Neuro-rough models for modelling HIV

Tshilidzi Marwala; Bodie Crossingham

doi:10.1109/ICSMC.2008.4811770

Neuro-rough models for modelling HIV

Tshilidzi Marwala
, Bodie Crossingham

University of the Witwatersrand
Accenture

Research output: Contribution to journal › Conference article › peer-review

15 Citations (Scopus)

Abstract

This paper proposes a neuro-rough model based on multi-layered perceptron (MLP) and rough set theory. The neuro-rough model is then tested on modeling the risk of HIV (human immunodeficiency virus) from demographic data. The model is formulated using Bayesian framework and trained using Monte Carlo method and Metropolis criterion. When the model was tested to estimate the risk of HIV infection given the demographic data it was found to give the accuracy of 62%. The proposed model is able to combine the accuracy of the Bayesian MLP model and the transparency of Bayesian rough set model.

Original language	English
Article number	4811770
Pages (from-to)	3089-3095
Number of pages	7
Journal	Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
DOIs	https://doi.org/10.1109/ICSMC.2008.4811770
Publication status	Published - 2008
Externally published	Yes
Event	2008 IEEE International Conference on Systems, Man and Cybernetics, SMC 2008 - Singapore, Singapore Duration: 12 Oct 2008 → 15 Oct 2008

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Bayesian MLP
HIV
Nerual networks
Rough sets

ASJC Scopus subject areas

Electrical and Electronic Engineering
Control and Systems Engineering
Human-Computer Interaction

Access to Document

10.1109/ICSMC.2008.4811770

Cite this

@article{44f77a8b72224d3f93067039f2f5b083,

title = "Neuro-rough models for modelling HIV",

abstract = "This paper proposes a neuro-rough model based on multi-layered perceptron (MLP) and rough set theory. The neuro-rough model is then tested on modeling the risk of HIV (human immunodeficiency virus) from demographic data. The model is formulated using Bayesian framework and trained using Monte Carlo method and Metropolis criterion. When the model was tested to estimate the risk of HIV infection given the demographic data it was found to give the accuracy of 62\%. The proposed model is able to combine the accuracy of the Bayesian MLP model and the transparency of Bayesian rough set model.",

keywords = "Bayesian MLP, HIV, Nerual networks, Rough sets",

author = "Tshilidzi Marwala and Bodie Crossingham",

year = "2008",

doi = "10.1109/ICSMC.2008.4811770",

language = "English",

pages = "3089--3095",

journal = "Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics",

issn = "1062-922X",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "2008 IEEE International Conference on Systems, Man and Cybernetics, SMC 2008 ; Conference date: 12-10-2008 Through 15-10-2008",

}

TY - JOUR

T1 - Neuro-rough models for modelling HIV

AU - Marwala, Tshilidzi

AU - Crossingham, Bodie

PY - 2008

Y1 - 2008

N2 - This paper proposes a neuro-rough model based on multi-layered perceptron (MLP) and rough set theory. The neuro-rough model is then tested on modeling the risk of HIV (human immunodeficiency virus) from demographic data. The model is formulated using Bayesian framework and trained using Monte Carlo method and Metropolis criterion. When the model was tested to estimate the risk of HIV infection given the demographic data it was found to give the accuracy of 62%. The proposed model is able to combine the accuracy of the Bayesian MLP model and the transparency of Bayesian rough set model.

AB - This paper proposes a neuro-rough model based on multi-layered perceptron (MLP) and rough set theory. The neuro-rough model is then tested on modeling the risk of HIV (human immunodeficiency virus) from demographic data. The model is formulated using Bayesian framework and trained using Monte Carlo method and Metropolis criterion. When the model was tested to estimate the risk of HIV infection given the demographic data it was found to give the accuracy of 62%. The proposed model is able to combine the accuracy of the Bayesian MLP model and the transparency of Bayesian rough set model.

KW - Bayesian MLP

KW - HIV

KW - Nerual networks

KW - Rough sets

UR - https://www.scopus.com/pages/publications/69949166678

U2 - 10.1109/ICSMC.2008.4811770

DO - 10.1109/ICSMC.2008.4811770

M3 - Conference article

AN - SCOPUS:69949166678

SN - 1062-922X

SP - 3089

EP - 3095

JO - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

JF - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

M1 - 4811770

T2 - 2008 IEEE International Conference on Systems, Man and Cybernetics, SMC 2008

Y2 - 12 October 2008 through 15 October 2008

ER -

Neuro-rough models for modelling HIV

Abstract

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this