Performance analysis of training algorithms of multilayer perceptrons in diabetes prediction

• Published in: 2015 International Conference on Advances in Computer Engineering and Applications (ICACEA) pp. 201 - 206
• Main Authors: Saji, Sumi Alice, Balachandran, K.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.03.2015
• Subjects: Artificial Neural Network; Artificial neural networks; Backpropagation; Diabetes; Diabetes Mellitus; Levenberg-Marquardt; Multi Layer Perceptrons; Multilayer perceptrons; Prediction algorithms; Training
• DOI: 10.1109/ICACEA.2015.7164695

Artificial Intelligence plays a vital role in developing machines or software that can create intelligence. Artificial Neural Networks is a field of neuroscience which contributes tremendous developments in Artificial Intelligence. This paper focuses on the study of performance of various training algorithms of Multilayer Perceptrons in Diabetes Prediction. In this study, we have used Pima Indian Diabetes data set from UCI Machine Learning Repository as input dataset. The system is implemented in MatlabR2013. The Pima Indian Diabetes dataset consists of about 768 instances. The input data is the patient history and the target output is the prediction result as tested positive or tested negative. From the performance analysis, it was observed that out of all the training algorithms, Levenberg-Marquardt Algorithm has given optimal training results.