摘要:

A three-level architecture is developed for knowledge-base management systems. As in database management systems, each level is an abstraction targeted for a different type of user. At the external level for end users, all data and rules are viewed as graphs, and all end-user interaction is facilitated with visual aids. At the conceptual level for analysis, all data and rules are viewed as logical clauses since they provide a concise and conceptual framework for analysis. At the internal level for the implementors, all rules are viewed as data and rule management is supported by the database management system

ISSN:0883-9514    

DOI:10.1080/08839519208949946

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor

摘要:

This article discusses some topics related to the MYCIN model for uncertainty handling in expert systems. Some previously identified problems in this model should be considered as evidence to support the point of view that the probabilistic interpretation for measure of belief (MB) and measure of disbelief (MD) given by Shortliffe is inappropriate. In connection lo this, some results achieved by Heckerman are also reviewed and one of his arguments is questioned. According to this argument, the original interpretation for certainty factors implies a noncommutative method for evidence combination, and therefore, this interpretation should be abandoned. Problems similar to those identified by Adams in the original interpretation for certainty factors exist also in the interpretation recommended by Heckerman. Then, in the context of previous results stating that there is an isomorphic mapping from the evidence combination scheme for the likelihood ratio to the evidence combination function adopted in EMYCIN and its successors, we point out that the evidence combination scheme for the likelihood ratio suffers from a strong restriction. We remark upon the complaint that the MYCIN model cannot always function as well as one has expected. Implementation of the certainty factor mechanism in an information system-oriented expert system shell with some substantial changes is described

ISSN:0883-9514    

DOI:10.1080/08839519208949947

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor

摘要:

Current interactive software systems try to offer many features and a user-friendly interface to aid the user. However, where one system may suit one user, another user may find it difficult to use, because each user is different. User modeling techniques have been applied to make a system suitable for different users. This paper surveys research works for developing interactive systems that use user modeling techniques. After presenting the systems and techniques, we introduce a system called the Intelligent Syntax-Directed Editor (ISE) as an example to show how this approach can benefit the user as an intelligent tool. The ISE assists the user in (1) using the editor more efficiently through ISE's active suggestions and on-line help and (2) program development through the syntax-directed editor. In applying user modeling techniques, ISE builds a profile/model of the user and, based on this model, ISE offers a suitable amount of help and advice depending on the proficiency of the user toward the system. The ISE is implemented on a VAX/780 computer to demonstrate its ability to volunteer advice

ISSN:0883-9514    

DOI:10.1080/08839519208949948

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor

摘要:

One of the problems solved by machine learning based techniques is symbolic data analysis and concept formation. We report on the program FAVORIT, which achieves a performance improvement over its predecessors (such as UNIMEM) by means of a simple mechanism mimicking the shortcomings of human learning: aging of knowledge and forgetting. When applied to large and noisy data sets, these characteristics enable efficient restructuring and pruning of the internal knowledge structures. The paper contains a brief description of the program, together with the rationale behind its philosophy, as well as a simple case study.

ISSN:0883-9514    

DOI:10.1080/08839519208949949

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor

摘要:

Most model-based approaches to diagnosis require a consistency-checking procedure to perform their task. When dealing with a dynamically changing system, such a procedure must take into account time-varying data. This requires suitable techniques for reasoning over time. Additional difficulties arise when delays are involved in interactions between variables. The worst case occurs when some of the delays are completely unspecified. This report presents an approach to consistency checking that handles qualitative models of dynamic systems exhibiting time lags. A component-centered ontology is adopted to model the structure of the physical system, and an episode-based approach is adopted for representing its behavior over time. An example consisting of a physical process exhibiting transportation lags is used to illustrate the power of the approach. We present algorithms and an implementation in PROLOG called C-CAT (consistency checking along time). Some meaningful outputs from the program are used as examples. The solution proposed represents an extension to B. C. Williams' temporal constraint propagation methodology. It also extends the applicability range of existing approaches to model-based diagnosis, permitting its use in tasks such as online diagnosis of dynamic systems.

ISSN:0883-9514    

DOI:10.1080/08839519208949950

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor

ISSN:0883-9514    

DOI:10.1080/08839519208949951

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor

ISSN:0883-9514    

DOI:10.1080/08839519208949952

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor

ISSN:0883-9514    

DOI:10.1080/08839519208949953

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor

ISSN:0883-9514    

DOI:10.1080/08839519208949954

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor