Implementation Of Knowledge-based System Research Articles

Knowledge-based systems in sheet metal stamping: a survey

This manuscript surveys and analyses the different implementations of knowledge-based systems (KBS) in sheet metal workings. The scope will cover different stamping phases; specifically the stamped part design, the stamping process planning, the die structure planning and manufacturing with the focus on progressive die designs, and lastly, the strip layout planning. The analysis of the KBS in each of these stamping phases will include the intended function of the system, the KBS construction methodology and the reasoning logic scheme utilised to manipulate the content of the knowledge bases. The survey compares the followed approaches in terms of challenges and merits found for each followed approach. This work serves as a current state-of-the-art analysis for employing KBS in sheet metal stamping (SMS).

Fuzzy Classification Rule Learning by Decision Tree Induction

Knowledge acquisition is a bottleneck in knowledge-based system implementation. Decision tree induction is a useful machine learning approach for extracting classification knowledge from a set of training examples. Many real-world data contain fuzziness due to observation error, uncertainty, subjective judgement, and so on. To cope with this problem of real-world data, there have been some works on fuzzy classification rule learning. This paper makes a survey for the kinds of fuzzy classification rules. In addition, it presents a fuzzy classification rule learning method based on decision tree induction, and shows some experiment results for the method.

Review of Biomedical Knowledge and Data Representation with Conceptual Graphs

The basis of conceptual graphs theory is an ontology of types of concepts. Concepts issued from the ontology are interlinked by semantic relationships and constitute canonical conceptual graphs. Canonical graphs may be combined to derive new conceptual graphs by means of formation rules. This formalism allows to separate knowledge representation into a conceptual level and a domain-dependent level, and enables to share and reuse a representation. This paper presents conceptual graph applications to biomedical data and concept representation, classification systems, information retrieval, and natural language understanding and processing. A discussion on the unifying role conceptual graphs theory plays in the implementation of knowledge-based systems is also presented.

The development, validation and implementation of knowledge-based systems

It is now ten years since Operational Research, and other groups that support management decision making, seized upon Knowledge-based Systems (KBS) as an alternative set of techniques and methods for building systems that support, augment or automate decision making. Success, as with most information technologies, has been mixed. This paper briefly reviews where KBS have been successful, and what benefits have been derived. It notes that interest in KBS has been rekindled by the present interest in business process re-engineering. Given the mature state of development tools, most KBS developers are now focusing on methodological and life-cycle issues. The paper reviews progress in understanding and using development methodologies, validation methods (now generally considered as crucial to technical success) and implementation. Some ideas about where KBS ‘fits in’ to the array of tools, techniques and methodologies available to the modern analyst and system developer are presented.

A Vertical Application Platform for Knowledge-Based Financial Systems

Implementations of knowledge-based systems can be divided into two distinct parts: the knowledge base and the underlying control software. The underlying control software implements reasoning mechanisms and manages data required by the knowledge base. We call this underlying control software a ‘vertical application platform‘. The vertical application platform may be re-used by other knowledge-based applications which have similar reasoning requirements. This paper studies a knowledge-based system called Risk Advisorsm which aids in the identification and assessment of audit risks. The knowledge roles and reasoning requirements of the knowledge base, and the architecture and implementation of the vertical application platform which implement the necessary reasoning mechanisms are described. The Risk Advisorsm application platform has in fact been applied with a different knowledge model to other problems in a similar domain.

Knowledge-based systems and intrinsic practices

Abstract Knowledge-based systems have the potential for an unusual amount and type of impact on organizations. Analyzing, predicting, and managing this impact requires analytical and pragmatic knowledge and skills in the human/organizational area, in some ways even more than with traditional software systems. This article addresses three important factors in the functioning of an organization: status, eligibility, and intrinsic practices and their role in the design and implementation of knowledge-based systems. Using these concepts, the reason for the even-greater-than-usual need for human competencies is addressed. Implications for designing and implementing knowledge-based systems are derived. Finally, the analysis is used to develop specific recommendations for managing the impact of the system on the organization.

Knowledge Acquisition for Knowledge—Based Systems (Vol 1) and Knowledge Acquisition Tools for Expert Systems (Vol 2) ed. by Boose, J .H . & Gaines, B .R. (Academic Press, 1988)

One of the major obstacles to the design and implementation of knowledge-based systems has been the knowledge acquisition bottleneck. A considerable amount of both basic research and application effort have gone into an analysis of this problem. This two volume series represent s a compilation of these diverse efforts as reported at the first annual Knowledge Acquisition for Knowledge--Based System s Workshop, held in Banff, Canada (November, 1986). While all of the papers are of the calibre that deserve mention, space precludes a review of all. As a best alternative-the general subjects covered and those papers which were unique, or offered unusual coverage of an interesting topic are presented in more detail. Volume 1 in this series ( Knowledge Acquisition for Knowledge--Based Systems ) describes research in three major areas: the cognitive aspects of expertise, the pragmatic aspects of knowledge acquisition skills, as well as, teaching those skills and, finally, inductive learning approaches to knowledge acquisition.