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

Learning systems in biosignal analysis

C N Schizas1, C S Pattichis

  • 1Department of Computer Science, University of Cyprus, Nicosia. schizas@turing.cs.ucy.ac.cy

Bio Systems
|January 1, 1997
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

Position Paper: Artificial Intelligence in Medical Image Analysis: Advances, Clinical Translation, and Emerging Frontiers.

IEEE journal of biomedical and health informatics·2025
Same author

Two-stage approach for risk estimation of fetal trisomy 21 and other aneuploidies using computational intelligence systems.

Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology·2017
Same author

Adaptive emergency scenery video communications using HEVC for responsive decision support in disaster incidents.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2016
Same author

Prediction of the time period of stroke based on ultrasound image analysis of initially asymptomatic carotid plaques.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2016
Same author

Electronic Health Record Application Support Service Enablers.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2016
Same author

Measurement of ultrasonic diaphragmatic motion.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2016
Same journal

Ruliological Resilience: Pattern Restoration and Robustness in Wolfram Patterns. A Basis for Regeneration, Not Just in Cone Shells?

Bio Systems·2026
Same journal

The quantum-to-classical transducer: A thermodynamic and quantum mechanical framework for the emergence of bioenergetics.

Bio Systems·2026
Same journal

Forward-backward gene expression binarization for boolean state inference over a known regulatory network.

Bio Systems·2026
Same journal

Partial-label metric ceilings for evaluating gene regulatory networks inferred from single-cell foundation models.

Bio Systems·2026
Same journal

The impedance mismatch theory: A non-equilibrium thermodynamic framework for a shared energetic stress pathway in neurodegeneration.

Bio Systems·2026
Same journal

Immune signal-status misclassification: A theoretical framework for biological status assignment and failed status resolution.

Bio Systems·2026
See all related articles

This study compares machine learning algorithms for classifying electromyographic (EMG) data. Self-organizing feature map and genetics-based machine learning showed high diagnostic accuracy, outperforming K-means for biosignal analysis.

Area of Science:

  • Biomedical Engineering
  • Computational Neuroscience
  • Machine Learning

Background:

  • Electromyographic (EMG) signal analysis is crucial for diagnosing neuromuscular disorders.
  • Artificial neural networks (ANN) have shown promise in EMG data classification.
  • Exploring alternative machine learning algorithms is essential for improving diagnostic performance.

Purpose of the Study:

  • To evaluate the practical application and diagnostic performance of Self-Organizing Feature Map (SOFM), Genetics-Based Machine Learning (GBML), and K-means nearest neighbor clustering algorithms for EMG data classification.
  • To compare the effectiveness of these algorithms across different feature vector configurations and disease group numbers.
  • To assess the generalizability of these machine learning paradigms for developing biosignal analysis diagnostic systems.

Related Experiment Videos

Main Methods:

  • Applied SOFM, GBML, and K-means algorithms to a dataset of 720 macro EMG recordings from normal subjects and patients with motor neuron disease, Becker's muscular dystrophy, and spinal muscular atrophy.
  • Extracted mean and standard deviation of amplitude, area, average power, and duration as features, creating both four- and eight-input feature vectors.
  • Investigated three-class models (excluding spinal muscular atrophy) and four-class models to account for group heterogeneity.

Main Results:

  • SOFM and GBML models achieved comparable diagnostic performance, with 80-90% correct classifications on the evaluation set.
  • K-means nearest neighbor algorithm models yielded lower correct classification rates.
  • All three learning paradigms demonstrated improved performance with three-class models compared to four-class models, and similar performance between eight- and four-input feature vectors.

Conclusions:

  • SOFM and GBML algorithms offer robust diagnostic performance for EMG data classification, comparable to ANNs.
  • The choice of algorithm, number of disease classes, and feature vector design impacts diagnostic accuracy.
  • The proposed methodology provides a framework for developing practical diagnostic systems for biosignal analysis.