Model-based reasoning

Abstract: This thesis presents a novel approach to model-based diagnosis. This approach, called Explanation-Aided diagnosis, addresses the two problems--computational complexity and partially incorrect device models--that have prevented model-based diagnostic techniques from being more widely used. A formal model is defined that combines deduction for ruling-out hypotheses, abduction to generate hypotheses, and induction to recall past experiences and account for potential errors in the device models. The main idea is to use the model of the device and the results of diagnostic tests to index and match cases representing past diagnostic situations. These cases are used to help the diagnostic process for later situations. A general architecture for the model is presented, followed by a description of the initial diagnostic methodology used while applying this methodology to two real-world devices. The incorporation of a case-based reasoning system, as a means for induction, is then described in detail. Experimental results show the effectiveness of both the indexing schema and the matching algorithm. The thesis also discusses how and why these results can be generalized to a multiple fault situation, to other types of device models and to other applications in the field of artificial intelligence.

Abstract: Our experience in developing a traditional expert system motivated us to develop a practical system that applies analogical reasoning to mechanism design. The new system could use existing solutions (apply analogical reasoning) to synthesize new mechanisms; use more informative knowledge representation so it could reason effectively and more meaningfully; and incorporate multiple reasoning capabilities, so it could generate new conceptual designs more intelligently. We called the system Smarts (Synthesis of Mechanisms using Analogical Reasoning Techniques). Traditional expert systems design mechanisms by exhaustive generation and evaluation. This system learns from experience to design mechanism more simply and efficiently. >

Abstract: The automation of protocol-based care requires reasoning about a patient's situation over time and about how the standard protocol plan can be adapted to address the patient's current clinical situation. The EON architecture brings together (1) a skeletal-planning reasoning method, ESPR, that can determine appropriate clinical interventions by instantiating an abstract protocol specification, (2) a temporal-reasoning system, RESUME, that can infer from time-stamped patient data higher-level, interval-based concepts, and (3) a historical database system, Chronus, that can perform temporal queries on a database of interval-based patient descriptions. The modular problem-solving elements of EON operate on knowledge bases of clinical protocols that clinicians enter into domain-specific knowledge-acquisition tools generated by the PROTEGE-II system. The EON architecture provides an integrated framework for development, execution, and maintenance of clinical-protocol knowledge bases.