Generation Of Knowledge-based Systems Research Articles

Knowledge capitalisation through case bases and knowledge engineering for road safety analysis

New generation knowledge-based systems should be fully integrated into their environment, by exploiting existing information sources, and should be flexible and easily extensible. This article describes the architecture of an organisational memory (OM) for road safety analysis. Starting from the design of a knowledge-based system, we show how we address knowledge capitalisation issues through the building of an OM. We present its main components and describe how knowledge engineering techniques can be exploited to build and enrich it. We then describe the major task that exploits the OM as decision support for site analysis. We also explain how domain knowledge can be exploited and capitalised using case-based reasoning and collaborative work.

Validation of Computational Models Based on MultipleHeterogeneous Knowledge Sources

Theories of organizations have brought together multiple heterogeneous theories in computational models. In addition, in artificial intelligence, there has been an emphasis on the generation of knowledge-based systems that include multiple heterogeneous knowledge bases. As a result, increasingly, theory and model developers have called for the need to validate these computational models. Unfortunately, there has been only limited attention given to validation of multiple knowledge source programs. The primary focus of this paper is on the identification of conflict between multiple knowledge bases. The existence of conflict is particularly critical in those situations where database evaluations are “averaged”. For example, what would it mean to average the assessments of supply and demand economists, or surgeons and chemotherapists? Correlational statistics are used to identify conflict situations. In addition, a new approach, referred to as cutpoints, is developed to determine if probability distributions of multiple agents are in conflict. A case study is used to illustrate the problems of combining expertise in multiple agent systems and to demonstrate the approach.

Development of an integrated Knowledge-Based System for Management Support on Dairy Farms

A knowledge-based system is an advanced computer program that can solve problems requiring the use of expertise and experience. This feature makes it very suitable for use in dairy farm management. A knowledge-based system contains a knowledge base, an inference engine, and a user interface. In second generation knowledge-based systems, the knowledge base is based upon a model in which declarative knowledge is stored. One of the possibilities for a model is a causal model. Causal models and other knowledge representation schemes can be used in an integrated knowledge-based system for management support on dairy farms. Such a knowledge-based system can contain three modules: 1) a health module, which must, for example, be able to detect and diagnose on-line (subclinical) diseases, such as mastitis, in an early stage; 2) a production module, which must help to reduce and prevent losses from diseases and managerial deficiencies; and 3) a financial module, which must be able to detect suboptimal financial results and search for the reasons causing those results. Tools and methods that can be used to build such a large integral knowledge-based system are discussed.