Microarray Gene Expression Data Classification Using Feature Selection and Naïve Bayes Classifier

Abstract

Microarrays are successful tools to predict cancer from DNA gene-expression data and are successfully used in cancer classification. However, they provide high-dimensional data which is not easy to get accurate results for classification algorithms. Moreover, small sample size and big feature set of microarray data brings the over-fitting problem for the classification algorithms. Therefore, feature-selection is necessary to select relevant genes from noisy dataset. This study presents a feature extraction approach with MK-SVM algorithm to improve classification accuracy. With the experimental results and Receiver Operating Characteristic Curve (ROC) values and prediction accuracy, we conclude that Naive Bayes classifier gives very high and compatible results by using relevant genes selected by MK-SVM.