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

A support vector machine using the lazy learning approach for multi-class classification.

E Comak1, A Arslan

  • 1Department of Computer Engineering, Engineering and Architecture Faculty, Selcuk University, Konya, Turkey. ecomak@selcuk.edu.tr

Journal of Medical Engineering & Technology
|March 15, 2006
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

Pediatric metacarpal and metatarsal fracture in pediatric emergency department.

European journal of trauma and emergency surgery : official publication of the European Trauma Society·2026
Same author

Hazards related to the presence of paracetamol in the environment - ultrastructural analysis of the midgut epithelium of tardigrade Hypsibius exemplaris (Eutardigrada, Hypsibiidae).

Aquatic toxicology (Amsterdam, Netherlands)·2025
Same author

Production, performance and emission of biodiesel from a mixture of castor oil and neem oil.

RSC advances·2025
Same author

Analysis of the protective effect of hydrogen sulfide over time in ischemic rat skin flaps.

Annales de chirurgie plastique et esthetique·2025
Same author

Effect of hyperbaric oxygen in hepatopulmonary syndrome: an innovative experimental study.

European review for medical and pharmacological sciences·2024
Same author

The value of potential immunohistochemical biomarkers and clinicopathological findings in predicting response to neoadjuvant chemotherapy in breast cancer.

European review for medical and pharmacological sciences·2022
Same journal

News and Product Update.

Journal of medical engineering & technology·2026
Same journal

PMMA based ultra miniaturized implantable antenna for biotelemetry applications.

Journal of medical engineering & technology·2026
Same journal

Comparative machine learning for accurate EEG-based epileptic seizure state classification using sub-band analysis.

Journal of medical engineering & technology·2026
Same journal

Genetic algorithm-optimized machine learning approaches for EEG-based silent speech decoding.

Journal of medical engineering & technology·2026
Same journal

Power transition signatures of vibroarthrographic spectrograms for diagnosing knee joint pathologies.

Journal of medical engineering & technology·2026
Same journal

News and product update.

Journal of medical engineering & technology·2026
See all related articles

Least squares support vector machines (LS-SVMs) with lazy learning classify data in challenging regions for multi-class problems. This machine learning technique offers results comparable to fuzzy LS-SVMs.

Area of Science:

  • Machine Learning
  • Statistical Learning
  • Data Classification

Background:

  • Support Vector Machines (SVMs) are a powerful machine learning technique.
  • Traditional SVMs involve solving complex quadratic programming problems.
  • Classifying data in unclassifiable regions, especially in multi-class scenarios, presents a challenge.

Purpose of the Study:

  • To develop a novel machine learning technique using least squares support vector machines (LS-SVMs) combined with the lazy learning approach.
  • To address the challenge of multi-class classification in unclassifiable regions.
  • To compare the performance of LS-SVMs with lazy learning against fuzzy LS-SVMs.

Main Methods:

  • Least Squares Support Vector Machines (LS-SVMs) were implemented.

Related Experiment Videos

  • The lazy learning approach, a local and memory-based technique, was utilized.
  • LS-SVMs were formulated using a set of linear equations, differing from the quadratic programming of standard SVMs.
  • The method was applied to multi-class classification tasks in unclassifiable regions.

    • Main Results:

    • LS-SVMs with the lazy learning approach demonstrated effectiveness in classifying data within unclassifiable regions.
    • The developed technique achieved results comparable to fuzzy LS-SVMs in multi-class classification.
    • The use of linear equations in LS-SVMs offers a computational alternative to quadratic programming.

    Conclusions:

    • Least squares support vector machines combined with the lazy learning approach provide a viable and effective method for multi-class classification, particularly in challenging data regions.
    • This approach serves as a competitive alternative to fuzzy inference systems for specific classification tasks.
    • The study highlights the potential of LS-SVMs for simplifying computations in machine learning classification problems.