Refine
Has Fulltext
- yes (25) (remove)
Keywords
- Case-Based Reasoning (13)
- Fallbasiertes Schliessen (8)
- Fallbasiertes Schließen (5)
- Case Based Reasoning (2)
- PATDEX (2)
- Case-Based Classification Algorithms (1)
- Diagnose technischer Systeme (1)
- Diagnosesystem (1)
- EBG (1)
- Expertensysteme (1)
Faculty / Organisational entity
Im Bereich der Expertensysteme ist das Problemlösen auf der Basis von bekannten Fallbeispielen ein derzeit sehr aktuelles Thema. Auch für Diagnoseaufgaben gewinnt der fallbasierte Ansatz immer mehr an Bedeutung. In diesem Papier soll der im Rahmen des Moltke -Projektes1 an der Universität Kaiserslautern entwickelte fallbasierte Problemlöser Patdex/22 vorgestellt werden. Ein erster Prototyp, Patdex/1, wurde bereits 1988 entwickelt.
Contrary to symbolic learning approaches, that represent a learned concept explicitly, case-based approaches describe concepts implicitly by a pair (CB; sim), i.e. by a measure of similarity sim and a set CB of cases. This poses the question if there are any differences concerning the learning power of the two approaches. In this article we will study the relationship between the case base, the measure of similarity, and the target concept of the learning process. To do so, we transform a simple symbolic learning algorithm (the version space algorithm) into an equivalent case-based variant. The achieved results strengthen the hypothesis of the equivalence of the learning power of symbolic and casebased methods and show the interdependency between the measure used by a case-based algorithm and the target concept.
When problems are solved through reasoning from cases, the primary kind of knowledge is contained in the specific cases which are stored in the case base. However, in many situations additional background-knowledge is required to cope with the requirements of an application. We describe an approach to integrate such general knowledge into the reasoning process in a way that it complements the knowledge contained in the cases. This general knowledge itself is not sufficient to perform any kind of model-based problem solving, but it is required to interpret the available cases appropriately. Background knowledge is expressed by two different kinds of rules that both must be formalized by the knowledge engineer: Completion rules describe how to infer additional features out of known features of an old case or the current query case. Adaptation rules describe how an old case can be adapted to fit the current query. This paper shows how these kinds of rules can be integrated into an object-oriented case representation.
Case-based knowledge acquisition, learning and problem solving for diagnostic real world tasks
(1999)
Within this paper we focus on both the solution of real, complex problems using expert system technology and the acquisition of the necessary knowledge from a case-based reasoning point of view. The development of systems which can be applied to real world problems has to meet certain requirements. E.g., all available information sources have to be identified and utilized. Normally, this involves different types of knowledge for which several knowledge representation schemes are needed, because no scheme is equally natural for all sources. Facing empirical knowledge it is important to complement the use of manually compiled, statistic and otherwise induced knowledge by the exploitation of the intuitive understandability of case-based mechanisms. Thus, an integration of case-based and alternative knowledge acquisition and problem solving mechanisms is necessary. For this, the basis is to define the "role" which case-based inference can "play" within a knowledge acquisition workbench. We will discuss a concrete casebased architecture, which has been applied to technical diagnosis problems, and its integration into a knowledge acquisition workbench which includes compiled knowledge and explicit deep models, additionally.
We describe a hybrid case-based reasoning system supporting process planning for machining workpieces. It integrates specialized domain dependent reasoners, a feature-based CAD system and domain independent planning. The overall architecture is built on top of CAPlan, a partial-order nonlinear planner. To use episodic problem solving knowledge for both optimizing plan execution costs and minimizing search the case-based control component CAPlan/CbC has been implemented that allows incremental acquisition and reuse of strategical problem solving experience by storing solved problems as cases and reusing them in similar situations. For effective retrieval of cases CAPlan/CbC combines domain-independent and domain-specific retrieval mechanisms that are based on the hierarchical domain model and problem representation.
We describe a hybrid architecture supporting planning for machining workpieces. The architecture is built around CAPlan, a partial-order nonlinear planner that represents the plan already generated and allows external control decision made by special purpose programs or by the user. To make planning more efficient, the domain is hierarchically modelled. Based on this hierarchical representation, a case-based control component has been realized that allows incremental acquisition of control knowledge by storing solved problems and reusing them in similar situations.
Fallbasiertes Schliessen ist ein derzeit viel diskutierter Problemlösesansatz. Dieser Beitrag gibt einen Überblick über den aktuellen Stand der Forschung auf diesem Gebiet, insbesondere im Hinblick auf die Entwicklung von Expertensystemen (einen ersten Schritt in diese Richtung stellte bereits der Beitrag von Bartsch-Spörl, [BS87] dar). Dazu stellen wir die dem fallbasierten Schliessen zugrundeliegenden Mechanismen vor. Ergänzt wird dies durch den Vergleich mit alternativen Verfahren wie z.B. regelbasiertes, analoges und induktives Schliessen sowie eine ausführliche Literaturübersicht.
