Designing a New Radial Basis Function Neural Network by Harmony Search for Diabetes Diagnosis

Abstract

Radial Basis Function Neural Networks (RBFNNs) have been widely used for classification and function approximation tasks. So, it is worthy to try improving and developing new learning algorithms for RBFNNs in order to get better results. This paper presents a new learning method for RBFNNs. Hence, an improved learning algorithm for center adjustment of RBFNNs using Harmony search (HS) algorithm has been proposed. The proposed RBFNN is used for diabetes recognition task. In order to increase the recognition accuracy as well as to reduce the dimensionality of feature vectors, Rough Set Theory (RST) has been applied on Pima Indians Diabetes. Comprehensive experiments have been conducted on Proben1 dataset in order to evaluate the efficiency and accuracy of the proposed RBFNN. The experimental results show that the proposed method can achieve higher performance compared to other state-of-the-art in the field.