Gene expression data classification using SVM-KNN classifier

Abstract

In this paper we propose a new classifier that combines Support Vector Machine (SVM) with K Nearest Neighbor (KNN) for gene expression data classification. This new classifier SVM-KNN (KSVM) takes SVM as a INN classifier in which only one representative point is selected for each class. In the class phase, the algorithm computes the distance from the test samples to the optimal hyperplane of SVM in feature space. If the distance is greater than the given threshold, the test sample will be classified on SVM; otherwise, the KNN algorithm will be used. The experiment results show that KSVM has higher classification rate than those of traditional SVM and KNN. And it also suggests a better method for the problem of gene selection.