NET-EFFECT IN THE DIAGNOSIS OF BREAST CANCER USING FEATURE REDUCTION AND CLASSIFICATION

Abstract

Soft Computing methods provide solutions to biologically inspired problem of medical domain like breast cancer. Neural Networks, Fuzzy Logic and Genetic Algorithms contribute novel algorithms to deal with breast cancer. Breast cancer can be diagnosed using soft computing methods. In this paper, we try to produce effective diagnosis of breast cancer by using feature reduction and classification methods. The net-effect of the classification before and after feature reduction process is stated. The feature reduction method applied is Principal Component Analysis (PCA) and the classification method includes Support Vector Machines (SVM). The result of the proposed method produced better outcome when applied on Wisconsin Breast Cancer Data Set (WBCD).