An application of artificial neural network classifier for medical diagnosis

Khaleel Ibraheem, Amjed (2013) An application of artificial neural network classifier for medical diagnosis. Masters thesis, Universiti Tun Hussein Onn Malaysia.

Preview	Text 24p AMJED KHALEEL IBRAHEEM.pdf Download (962kB) | Preview
	Text (Copyright Declaration) AMJED KHALEEL IBRAHEEM COPYRIGHT DECLARATION.pdf Restricted to Repository staff only Download (313kB) | Request a copy
	Text (Full Text) AMJED KHALEEL IBRAHEEM WATERMARK.pdf Restricted to Registered users only Download (2MB) | Request a copy

Abstract

In recent year, various models have been proposed for medical diagnosis, which broadly can be classified into physical-based approaches and statistical-based approaches. Uncertainty and imprecision are the most important problems in medical diagnosis, other many problems in medical diagnostic domains need to be represented at varying degrees of diagnosis to be solved. Moreover, classification is very important in computer-aided medical diagnosis. In this respect, Artificial Neural Network (ANN) have been successfully applied and with no doubt, they provide the ability and potentials to diagnose the diseases. Therefore, this research focuses on using ANN to classify medical data. ANN model with two layers of tunable weights were used and trained using four different backpropagation algorithms while are the gradient descent(GD), gradient descent with momentum(GDM), gradient descent with adaptive learning rate(GDA) and gradient descent with momentum and adaptive learning rate(GDX). The network was used to classify three sets of medical data taken from UCI machine learning repository. The ability of all training algorithms tested and compared to each other on all datasets. Simulation results proved the ability of ANN for medical data classification with high accuracy and excellent performance and efficiency. This research provides the possibility of reduce costs and human resources. Increasing speed to find the results of medical analysis by using ANN also contributes in saving time for both physicians and patients

Item Type:	Thesis (Masters)
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) T Technology > TA Engineering (General). Civil engineering (General) > TA168 Systems engineering
Divisions:	Faculty of Computer Science and Information Technology > Department of Software Engineering
Depositing User:	Mrs. Sabarina Che Mat
Date Deposited:	12 Oct 2021 04:28
Last Modified:	12 Oct 2021 04:28
URI:	http://eprints.uthm.edu.my/id/eprint/1890

Actions (login required)

View Item