Augmentation of classifier accuracy through implication of feature selection for breast cancer prediction

Abstract

Breast Cancer Examination and Prediction are great provocations to the researchers in the medical applications. Breast Cancer Examination distinguishes benign from malignant breast lumps, Breast Cancer Prediction has great deal in foretelling when Breast Cancer is expected to reoccur in patients that have had their cancers excised. Feature Selection is considered to be the preliminary step used in process to find best subsets of attributes. In this paper authors confer about the performance of five classifiers Sequential minimal optimization (SMO), Multilayer Perceptrons, Kstar, Decision Table and Random Forest with and without feature selection. The results manifest that after implying two feature selection techniques such as Correlation based and information based with ranker algorithm there is an augmentation in the accuracy rate of the classifier. It has been observed that after through implication feature selection techniques accuracy of the classifiers such as SMO, Multilayer Perceptrons, Kstar, Decision Trees, and Random Forest are enhanced.