Multi-agent system surveillance support for Hiv/aids & tuberculosis
Abstract
Health information required for national and international use is not adequate and often, is not
timely for effective and efficient management. The information collected is from Government
health facilities only and hence incomplete for analysis of population health status from the
whole country perspective. The challenge of data integration, analysis and monitoring in the
healthcare sector still bothers so many Governments and organizations.
This research project seeks to establish challenges facing surveillance systems while choosing
the appropriate surveillance strategy and reviewing of the current state of health management
systems in Kenya. Finally it examines the appropriate way to collect, integrate and analyze data
from varied sources using multi agent technology and make analysis for effective decision
making by analyzing, designing and building of the multi-agent based disease surveillance
system.
The agent oriented methodology i.e Prometheus for multi-agent systems was used for analysis
and design of the system and also an open source Java toolkit called, JADE framework for
building a multi-agent system .
The study also utilized both secondary and primary data with use of questionnaires and interview
schedule. The study employed quantitative data analysis. The data in the questionnaire forms
was edited, coded, entered and analyzed using statistical package for social scientists (SPSS).
The study established that the integrated disease surveillance and response strategy is preferred
over other strategies. It was also established that the country‟s current Health information system
has not been sufficiently responsive or effective in meeting evolving needs of disease
surveillance. The developed surveillance system is able to monitor cases as they happen , send
alerts for the various epidemics after collecting, integrating and analyzing data from varied
sources as evidenced from the evaluation.
A lot of current research and development work is oriented towards providing suitable
techniques and software tools for the integration of multi-agent systems with Web technologies
such as, for example, Web services, Semantic Web technologies & Geographic Information
System. The results of the research have actualized the integration of multi-agent technology
with other web technologies. This shows why agents are considered one of the most important
paradigms that on the one hand may improve on current methods for conceptualizing, designing
and implementing software systems, and on the other hand may be the solution to the legacy
software integration problem.
Citation
Masters of science in computer sciencePublisher
University of Nairobi School of Computing and Informatics