Design of a Two-level Adaptive Multi-Agent System for Malaria Vectors driven by an ontology
1 Laboratoire de Recherche en Informatique, Multimédia et Applications, Ecole Nationale Supérieure Polytechnique. B.P. 8390 Yaounde, Cameroon, Africa
2 Institut de Recherche pour le Développement -Unité de Recherche 016, Organisation de Coordination pour la lutte contre les grandes Endémies en Afrique Centrale. B.P 288 Yaounde, Cameroon, Africa
3 Institut de recherches Médicales et d'études sur les Plantes Médicinales, Ministère de la Recherche Scientifique et de l'Innovation. B.P 6163 Yaounde, Cameroon, Africa
BMC Medical Informatics and Decision Making 2007, 7:19 doi:10.1186/1472-6947-7-19Published: 2 July 2007
The understanding of heterogeneities in disease transmission dynamics as far as malaria vectors are concerned is a big challenge. Many studies while tackling this problem don't find exact models to explain the malaria vectors propagation.
To solve the problem we define an Adaptive Multi-Agent System (AMAS) which has the property to be elastic and is a two-level system as well. This AMAS is a dynamic system where the two levels are linked by an Ontology which allows it to function as a reduced system and as an extended system. In a primary level, the AMAS comprises organization agents and in a secondary level, it is constituted of analysis agents. Its entry point, a User Interface Agent, can reproduce itself because it is given a minimum of background knowledge and it learns appropriate "behavior" from the user in the presence of ambiguous queries and from other agents of the AMAS in other situations.
Some of the outputs of our system present a series of tables, diagrams showing some factors like Entomological parameters of malaria transmission, Percentages of malaria transmission per malaria vectors, Entomological inoculation rate. Many others parameters can be produced by the system depending on the inputted data.
Our approach is an intelligent one which differs from statistical approaches that are sometimes used in the field. This intelligent approach aligns itself with the distributed artificial intelligence. In terms of fight against malaria disease our system offers opportunities of reducing efforts of human resources who are not obliged to cover the entire territory while conducting surveys. Secondly the AMAS can determine the presence or the absence of malaria vectors even when specific data have not been collected in the geographical area. In the difference of a statistical technique, in our case the projection of the results in the field can sometimes appeared to be more general.