Logistic Regression Versus Neural Networks: The Best Accuracy in Prediction of Diabetes Disease

Back to Journal

Home»Articles»Logistic Regression Versus Neural Networks: The Best Accuracy in Prediction of Diabetes Disease

Logistic Regression Versus Neural Networks: The Best Accuracy in Prediction of Diabetes Disease

Author : Musavir Hassan, Muheet Ahmed Butt and Majid Zaman Baba
Volume 6 No.2 July-December 2017 pp 33-42

Abstract

To derive actionable insights from vast amount of data in an intelligent fashion some techniques are used called machine learning techniques. These techniques support for predicting disease with correct case of training and testing. To classify the medical data logistic regression and artificial neural networks are the models to be selected. Today in world a major health problem is Diabetes Mellitus for which many classification algorithms have been applied for its diagnoses and treatment. To detect diabetes disease in early stage it needs greatest support of machine learning, since it cannot be cured and also brings great complication to our health system. In this paper, we establish a general framework for explaining the functioning of Artificial Neural Networks (ANNs) in binomial classification and implement and evaluate the variants of Back propagation algorithm (Standard Back Propagation, Resilient – Back propagation, Variable Learning Rate, Powell-Beale Conjugate Gradient, Levenberg Marquardt, Quasi-Newton Algorithm and Scaled Conjugate Gradient) using Pima Indians Diabetes Data set from UCI repository of machine learning databases. We also compare Artificial Neural Networks (ANNs) with one of the conventional techniques, namely logistic regression (LR) to predict diabetic disease decisions.

Keywords

Artificial Neural Networks (ANNs), logistic regression (LR), Quasi-Newton Algorithm, Resilient - Back propagation, Standard Back Propagation.

Full Text:

References

Asian Journal of Computer Science and Technology is a peer-reviewed international journal that publishes high-quality scientific articles (both theory and practice) and research papers covering all aspects of future computer and Information Technology areas. Topics include, but are not limited to:

Foundations of High-performance ComputingTheory of algorithms and computability

Parallel & distributed computing

Computer networks

Neural networks

LAN/WAN/MAN

Database theory & practice

Mobile Computing for e-Commerce

Future Internet architecture

Protocols and services

Mobile and ubiquitous networks

Green networking

Internet content search

Opportunistic networking

Network applications

Network scaling and limits

Artifial Intelligences

Pattern/Image Recognitions

Communication Network

Information Security

Knowledge Management

Management Information systems

Multimedia communicatiions

Operations research

Optical networks

Software Engineering

Virtual reality

Web Technologies

Wireless technology

To derive actionable insights from vast amount of data in an intelligent fashion some techniques are used called machine learning techniques. These techniques support for predicting disease with correct case of training and testing. To classify the medical data logistic regression and artificial neural networks are the models to be selected. Today in world a major health problem is Diabetes Mellitus for which many classification algorithms have been applied for its diagnoses and treatment. To detect diabetes disease in early stage it needs greatest support of machine learning, since it cannot be cured and also brings great complication to our health system. In this paper, we establish a general framework for explaining the functioning of Artificial Neural Networks (ANNs) in binomial classification and implement and evaluate the variants of Back propagation algorithm (Standard Back Propagation, Resilient - Back propagation, Variable Learning Rate, Powell-Beale Conjugate Gradient, Levenberg Marquardt, Quasi-Newton Algorithm and Scaled Conjugate Gradient) using Pima Indians Diabetes Data set from UCI repository of machine learning databases. We also compare Artificial Neural Networks (ANNs) with one of the conventional techniques, namely logistic regression (LR) to predict diabetic disease decisions.