The Second IASTED African Conference on
Modelling and Simulation
~AfricaMS 2008~

SCIENCE AND TECHNOLOGY INNOVATION FOR SUSTAINABLE DEVELOPMENT

September 8 – 10, 2008
Gaborone, Botswana

Group Decision Support for Provision of HIV Therapy

The main objective of this paper is to extend the idea of a previously submitted paper which attempted to explore the applicability of a formal decision procedure to the process of providing tailored, ARV Treatment (Anti- Retroviral Therapy). The case study is based on Botswana, one of the leading countries hard hit by the HIV and AIDS pandemic where the government is working hard to facilitate the provision of ARV to the infected. The process involves issues such socioeconomic, biomedical, and human rights. Doctors are faced with the challenge of trying to restore full function of patients immune systems while avoiding or minimizing drug resistance, side effects, treatment failure and evolution of new viral streams. Selecting the best therapy from available alternatives where there are many criteria to use for each patient is complex. Due to the large number of patients in Botswana, the task is deemed enormous and requires formalized decision methods to support the doctors. The main objective of the paper is to increase confidence levels in provision of the right combination of drugs for each patient by involving more than one doctors opinion. We propose to present a formal group decision technique that can synthesize judgements from different doctors in making a recommendation for the correct therapy.

Incorporating Data Mining Into a Mobile Healthcare Portal

This research paper describes a partial model of a mobile healthcare information portal (from the IHISM project: Integrated Healthcare Information Service through Mobile telephony) that incorporates data mining functionality. It makes two contributions: 1) tests are carried out to select appropriate data mining algorithms for such a domain and 2) the model proposed shows how data mining can be integrated into such a portal for the purpose of improving portal services, understanding user needs better, and guiding the IHISM research project. From the patterns observed, one could easily conclude that the IHISM portal would benefit greatly from the use of data mining to improve its information content and services.

Organization of a Healthcare Informatics Research Project

This paper is concerned with computing research management i.e. the principles and practices for developing and operating a computing research project. In this paper we describe how a technology research project in the area of Mobile Health care was introduced into the Department of Computer Science, University of Botswana.

Healthcare FAQ Information Retrieval Using a Commercial Database Management System

This paper describes the IHISM FAQ System, used in a mobile healthcare project (IHISM: Integrated Healthcare Information Service through Mobile telephony). It is implemented using the Full-Text search facility of a commercial Database Management System. It is meant to be used with a Web and Cell phone (SMS) interface. We describe the evaluation of the system using two different configurations and calculate Recall, Rejection and FAQ Precision statistics. The IHISM FAQ System proves to be very useful for FAQ queries and more work is planned on it.

Understanding HIV/AIDS Pandemic by High Performance Computing Epidemiology

This paper presents the application of distributed systems high performance cluster in modelling the spread of HIV in a given population. A population of a complex ecosystem such as a community of sexually related individuals has been modelled around distributed objects. An object modelled one individual and its communication with other objects represents social interaction between individuals. This research focuses on the heterosexual transmission of HIV and uses the probability of infection as determined by medical research work. The probability of infection is dependent on a number of factors; one) viral load of the infected person as well as two) the CD4+CCR5 receptor cell count of the person at risk and three) use of ARVs on mortality and transmission rate is also considered. The experiment was run on a cluster of 70 connected computers each capable of running hundreds of objects (individuals). These objects are implemented in Java in a distributed programming environment called CORBA that enable object across a network to communicate. The results obtained show patterns consistent with the epidemiological nature of the HIV as well as the behavioural properties of the people. The results have clearly demonstrated the ability for the high performance computer cluster to play out different scenarios and provide predictions and answers to what if? questions especially those of intervention programmes.

Modeling and Optimization of Process Parameters in PMEDM Using Genetic Algorithm

The objective of this paper is to model and optimize the process parameters of powder mixed electrical discharge machining (PMEDM). The process output characteristics include metal removal rate (MRR) and electrode wear rate (EWR). The grain size of Aluminum powder (S), concentration of the powder (C), and discharge current (I) pulse on time (T) are chosen as control variables to study the process performance. The experimental results are used to develop the regression models based on second order polynomial equations for the different process characteristics. Then, a genetic algorithm (GA) is employed to determine optimal process parameters for any desired output values.