CFP last date
20 March 2024
Reseach Article

Novel Application of Multi-Layer Perceptrons (MLP) Neural Networks to Model HIV in South Africa using Seroprevalence Data from Antenatal Clinics

by Wilbert Sibanda, Philip Pretorius
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 35 - Number 5
Year of Publication: 2011
Authors: Wilbert Sibanda, Philip Pretorius
10.5120/4398-6106

Wilbert Sibanda, Philip Pretorius . Novel Application of Multi-Layer Perceptrons (MLP) Neural Networks to Model HIV in South Africa using Seroprevalence Data from Antenatal Clinics. International Journal of Computer Applications. 35, 5 ( December 2011), 26-31. DOI=10.5120/4398-6106

@article{ 10.5120/4398-6106,
author = { Wilbert Sibanda, Philip Pretorius },
title = { Novel Application of Multi-Layer Perceptrons (MLP) Neural Networks to Model HIV in South Africa using Seroprevalence Data from Antenatal Clinics },
journal = { International Journal of Computer Applications },
issue_date = { December 2011 },
volume = { 35 },
number = { 5 },
month = { December },
year = { 2011 },
issn = { 0975-8887 },
pages = { 26-31 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume35/number5/4398-6106/ },
doi = { 10.5120/4398-6106 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T20:20:56.887498+05:30
%A Wilbert Sibanda
%A Philip Pretorius
%T Novel Application of Multi-Layer Perceptrons (MLP) Neural Networks to Model HIV in South Africa using Seroprevalence Data from Antenatal Clinics
%J International Journal of Computer Applications
%@ 0975-8887
%V 35
%N 5
%P 26-31
%D 2011
%I Foundation of Computer Science (FCS), NY, USA
Abstract

This paper presents an application of Multi-layer Perceptrons (MLP) neural networks to model the demographic characteristics of antenatal clinic attendees in South Africa. The method of cross-validation is used to examine the between-sample variation of neural networks for HIV prediction. MLP neural networks for classifying both the HIV negative and positive clinic attendees are developed and evaluated using validity and reliability of the test. Neural networks are robust to sampling variations in overall classification performance.

References
  1. Efron B., Gong G. 1983. A leisurely look at the bootsrap, the jackknife and cross-validation. American Statistician. vol. 37, 36-48.
  2. Patel J.L, Goyal R.K. 2007. Applications of artificial neural networks in medical science. Curr Clin Pharmacol. (Sep. 2007), 2(3), 217-26.
  3. Trentin E. and Freno A. 2009. Unsupervised nonparametric density estimation: A neural network approach. Proceedings of International Joint Conference on Neural Networks, Atlanta, Georgia, USA. (Jun. 2009), 14-19.
  4. UNAIDS. 2009. AIDS Epidemic Update, www.unaids.org
  5. World Health Organization (WHO) and the Joint United Nations Programme. Guidelines for measuring national HIV prevalence. UNAIDS/WHO Working Group on Global HIV/AIDS and STI surveillance
  6. Zimmermann H.G., Minin A. and Kusherbaeva A. 2011. Comparison of the complex valued and real valued neural networks trained with gradient descent and random search algorithms. ESANN 2011 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium), 27-29 April 2011.
Index Terms

Computer Science
Information Sciences

Keywords

Multi-layer Perceptrons Neural Networks HIV/AIDS Seroprevalence Data Antenatal