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 Video

Updated: Apr 28, 2026

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

8.7K

Quality assessment of data discrimination using self-organizing maps.

Alexey Mekler1, Dmitri Schwarz1

  • 1The Bonch-Bruevich Saint-Petersburg State University of Telecommunications, 61, Moika, 191186 Saint-Petersburg, Russia.

Journal of Biomedical Informatics
|June 14, 2014
PubMed
Summary

This study introduces novel methods for feature selection using self-organizing maps (SOMs) to evaluate data discrimination power. These techniques effectively assess feature sets, even for complex, nonlinear data, aiding in efficient variable selection for classification.

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

Calculation of EEG correlation dimension: large massifs of experimental data.

Computer methods and programs in biomedicineยท2008
See all related articles

Area of Science:

  • Data Science
  • Machine Learning
  • Pattern Recognition

Background:

  • Effective data classification relies on selecting optimal feature subsets.
  • Feature sets should be concise yet provide reliable class discrimination.
  • Evaluating the discriminating power of variable sets is crucial for feature selection.

Purpose of the Study:

  • To present a novel approach for feature selection.
  • To introduce two methods for evaluating the data discriminating power of feature sets.
  • To enable comparison between different sets of variables for improved classification.

Main Methods:

  • Utilizes self-organizing maps (SOMs) for data visualization and analysis.
  • Introduces novel exponents measuring data clusterization degree on SOMs.
Keywords:
Artificial intelligenceArtificial neural networksClassificationData miningFeature selectionSelf-organizing maps

More Related Videos

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.2K

Related Experiment Videos

Last Updated: Apr 28, 2026

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

8.7K
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.2K
  • Employs two distinct methods: comparing intraclass/interclass distances and analyzing nearest neighbors of Best Matching Units (BMUs).

    • Main Results:

    • Two new methods for evaluating feature set discriminating power are proposed.
    • Both methods are based on self-organizing maps and clusterization exponents.
    • The methods effectively assess feature sets, including those providing nonlinear discrimination.

    Conclusions:

    • The presented methods offer a robust way to evaluate feature set discriminating power.
    • These approaches are particularly useful when dealing with nonlinear data discrimination.
    • The findings support more efficient and reliable feature selection in data classification tasks.