Adaptive model-based diagnosis is with hierarchical models:

Abstract: "This paper describes an efficient diagnostic mechanism which utilizes hierarchical models of a device. Model-based diagnosis is a general approach for diagnosing devices using the behavioral specification of a device. Although model-based systems are more robust than heuristic-based...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Nakakuki, Yoichiro (VerfasserIn), Koseki, Yoshiyuki (VerfasserIn), Tanaka, Midori (VerfasserIn)
Format: Buch
Sprache:English
Veröffentlicht: Tokyo, Japan 1991
Schriftenreihe:Shin-Sedai-Konpyūta-Gijutsu-Kaihatsu-Kikō <Tōkyō>: ICOT technical report 688
Schlagworte:
Zusammenfassung:Abstract: "This paper describes an efficient diagnostic mechanism which utilizes hierarchical models of a device. Model-based diagnosis is a general approach for diagnosing devices using the behavioral specification of a device. Although model-based systems are more robust than heuristic-based expert systems, they require more computation time. In order to develop an efficient model-based diagnostic system, it is important to utilize the information about hierarchical structure of a device. In general, a diagnosis using detailed level model is expensive. Therefore, in order to select an appropriate level to use, we must resolve the trade-off between the diagnosis cost and the diagnosis precision
This paper introduces the model diagnosability criterion to estimate how detailed diagnosis can be achieved with a model. This criterion enables to select an appropriate level to use. The techniques described in this paper is [sic] adaptive to several kinds of situations, such as, the required diagnosis precision, the given computation power, the observation cost, and the phase of a diagnosis.
Beschreibung:16 S.