Title: In-depth analysis of neural network ensembles for early detection method of diabetes disease

Authors: Bayu Adhi Tama; Kyung-Hyune Rhee

Addresses: Department of IT Convergence and Application Engineering, Pukyong National University, Busan, South Korea; Faculty of Computer Science, University of Sriwijaya, Ogan Ilir, Sumatera Selatan, Indonesia ' Department of IT Convergence and Application Engineering, Pukyong National University, Busan, South Korea

Abstract: Lifestyle-driven disease such as diabetes mellitus has become a serious health problem worldwide. We propose the fusion of neural network-based classifiers, i.e., neural network and support vector machine to assist in early detection of diabetes mellitus. These classifiers are combined to produce the final prediction. However, when considering a number of classifiers in the pool, the selection of combination rule is not easy to understand. The aim of this paper is to investigate the performance of different combination rules, including several single classifiers involved in the ensemble. We use various performance metrics and validation tests to assess the performance of these classifiers using a real-world dataset. Finally, among the classifiers we evaluate their performance differences using statistical significant test. The experimental results indicate that combination rule with average voting scheme is the best performer compared with other combination rules and single classifiers in the ensemble.

Keywords: diabetes mellitus; neural-based classifiers; classifier ensembles; early detection method.

DOI: 10.1504/IJMEI.2018.095083

International Journal of Medical Engineering and Informatics, 2018 Vol.10 No.4, pp.327 - 341

Received: 02 Aug 2016
Accepted: 23 May 2017

Published online: 01 Oct 2018 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article