Çok Katmanlı Perseptron Sinir Ağları ile Diyabet Hastalığının Teşhisi

Abstract

Artificial neural networks (ANNs) have become modeling tools that have found extensive acceptance and they have frequently used in applications in many disciplines for solving complex problems. Different ANN structures are valuable models, which are used in the medical field for the development of decision support systems. In this study, four multilayer perceptron neural networks (MLPNNs) trained with different algorithms were used for diabetes prediction and the most efficient training algorithm was determined. Backpropagation, delta-bar-delta, extended delta-bar-delta and quick propagation were the studied four training algorithms. The MLPNNs were trained, cross validated and tested with subject records from the database. Performance indicators and statistical measures were used for evaluating the MLPNNs and the results demonstrated that the quick propagation algorithm was the most efficient multilayer perceptron training algorithm for diabetes prediction.