Fuzzy-neural networks for medical diagnosis

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.