CityU Institutional Repository >
CityU Electronic Theses and Dissertations >
ETD - Dept. of Information Systems >
IS - Master of Philosophy >
Please use this identifier to cite or link to this item:
|Title: ||Common sense ontology supported artificial intelligence applications|
|Other Titles: ||Gong gong zhi shi ben ti zhi yuan de ren gong zhi hui ying yong|
|Authors: ||He, Jingwen (何靜雯)|
|Department: ||Department of Information Systems|
|Degree: ||Master of Philosophy|
|Issue Date: ||2008|
|Publisher: ||City University of Hong Kong|
|Subjects: ||Ontologies (Information retrieval)|
|Notes: ||CityU Call Number: QA76.9.D35 H43 2008|
ix, 98 leaves 30 cm.
Thesis (M.Phil.)--City University of Hong Kong, 2008.
Includes bibliographical references (leaves 79-86)
|Abstract: ||Multi-agent systems (MAS) are those in which many intelligent agents interact with each other to accomplish a common goal, e.g. solving a complicated problem in a distributed environment. Researchers have designed and developed numerous MAS to support the knowledge management process. Along with the increasing amount of knowledge creation all over the world, the global communication and exchange of knowledge between different science domains in MAS has become more and more important. Domain-specific knowledge from experts can no longer single-handedly support reasoning in MAS. Moreover, commonsense knowledge, which connects different science domains as a bridge, has become more critical to the reasoning quality, and incorporating a common sense ontology that includes a great amount of common sense knowledge has become paramount. However, the reuse of an existing common sense ontology induces implementation dilemmas. Effective reuse depends not only on finding and reusing components, but also on the ways those component are combined. For example, OpenCyc, one of the most influential information systems ontologies, is not only a common sense knowledge base, but also has its own inference engine. Developers have to determine whether to use their existing inference engine or the one OpenCyc provides.
This research explains the definition of ontology, common sense knowledge, and the connection between them. This research also analyze the knowledge reuse in MAS during the knowledge management process, and four approaches to incorporating common sense ontology in MAS are proposed and evaluated. Finally, the favorite approach is advocated. In addition, a common sense ontology-supported artificial intelligence application is investigated in a multi-agent systems context, for solving a certain problem existing in the real world. The implementation of this application demonstrates that this research is reasonable and workable.
The main part of this thesis (Chapters 2-4) has been organized elsewhere as a full paper (Jingwen He, Hokyin Lai, and Huaiqing Wang, in press), and has been accepted by the Journal of Expert Systems with Applications.
Key words: common sense ontology, multi-agent architecture, intelligent agents|
|Online Catalog Link: ||http://lib.cityu.edu.hk/record=b2340682|
|Appears in Collections:||IS - Master of Philosophy |
Items in CityU IR are protected by copyright, with all rights reserved, unless otherwise indicated.