A Novel Weighted Hierarchical Adaptive Voting Ensemble Machine Learning Method for Breast Cancer Detection

Abstract

A novel Weighted Hierarchical Adaptive Voting Ensemble (WHAVE) machine learning (ML) method was developed for breast cancer detection. It was constructed using three individual ML methods based on Multiple-Valued Logic: Disjunctive Normal Form (DNF) rule based method, Decision Trees, Naïve Bays, and one method based on continuous representation: Support Vector Machines (SVM). Results were compared with other methods and show that the WHAVE method accuracy was noticeably higher than the individual ML methods tested. This paper demonstrates that the WHAVE method proposed outperforms all methods researched, and shows the advantage of using WHAVE method for ML in breast cancer detection.