Development of Autonomous Multi Agent System for Multi-Hazard Risk Assessment
Abstract
Developing autonomous multi agent systems are to be considered anadvancement of multi agent systems can be applied in both the physical and the logicalworld. Constructions of multi hazard risk assessment using spatial data for disastermanagement have a problem of effective communication because of implicitknowledge. Risk assessment is the determination of quantitative or qualitative value ofrisk related to a concrete situation and a recognized hazard. Multi hazard riskassessment requires commonsense knowledge related with the hazard. This complicatesthe effective communication of data to the user in real-time machine processing insupport of disaster management. The aim of the approach is to identify the influences ofdeveloping autonomous multi agent systems for risk assesmnet in disaster management.The objectives should a) contribute to a better understanding of the transformationprocesses in commonsense knowledge related with a hazard and b) provide effectivecommunication of data to the user in real-time machine processing in support of disastermanagement.In this paper we present a metodology to modeling commonsenseknowledge in Multi hazard risk assessment using Autonomous multi agent system. Thisgives three-phase knowledge modeling approach for modeling commonsenseknowledge in, which enables holistic approach for disaster management. At the initialstage autonomous agents are initialized to convert commonsense knowledge based onmulti hazards into a questionnaire. Removing dependencies among the questions aremodeled using principal component analysis. Classification of the knowledge isprocessed through fuzzy logic agent, which is constructed on the basis of principalcomponents. Further explanations for classified knowledge are derived by agent basedon expert system technology. We have implemented the system using FLEX expertsystem shell, SPSS, XML and VB. This paper describes one such approach usingclassification of human constituents in Ayurvedic medicine. Evaluation of the systemhas shown 77% accuracy.
Key words: Autonomous multi agent systems, Multi hazards, risk assessment,commonsense knowledge, Fuzzy logic
