Boosting evolutionary support vector machine for designing tumor classifiers from microarray data

Hui Ling Huang, Yi Hsiung Chen, Dwight D. Koeberl, Shinn-Ying Ho

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Since there are multiple sets of relevant genes having the same high accuracy in fitting training data called model uncertainty, to identify a small set of informative genes from microarray data for designing an accurate tumor classifier for unknown samples is intractable. Support vector machine (SVM), a supervised machine learning technique, is one of the methods successfully applied to cancer diagnosis problems. This study proposes an SVM-based classifier with automatic feature selection associated with a boosting strategy. The proposed boosting evolutionary support vector machine (named BESVM) hybridizes the advantages of SVM, boosting using a majority-voting ensemble and an intelligent genetic algorithm for gene selection. The merits of the BESVM-based classifier are threefold: 1) a small set of used genes, 2) accurate test classification using leave-one-out cross-validation, and 3) robust performance by avoiding overfitting training data. Five benchmark datasets were used to evaluate the BESVM-based classifier. Simulation results reveal that BESVM performs well having a mean accuracy 94.26% using only 10.1 genes averagely, compared with the existing SVM and non-SVM based classifiers.

Original languageEnglish
Title of host publication2007 IEEE Symposium on Computational Intelligence and Bioinformatics and Computational Biology, CIBCB 2007
Pages32-38
Number of pages7
DOIs
StatePublished - 1 Dec 2007
Event2007 4th IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2007 - Honolulu, HI, United States
Duration: 1 Apr 20075 Apr 2007

Publication series

Name2007 IEEE Symposium on Computational Intelligence and Bioinformatics and Computational Biology, CIBCB 2007

Conference

Conference2007 4th IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2007
CountryUnited States
CityHonolulu, HI
Period1/04/075/04/07

Fingerprint Dive into the research topics of 'Boosting evolutionary support vector machine for designing tumor classifiers from microarray data'. Together they form a unique fingerprint.

Cite this