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

ESVM: evolutionary support vector machine for automatic feature selection and classification of microarray data.

Hui-Ling Huang1, Fang-Lin Chang

  • 1Department of Information Management, Jin Wen Institute of Technology, and Department of Anesthesiology, Tri-Service General Hospital, Taipei, Taiwan. hlhuang@jwit.edu.tw

Bio Systems
|February 7, 2007
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

Prediction-Guided Biotransformation of <i>p</i>-Hydroxyphenethyl Anisate into a Novel 3',4'-Dihydroxyphenethyl Anisate with Potent Anti-Inflammatory, Anti-Melanoma, and Antioxidant Activities.

Journal of microbiology and biotechnology·2026
Same author

Risk-adaptive therapy guided by dynamic ctDNA in nasopharyngeal carcinoma.

Nature·2026
Same author

Patient-reported outcomes from a phase 2 PLATINUM trial of nivolumab combination therapy sparing concurrent cisplatin in nasopharyngeal carcinoma.

Med (New York, N.Y.)·2026
Same author

Imaging Features of Patients with Hepatocellular Carcinoma and Portal Vein Tumor Thrombosis Surviving Beyond 1 Year After Combined Therapy.

Diagnostics (Basel, Switzerland)·2026
Same author

Prognostic Determinants and Treatment Strategies Associated with Long-Term Survival in Early-Stage Hepatocellular Carcinoma: A Retrospective Cohort Study.

Journal of hepatocellular carcinoma·2025
Same author

Applying quality indicators and multidisciplinary team care to improve long-term survival in early-stage hepatocellular carcinoma.

Asia-Pacific journal of oncology nursing·2025
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 introduces an evolutionary support vector machine (ESVM) for enhanced prediction accuracy. ESVM simultaneously optimizes feature selection and parameter tuning, achieving high accuracy in microarray classification.

Area of Science:

  • Bioinformatics
  • Machine Learning
  • Computational Biology

Background:

  • Support Vector Machines (SVMs) require manual feature selection and parameter tuning for optimal predictive performance.
  • Existing SVM approaches lack automatic internal relevant feature detection and treat parameter setting as a separate problem.

Purpose of the Study:

  • To propose an evolutionary approach (ESVM) for simultaneous optimization of feature selection and SVM parameter tuning.
  • To enhance the predictive accuracy and feature extraction capabilities of SVM-based classifiers.

Main Methods:

  • An intelligent genetic algorithm is employed for simultaneous optimization of automatic feature selection and SVM parameter tuning.
  • K-fold cross-validation is used to estimate generalization ability.

Related Experiment Videos

  • A frequency-based voting technique is utilized to identify the most informative gene subsets, considering model uncertainty.

    • Main Results:

    • ESVM achieved an average accuracy of 96.88% on 11 multi-class microarray datasets.
    • The method effectively identified a small subset of 10.0 informative genes.
    • The ESVM approach demonstrated superior prediction abilities compared to traditional SVMs.

    Conclusions:

    • ESVM offers an integrated solution for automatic feature selection and parameter optimization in SVM classifiers.
    • ESVM functions as both an accurate classifier and an adaptive feature extractor for bioinformatics problems.
    • The developed ESVM framework provides an efficient tool for applying various SVMs to bioinformatics challenges.