Intelligent Diagnosis Systems

This paper examines and compares several di erent approaches to the design of intelligent systems for diagnosis applications. These include expert systems (or knowledgebased systems), truth (or reason) maintenance systems, case-based reasoning systems, and inductive approaches like decision trees, arti cial neural networks (or connectionist systems), and statistical pattern classi cation systems. Each of these approaches is demonstrated through the design of a system for a simple automobile fault diagnosis task. The paper also discusses the domain characteristics and design and performance requirements that in uence the choice of a speci c technique (or a combination of techniques) for a given application.