Bestimmung der Ähnlichkeit in der fallbasierten Diagnose mit simulationsfähigen Maschinenmodellen
(1999)
Eine Fallbasis mit bereits gelösten Diagnoseproblemen Wissen über die Struktur der Maschine Wissen über die Funktion der einzelnen Bauteile (konkret und abstrakt) Die hier vorgestellte Komponente setzt dabei auf die im Rahmen des Moltke-Projektes entwickelten Systeme Patdex[Wes91] (fallbasierte Diagnose) und iMake [Sch92] bzw. Make [Reh91] (modellbasierte Generierung von Moltke- Wissensbasen) auf.
While most approaches to similarity assessment are oblivious of knowledge and goals, there is ample evidence that these elements of problem solving play an important role in similarity judgements. This paper is concerned with an approach for integrating assessment of similarity into a framework of problem solving that embodies central notions of problem solving like goals, knowledge and learning.
Patdex is an expert system which carries out case-based reasoning for the fault diagnosis of complex machines. It is integrated in the Moltke workbench for technical diagnosis, which was developed at the university of Kaiserslautern over the past years, Moltke contains other parts as well, in particular a model-based approach; in Patdex where essentially the heuristic features are located. The use of cases also plays an important role for knowledge acquisition. In this paper we describe Patdex from a principal point of view and embed its main concepts into a theoretical framework.
Forschungsprojekte im Bereich des fallbasierten Schliessens in den USA, die Verfügbarkeit kommerzieller fallbasierter Shells, sowie erste Forschungsergebnisse initialer deutscher Projekte haben auch in Deutschland verstärkte Aktivitäten auf dem Gebiet des fallbasierten Schliessens ausgelöst. In diesem Artikel sollen daher Projekte, die sich als Schwerpunkt oder als Teilaspekt mit fallbasierten Aspekten beschäftigen, einer breiteren Öffentlichkeit kurz vorgestellt werden.
Die Verwendung von existierenden Planungsansätzen zur Lösung von realen Anwendungs- problemen führt meist schnell zur Erkenntnis, dass eine vorliegende Problemstellung im Prinzip zwar lösbar ist, der exponentiell anwachsende Suchraum jedoch nur die Behandlung relativ kleiner Aufgabenstellungen erlaubt. Beobachtet man jedoch menschliche Planungsexperten, so sind diese in der Lage bei komplexen Problemen den Suchraum durch Abstraktion und die Verwendung bekannter Fallbeispiele als Heuristiken, entscheident zu verkleinern und so auch für schwierige Aufgabenstellungen zu einer akzeptablen Lösung zu gelangen. In dieser Arbeit wollen wir am Beispiel der Arbeitsplanung ein System vorstellen, das Abstraktion und fallbasierte Techniken zur Steuerung des Inferenzprozesses eines nichtlinearen, hierarchischen Planungssystems einsetzt und so die Komplexität der zu lösenden Gesamtaufgabe reduziert.
We describe a hybrid architecture supporting planning for machining workpieces. The archi- tecture is built around CAPlan, a partial-order nonlinear planner that represents the plan already generated and allows external control decision made by special purpose programs or by the user. To make planning more efficient, the domain is hierarchically modelled. Based on this hierarchical representation, a case-based control component has been realized that allows incremental acquisition of control knowledge by storing solved problems and reusing them in similar situations.
We describe a hybrid case-based reasoning system supporting process planning for machining workpieces. It integrates specialized domain dependent reasoners, a feature-based CAD system and domain independent planning. The overall architecture is build on top of CAPlan, a partial-order nonlinear planner. To use episodic problem solving knowledge for both optimizing plan execution costs and minimizing search the case-based control component CAPlan/CbC has been realized that allows incremental acquisition and reuse of strategical problem solving experience by storing solved problems as cases and reusing them in similar situations. For effective retrieval of cases CAPlan/CbC combines domain-independent and domain-specific retrieval mechanisms that are based on the hierarchical domain model and problem representation.
In den letzten Jahren wurden Methoden des fallbasierten Schliessens häufig in Bereichen verwendet, in denen traditionell symbolische Verfahren zum Einsatz kommen, beispielsweise in der Klassifikation. Damit stellt sich zwangsläufig die Frage nach den Unterschieden bzw. der Mächtigkeit dieser Lernverfahren. Jantke [Jantke, 1992] hat bereits Gemeinsamkeiten von Induktiver Inferenz und fallbasierter Klassifikation untersucht. In dieser Arbeit wollen wir einige Zusammenhänge zwischen der Fallbasis, dem Ähnlichkeitsmass und dem zu erlernenden Begriff verdeutlichen. Zu diesem Zweck wird ein einfacher symbolischer Lernalgorithmus (der Versionenraum nach [Mitchell, 1982]) in eine äquivalente, fallbasiert arbeitende Variante transformiert. Die vorgestellten Ergebnisse bestätigen die Äquivalenz von symbolischen und fallbasierten Ansätzen und zeigen die starke Abhängigkeit zwischen dem im System verwendeten Mass und dem zu lernenden Begriff.
