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

Microarray data classification using automatic SVM kernel selection.

Jesmin Nahar1, Shawkat Ali, Yi-Ping Phoebe Chen

  • 1Faculty of Science and Technology, Deakin University, Victoria, Australia.

DNA and Cell Biology
|August 10, 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

Significant Land Cover Transitions and Regional Acceleration at the Continental Scale of Africa over the Last Four Decades.

Sensors (Basel, Switzerland)·2026
Same author

Diversity and Pathogenicity of <i>Neopestalotiopsis</i> Species Associated with Strawberry Leaf Spot and Fruit Rot in Nova Scotia.

Journal of fungi (Basel, Switzerland)·2026
Same author

MULGONET: An interpretable neural network framework to integrate multi-omics data for cancer recurrence prediction and biomarker discovery.

Fundamental research·2026
Same author

Establishing the Asia & Pacific Bioinformatics Joint Congress: a historic milestone in regional bioinformatics collaboration.

Briefings in bioinformatics·2025
Same author

Changes in Environmental Conditions Differentially Affect the Bacterial Microbiome Communities in Different Apple Fruit Tissues.

Environmental microbiology reports·2025
Same author

Diversity, Virulence, and Fungicide Sensitivity of <i>Colletotrichum</i> Species Associated with Apple Bitter Rot in Nova Scotia.

Plant disease·2025

Selecting the best kernel for Support Vector Machines (SVM) is crucial for accurate microarray data classification in clinical applications. A rule-based approach proved most effective for automatic kernel selection in SVM-based patient diagnosis.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Medical Informatics

Background:

  • Microarray data classification is vital for clinical applications.
  • Machine learning, particularly Support Vector Machines (SVM), is frequently used for this task.
  • Choosing the optimal kernel for SVM is a significant challenge in microarray analysis.

Purpose of the Study:

  • To investigate the best kernel selection methods for Support Vector Machines (SVM) in microarray data classification.
  • To address the challenge of selecting the most effective kernel for patient diagnosis using SVM.

Main Methods:

  • Utilized Support Vector Machine (SVM), a state-of-the-art kernel-based algorithm.
  • Proposed three solutions for kernel selection based on data visualization and quantitative measures.

Related Experiment Videos

  • Evaluated proposed solutions across diverse microarray datasets.

    • Main Results:

    • Identified that a rule-based approach is highly effective for automatic kernel selection.
    • Demonstrated the utility of the proposed methods in classifying microarray data for patient diagnosis.
    • Quantitative measures and data visualization guided the kernel selection process.

    Conclusions:

    • A rule-based approach offers a robust solution for automatic kernel selection in SVM for microarray data.
    • Effective kernel selection using this approach can improve patient diagnosis accuracy.
    • This method enhances the clinical applicability of machine learning in analyzing gene expression data.