Stacked Generalization Based Ensemble Model for Classification of Coronary Artery Disease

Abstract

AbstractData mining based classification techniques plays an important role in medical data analysis that gives a better way to predict or diagnose any disease at an early stage. The development of a robust model is very important to achieve better classification accuracy. The proposed work constructed a robust ensemble model using a combination of Radial Basis Function Network (RBFN) and Random Forest (RF) with the stacking ensemble method. This research work has used two Coronary Artery Disease (CAD) datasets namely Z-Ali-Zadeh Sani (ZAZS) and Extension Z-Ali-Zadeh Sani (E-ZAZS) for analysis and check the robustness of models. It presents the robust ensemble model for predicting both datasets and showed improved accuracy over other traditional methods. KeywordsRandom Forest (RF)Radial Basis Function Network (RBFN)Ensemble modelCoronary Artery Disease (CAD)