Development of a Generic Knowledge-Based Risk Assessment System

Abstract

In recent years, artificial intelligence (AI) programs have appeared which contribute significantly to the field in which they are applied. Risk assessment and risk management (RA/RM) is an ideal candidate for such a program, and researchers at the Center for Intelligent Systems of Vanderbilt University are investigating the application of AI techniques to RA/RM, specifically within the context of a knowledge-based system, or expert system. Knowledge-based systems are one of the better known fruits of AI research and offer many benefits. Chief among these are the ability to make expert knowledge available to non-experts, the ability to explore “what it” scenarios safely, improved communication channels, and methods of handling uncertainty. This paper describes the development of a generic knowledge-based risk assessment system. By identifying an underlying representation common to many risk assessment fields (a network), the same architecture and construction techniques embodied in this generic system may be used in numerous individual applications. The system architecture and design principles, as well as the benefits they will provide, are described.