Diagnosis the Breast Cancer using Bayesian Rough Set Classifier

Abstract

Breast cancer was one of the most common reasons for death among the women in the world. Limited awareness of the seriousness of this disease, shortage number of specialists in hospitals and waiting the diagnostic for a long period time that might increase the probability of expansion the injury cases. Consequently, various machine learning techniques have been formulated to decrease the time taken of decision making for diagnoses the breast cancer and that might minimize the mortality rate. The proposed system consists of two phases. Firstly, data pre-processing (data cleaning, selection) of the data mining are used in the breast cancer dataset taken from the University of California, Irvine machine learning repository in this stage we modified the Correlation Feature Selection (CFS) with Best First Search (BFS) established on the Discriminant Index (DI) so as to reduce the complexity of time and get high accuracy. Secondly, Bayesian Rough Set (BRS) classifier is applied to predict the breast cancer and help the inexperienced doctors to make decisions without need the direct discussion with the specialist doctors. The result of experiments showed the proposed system give high accuracy with less time of predication the disease.