An Ensemble Classifier Approach for Diagnosis of Breast Cancer

Abstract

Accurate and early diagnosis of breast cancer increases survival rate of patients. Diagnosis of Breast cancer involves identifying tumour as either benign or malignant. In this paper, proposed methodology is an integration of ensemble classifiers AdaBoost and Random Forest named as ADARF a prediction model for diagnosis of breast cancer. The main objective is to enhance the performance and to reduce error. Experimental result shows that the proposed approach has higher accuracy of 98.8% compared to Logistic Regression (LR), K Nearest Neighbour (KNN) and Support Vector Machine (SVM) classifiers.