Comparative Study of Filter Feature Selection in Gene Expression Classification using Support Vector Machine: Array

The purpose of this study is to investigate the application of feature selection (FS) in the classification of cancer disease. Classification of data is an important part of microarray data processing and analyzing, based on relevance of gene expression data. The goal is to identify the subset of genes, so that it can be used to predict the new classes of samples. The dataset used in this paper is a microarray dataset. Microarray dataset contains many noisy data and redundant data.  SVM is a common classifier for cancer classification. SVM is a machine learning approach for gene selection process to select informative gene. Feature selection techniques is used to extract/select informative features and remove noise. Several feature selection techniques are used with machine learning classifiers, to analyze the effect they have on the accuracy and performance of the classifiers.