Title: Fuzzy-neural networks for medical diagnosis

Authors: Canan Senol, Tulay Yildirim

Addresses: Department of Electronic Engineering, Kadir Has University, Cibali, Istanbul, 34083, Turkey. ' Department of Electronics and Communication Engineering, Yildiz Technical University, Besiktas, Istanbul, 34349, Turkey

Abstract: In this paper, a novel fuzzy-neural network architecture is proposed and the algorithm is developed. Using this new architecture, fuzzy-CSFNN, fuzzy-MLP and fuzzy-RBF configurations were constituted, and their performances have been compared on medical diagnosis problems. Here, conic section function neural network (CSFNN) is also a hybrid neural network structure that unifies the propagation rules of multilayer perceptron (MLP) and radial basis function (RBF) neural networks at a unique network by its distinctive propagation rules. That means CSFNNs accommodate MLPs and RBFs in its own self-network structure. The proposed hybrid fuzzy-neural networks were implemented in a well-known benchmark medical problems with real clinical data for thyroid disorders, breast cancer and diabetes disease diagnosis. Simulation results show that proposed hybrid structures outperform both MATLAB-ANFIS and non-hybrid structures.

Keywords: fuzzy CSFNN; fuzzy MLP; fuzzy RBF; fuzzy-neural hybrid schemes; medical diagnosis; fuzzy neural networks; conic section function neural networks; multilayer perceptron; radial basis function; thyroid disorders; breast cancer; diabetes; disease diagnosis; simulation; helthcare technology; electronic healthcare; e-healthcare.

DOI: 10.1504/IJRIS.2010.036873

International Journal of Reasoning-based Intelligent Systems, 2010 Vol.2 No.3/4, pp.265 - 271

Published online: 12 Nov 2010 *

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