Research On Case-Based Reasoning For Emergency Decision Making

Recently the research on the crisis management and emergency decision making, especially the decision support method, shows its importance because various kinds of crisis and public emergencies happen frequently and cause great lost.Compared with general events, the crisis has it own characteres which including:Serious results, urgency, uncertainty and so on. To response to the crisis and incidents, quick and correct judgment as well as rational reactive decision is necessary. But owing to time constraints, dynamic evolution of the crisis, limited information source, it is difficult for the decision-maker to perform well under such high psychological pressure. So it is feasible and necessary to introduce reliable emergency decision making support system to support the decision-making process.Initiated by researching on the characteristics of EDM for crisis, this paper proposes a novel iterative decision support model based on Case-based Reasoning for EDM. Using CBR in EDM process can make full use of the previous experiences. And the iterative model will satisfy the requirement of the dynamically evolutionary process of crisis.Then, based on the theory of similarity-based rough set and Prolog artificial intelligence language, this paper describes the method for attribute reduction, weighting, and similarity measurement, case reasoning and case base maintenance. It also establishes emergency decision support system’s functional modules, corresponding case base and Prolog procedures.Last, a sample decision support system for flood control is presented to demonstrate the application of proposed model.