Development of Autonoumos Multi Agent Systems for Qualitative Risk Assessment in Disaster Management

Abstract

Developing autonomous multi agent systems are to be considered an advancement of multi agent systems can be applied in both physical and logical world. Constructions of multi hazard risk assessment using spatial data for disaster management have a problem of effective communication because of implicit knowledge. Risk management is the identification, assessment, and prioritization of risks followed by coordinated and economical application of resources to minimize, monitor, and control the probability and/or impact of unfortunate events. Constructions of risk assessment using spatial data for disaster management have a problem of effective communication because of implicit knowledge Risk assessment is the determination of quantitative or qualitative value of risk related to a concrete situation and a recognized hazard. Quantitative risk assessment requires commonsense knowledge related with the hazard. This complicates the effective communication of data to the user in real-time machine processing in support of disaster management. In this paper we present an approach to modeling commonsense knowledge in qualitative risk assessment using Autonomous multi agent system. This gives three-phase knowledge modeling approach for modeling commonsense knowledge in, which enables holistic approach for disaster management. At the initial stage commonsense knowledge is converted into a questionnaire. Removing dependencies among the questions are modeled using principal component analysis. Classification of the knowledge is processed through fuzzy logic module, which is constructed on the basis of principal components. Further explanations for classified knowledge are derived by expert system technology. We have implemented the system using FLEX expert system shell, SPSS, XML and VB. This paper describes one such approach using classification of human constituents in Ayurvedic medicine. Evaluation of the system has shown 77% accuracy.