Search This Issue


Home Site
 

   Page 37
Sample Issue - Subscribe TODAY to see the entire issue
18.3 Table of ContentsBottom of PageSite Map

Abstract - Protégé, Ontology and Knowledge Acquisition: Knowledge Representation, the Foundation of Intelligent Systems

     Terry Hengl details the evolution and uses of a tool called Protege that is used for creating custom knowlege bases. He discusses the early incarnations of Protege as well as current versions. Ontologies are also discussed. Ontologies are complex definitions of concepts that provide information on not only the dictionary meaning but also how they relate to other concepts. Information is also provided on Open Knowledge Base Connectivity, Generic Frame Protocol, and the Ontology Web Language.


 

Protégé, Ontology and Knowledge Acquisition: Knowledge Representation, The Foundation of Intelligent Systems

 

 
By Terry Hengl
 

Introduction
     Knowledge is a decisive competitive-advantage for today's corporations. Knowledge of schedules, raw materials, labor, manufacturing and distribution is essential to the supply chain while knowledge of customer interests and buying habits, latest technologies, budget constraints, marketing plans are crucial to product development. It offers a powerful tool for gaining market share and preserving a competitive edge, but it is costly to capture and control. Methodologies and technologies that assist in the acquisition, maintenance, and distribution of knowledge are essential to an organization's success. Today's society, and the world in general, have contributed to this growth in importance of knowledge management and knowledge based systems. Some examples include (www.worldedreform.com/intercon2/f15a.pdf):

     * Accelerating rate of change in every aspect of           technology and society
     * Staff migration and attrition (downsizing and           reengineering)
     * Geographic dispersion associated with globalization of           markets
     * Global integration of cultures, companies and markets
     * Increase in networked organizations
     * Increased level of education and training of the           population
     * Growing knowledge-intensity of goods and services
     * Revolution in information technology

 It is not easy to efficiently and cost-effectively identify, acquire and maintain this knowledge. At a minimum, organizations must be able to:
     * agree to an organization-wide vocabulary to ensure           knowledge is consistently communicated and           understood;
     * identify, explicitly represent and model this knowledge;
     

 

    * share and reuse this knowledge across independent           applications and domains.

     This article looks at these aspects of knowledge acquisition by examining Protégé (http://Protégé.stanford.edu), a free open-source Java tool with an extensible architecture for creating customized knowledge-based applications - based on Ontologies (www.ontology.org). It also reviews the concept of Ontologies (see side bar), and associated support methodologies, which establish the vocabulary and model the concepts along with their inter-relationships. This concept also includes processing of the associated attributes for a particular field of knowledge. By reviewing the evolution of Protégé, an ontology modeling and knowledge acquisition environment (developed by Stanford Medical Informatics (http://camis.stanford.edu) at the Stanford University School of Medicine), an understanding of fundamental concepts that underpin knowledge acquisition emerges. This environment creates and modifies the ontologies and knowledge bases it generates to enable developers and domain experts to build knowledge-based systems.
     Other associated technologies and standards mentioned in this article include the Open Knowledge Base Connectivity (OKBC), Generic Frame Protocol (GFP), Resource Description Framework (RDF), OWL and OWL-S.

The Evolution of Protégé
     Opal (http://smi-web.stanford.edu/ pubs/SMI_Abstracts/SMI-86-0137.html) was an expert system shell-based application developed as part of the medical domain Oncocin (http://citeseer.ist.psu.edu/context/1419258/0). Oncocin developed this knowledge acquisition and advice system for protocol-based cancer therapy. Opal enabled patient history entry by the physician or nurse (the domain experts)

Order the new Volume 17

CD at www.pcai.com/store

To Page 30

18.3 Table of Contents
Top of Page

To Page 38


18.3
37

PC AI Magazine - -
e-mail: PCAI.TH @ gmail.com - Comments: webmaster @ pcai.com