|標題:||Boosting Evolutionary Support Vector Machine for Designing Tumor Classifiers from Microarray Data|
Koeberl, Dwight D.
Department of Biological Science and Technology
Institude of Bioinformatics and Systems Biology
|摘要:||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.|
|期刊:||2007 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE IN BIOINFORMATICS AND COMPUTATIONAL BIOLOGY|
|Appears in Collections:||Conferences Paper|