Die Mehrzahl aller CBR-Systeme in der Diagnostik verwendet für das Fallretrieval ein numerisches Ähnlichkeitsmass. In dieser Arbeit wird ein Ansatz vorgestellt, bei dem durch die Einführung eines an den Komponenten des zu diagnostizierenden technischen Systems orientierten Ähnlichkeitsbegriffs nicht nur das Retrieval wesentlich verbessert werden kann, sondern sich auch die Möglichkeit zu einer echten Fall- und Lösungstransformation bietet. Dies führt wiederum zu einer erheblichen Verkleinerung der Fallbasis. Die Ver- wendung dieses Ähnlichkeitsbegriffes setzt die Integration von zusätzlichem Wissen voraus, das aus einem qualitativem Modell der Domäne (im Sinne der modellbasierten Diagnostik) gewonnen wird.
Im Bereich der Expertensysteme ist das Problemlösen auf der Basis von Fallbeispielen ein derzeit sehr aktuelles Thema. Da sich sehr unterschiedliche Fachgebiete und Disziplinen hiermit auseinandersetzen, existiert allerdings eine entsprechende Vielfalt an Begriffen und Sichten auf fallbasiertes Problemlösen. In diesem Beitrag werden wir einige für das fallbasierte Problemlösen wichtige Begriffe präzisieren bzw. begriffliche Zusammenhänge aufdecken. Die dabei verfolgte Leitlinie ist weniger die, ein vollständiges Begriffsgebäude zu entwickeln, sondern einen ersten Schritt in Richtung eines einfachen Beschreibungsrahmens zu gehen, um damit den Vergleich verschiedener Ansätze und Systeme zu ermöglichen. Auf dieser Basis wird dann der derzeitige Stand der Forschung am Beispiel konkreter Systeme zur fallbasierten Diagnose dargelegt. Den Abschluss bildet eine Darstellung bislang offener Fragen und interessanter Forschungsziele.
Retrieval of cases is one important step within the case-based reasoning paradigm. We propose an improvement of this stage in the process model for finding most similar cases with an average effort of O[log2n], n number of cases. The basic idea of the algorithm is to use the heterogeneity of the search space for a density-based structuring and to employ this precomputed structure, a k-d tree, for efficient case retrieval according to a given similarity measure sim. In addition to illustrating the basic idea, we present the expe- rimental results of a comparison of four different k-d tree generating strategies as well as introduce the notion of virtual bounds as a new one that significantly reduces the retrieval effort from a more pragmatic perspective. The presented approach is fully implemented within the (Patdex) system, a case-based reasoning system for diagnostic applications in engineering domains.
Patdex is an expert system which carries out case-based reasoning for the fault diagnosis of complex machines. It is integrated in the Moltke workbench for technical diagnosis, which was developed at the university of Kaiserslautern over the past years, Moltke contains other parts as well, in particular a model-based approach; in Patdex where essentially the heuristic features are located. The use of cases also plays an important role for knowledge acquisition. In this paper we describe Patdex from a principal point of view and embed its main concepts into a theoretical framework.
While symbolic learning approaches encode the knowledge provided by the presentation of the cases explicitly into a symbolic representation of the concept, e.g. formulas, rules, or decision trees, case-based approaches describe learned concepts implicitly by a pair (CB; d), i.e. by a set CB of cases and a distance measure d. Given the same information, symbolic as well as the case-based approach compute a classification when a new case is presented. This poses the question if there are any differences concerning the learning power of the two approaches. In this work we will study the relationship between the case base, the measure of distance, and the target concept of the learning process. To do so, we transform a simple symbolic learning algorithm (the version space algorithm) into an equivalent case-based variant. The achieved results strengthen the conjecture of the equivalence of the learning power of symbolic and casebased methods and show the interdependency between the measure used by a case-based algorithm and the target concept.
This paper motivates the necessity for support for negotiation during Sales Support on the Internet within Case-Based Reasoning solutions. Different negotiation approaches are discussed and a general model of the sales process is presented. Further, the tradition al CBR-cycle is modified in such a way that iterative retrieval during a CBR consulting session is covered by the new model. Several gen eral characteristics of negotiation are described and a case study is shown where preliminary approaches are used to negotiate with a cu stomer about his demands and available products in a 'CBR-based' Electronic Commerce solution.
Contrary to symbolic learning approaches, which represent a learned concept explicitly, case-based approaches describe concepts implicitly by a pair (CB; sim), i.e. by a measure of similarity sim and a set CB of cases. This poses the question if there are any differences concerning the learning power of the two approaches. In this article we will study the relationship between the case base, the measure of similarity, and the target concept of the learning process. To do so, we transform a simple symbolic learning algorithm (the version space algorithm) into an equivalent case- based variant. The achieved results strengthen the hypothesis of the equivalence of the learning power of symbolic and case-based methods and show the interdependency between the measure used by a case-based algorithm and the target concept.