Efficiency enhancement of rule-based expert systems

Abstract

Describes several types of efficiency enhancements of "classical" rule-based diagnostic expert systems. The blackboard control structure enables one to explore more knowledge bases of the same syntax in parallel, the taxonomy structures make fast zooming of attention possible and provide an additional inference mechanism based on inheritance principles. In addition to these mechanisms, we describe a method utilizing a machine learning approach in the process of developing and refining a knowledge base. The applicability of the enhancing techniques and the machine learning is documented in four case studies exploring the extended FEL-EXPERT shell in different tasks of medical decision-making. The authors consider these techniques as useful steps on the way from "classical" diagnostic expert systems towards more complex multi-agent decision tools.