Academic Journals Database
Disseminating quality controlled scientific knowledge

REVIEW ON FEATURE SELECTION TECHNIQUES AND THE IMPACT OF SVM FOR CANCER CLASSIFICATION USING GENE EXPRESSION PROFILE

ADD TO MY LIST
 
Author(s): G.Victo Sudha George | Dr. V.Cyril Raj

Journal: International Journal of Computer Science and Engineering Survey
ISSN 0976-3252

Volume: 2;
Issue: 3;
Start page: 16;
Date: 2011;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Microarray | feature selection | cancer classification | integrative gene selection.

ABSTRACT
The DNA microarray technology has modernized the approach of biology research in such a way thatscientists can now measure the expression levels of thousands of genes simultaneously in a singleexperiment. Gene expression profiles, which represent the state of a cell at a molecular level, have greatpotential as a medical diagnosis tool. But compared to the number of genes involved, available trainingdata sets generally have a fairly small sample size for classification. These training data limitationsconstitute a challenge to certain classification methodologies. Feature selection techniques can be usedto extract the marker genes which influence the classification accuracy effectively by eliminating the unwanted noisy and redundant genes This paper presents a review of feature selection techniques that havebeen employed in micro array data based cancer classification and also the predominant role of SVMfor cancer classification.

Tango Rapperswil
Tango Rapperswil

     Save time & money - Smart Internet Solutions