A hybrid selection method based on HCELFS and SVM for the diagnosis of oral cancer staging

Abstract

A diagnostic model based on Support Vector Machines (SVM) with a proposed hybrid feature selection method is developed to diagnose the stage of oral cancer in patients. The hybrid feature selection method, named Hybrid Correlation Evaluator and Linear Forward Selection (HCELFS), combines the advantages of filters and wrappers to select the optimal feature subset from the original feature set. In HCELFS, Correlation Attribute Evaluator acts as filters to remove redundant features and Linear Forward Selection with SVM acts as the wrappers to select the ideal feature subset from the remaining features. This study conducted experiments in WEKA with ten fold cross validation. The experimental results with oral cancer data sets demonstrate that our proposed model has a better performance than well-known feature selection algorithms. F.