistic insights from Hill-type computational simulations.

Medical engineering & physics·2026
Same journal

Enabling laboratory-based personalization of musculoskeletal spine models: a standardized rail-guided ultrasound method.

Medical engineering & physics·2026
See all related articles

Artificial neural networks show promise for classifying electromyography (EMG) signals in neuromuscular disorders. Supervised networks achieved 60-80% diagnostic accuracy, outperforming unsupervised methods.

Area of Science:

  • Biomedical Engineering
  • Computational Neuroscience
  • Neurology

Background:

  • Electromyography (EMG) signal analysis is crucial for diagnosing neuromuscular disorders.
  • Artificial neural networks (ANNs) offer advanced pattern recognition capabilities for complex biological signals.

Purpose of the Study:

  • To evaluate the performance of various ANNs in classifying EMG signals from healthy individuals and patients with myopathic and neuropathic conditions.
  • To compare the diagnostic accuracy of supervised and unsupervised ANN models using different EMG signal parameters.

Main Methods:

  • EMG interference patterns (IP) were recorded from the biceps under maximum voluntary contraction in 50 subjects.
  • Signal quantification involved turns analysis, small segments analysis, and frequency analysis.

Related Experiment Videos

  • Supervised ANNs (IBPN, RBN, INQ) and unsupervised SOFM were trained and tested.

    • Main Results:

    • Supervised networks achieved diagnostic yields of 60-80% when using parameters from turns and small segments analysis.
    • Frequency analysis parameters yielded comparable results to other methods.
    • Unsupervised SOFM performance was generally lower than supervised networks.
    • Inclusion of personal data (sex, age) did not enhance diagnostic performance.

    Conclusions:

    • Supervised ANNs demonstrate potential for accurate EMG signal classification in diagnosing neuromuscular disorders.
    • Specific parameter combinations from signal quantification significantly influence diagnostic accuracy.
    • Further research may optimize ANN architectures and feature selection for improved diagnostic performance.