Heterogeneous classifiers fusion for dynamic breast cancer diagnosis using weighted vote based ensemble

Ensemble classifiers provide an efficient method to deal with diverse set of applications in various domains. The proposed research signifies the effectiveness of ensemble classifier for computer-aided breast cancer diagnosis. A novel combination of five heterogeneous classifiers namely Naïve Bayes, Decision tree using Gini index, Decision tree using information gain, Support vector machine and Memory based learner are used to make an ensemble framework. Weighted voting technique is used to determine the final prediction where weights are assigned on the basis of classification accuracy. Four different breast cancer datasets are used from online data repositories. Feature selection and various preprocessing techniques are applied on the datasets to enhance the classification accuracy. The analyses of experimental results show that the proposed ensemble technique provided a significant improvement as compared to other classifiers. The best accuracy achieved by proposed ensemble is 97.42 % whereas the best precision and recall is 100 and 98.60 % respectively.