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

Parameters selection in gene selection using Gaussian kernel support vector machines by genetic algorithm.

Yong Mao1, Xiao-Bo Zhou, Dao-Ying Pi

  • 1National Laboratory of Industrial Control Technology, Institute of Modern Control Engineering, Zhejiang University, Hangzhou 310027, China. ymao@iipc.zju.edu.cn

Journal of Zhejiang University. Science. B
|September 28, 2005
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

RGCNN-nnUNet: Recurrent group equivariant nnU-Net for robust brain tissue segmentation on stroke NCCT.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same author

Quantitative second harmonic generation microscopy for characterizing collagen remodeling in papillary thyroid carcinoma.

Journal of biomedical optics·2026
Same author

iS2C2: a cointelligent platform for mechanistic discovery of disease cellular crosstalk.

Signal transduction and targeted therapy·2026
Same author

Biophysical Characterization of a Novel KCNJ8 Rare Variant Linked With Inherited and Acquired J Wave Syndrome.

JACC. Clinical electrophysiology·2026
Same author

Obesity-driven phosphatidylethanolamine dysregulation impairs neuroimmune crosstalk and accelerates Alzheimer's pathogenesis.

Molecular neurodegeneration·2026
Same author

Disparities in breast cancer incidence and survival by age, race, and molecular subtype in US women.

NPJ breast cancer·2026
Same journal

Halotolerant plant growth-promoting bacteria <i>Enterobacter</i> sp. Av16 and <i>Acinetobacter</i> sp. Av23 enhance seed germination and seedling photosynthesis of <i>Apocynum pictum</i> under salt stress.

Journal of Zhejiang University. Science. B·2026
Same journal

Integrative analytical and statistical framework for optimization of multiplex qPCR detection of <i>TGFBI</i> mutations in refractive surgery candidates.

Journal of Zhejiang University. Science. B·2026
Same journal

Regenerative potential of Schneiderian membrane-derived mesenchymal stem cells in sinus floor elevation model and calvarial defect model.

Journal of Zhejiang University. Science. B·2026
Same journal

Esculetin attenuates migraine-like pain via CGRP suppression and meningeal mast cell modulation in rat models.

Journal of Zhejiang University. Science. B·2026
Same journal

Cell proliferation and differentiation during epidermis renewal.

Journal of Zhejiang University. Science. B·2026
Same journal

HENMT1: an RNA methyltransferase in biology and disease.

Journal of Zhejiang University. Science. B·2026
See all related articles

This study introduces an optimized parameter selection method for Support Vector Machine Recursive Feature Elimination (SVM-RFE) to improve cancer classification. The new approach enhances gene selection accuracy and achieves high classification performance on breast cancer and leukemia datasets.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Microarray analysis for cancer classification faces challenges due to high dimensionality and non-linearity.
  • Conventional linear statistical methods often yield suboptimal results for gene selection in cancer studies.

Purpose of the Study:

  • To propose a novel parameter optimization method for Support Vector Machine Recursive Feature Elimination (SVM-RFE) using Gaussian kernel SVMs.
  • To enhance the accuracy of gene selection and cancer classification in high-dimensional microarray data.

Main Methods:

  • Implemented a genetic algorithm to search for optimal parameters for SVM-RFE.
  • Utilized Gaussian kernel Support Vector Machines (SVMs) within the SVM-RFE framework.
  • Discussed fast implementation strategies for pragmatic application.

Related Experiment Videos

Main Results:

  • The proposed parameter selection method demonstrated effective gene selection capabilities.
  • Achieved high classification accuracies on hereditary breast cancer and acute leukemia datasets.
  • Outperformed common practices in parameter selection for SVM-RFE.

Conclusions:

  • The novel parameter optimization technique significantly improves gene selection for cancer classification.
  • The method offers a robust and accurate approach for analyzing complex genomic data.
  • This approach provides a valuable tool for advancing personalized cancer diagnostics.