An Expert Sytem for Diagnosis Breast Cancer based on Principal Component Analysis Method

Abstract

This paper presents an expert diagnosis system for detecting breast cancer based on Principle Component Analysis (PCA). In this study PCA is used for reducing the dimension of breast cancer database and Adaptive Network Based Fuzzy Inference System (ANFIS) and Artitifical Neural Network (ANN) are used for intelligent classification respectively. In there, PCA-ANN system performance is compared with PCA-ANFIS. The dimension of input feature space is reduced from nine to four by using PCA. In test stage, 3-fold cross validation method was applied to the Wisconsin breast cancer database to evaluate the proposed systems performances. The correct classification rates of proposed systems are 97.2% and 95.3% for PCA-YSA and PCA-ANFIS respectively.