Brought to you by EarthWeb
IT Library Logo

Click Here!
Click Here!

Search the site:
 
EXPERT SEARCH -----
Programming Languages
Databases
Security
Web Services
Network Services
Middleware
Components
Operating Systems
User Interfaces
Groupware & Collaboration
Content Management
Productivity Applications
Hardware
Fun & Games

EarthWeb Direct EarthWeb Direct Fatbrain Auctions Support Source Answers

EarthWeb sites
Crossnodes
Datamation
Developer.com
DICE
EarthWeb.com
EarthWeb Direct
ERP Hub
Gamelan
GoCertify.com
HTMLGoodies
Intranet Journal
IT Knowledge
IT Library
JavaGoodies
JARS
JavaScripts.com
open source IT
RoadCoders
Y2K Info

Previous Table of Contents Next


Chapter 9
Model-Based Reasoning

Roar Arne Fjellheim


CONTENTS

1. Introduction
2. Background and History
3. Techniques and Methodologies
3.1. Introduction
  3.2. Model Categories
  3.3. Qualitative Models
  3.4. Qualitative Simulation
  3.5. Model-Based Diagnosis
4. Applications of MBR
4.1. Introduction
  4.2. Where is MBR Used?
  4.3. Monitoring
  4.4. Control
  4.5. Diagnosis
5. Trends and Open Issues
6. Summary
References

1. INTRODUCTION

Most early expert systems relied on a knowledge base acquired from domain experts through an elaborate knowledge acquisition process. This was a consequence of the insight that "knowledge is power," applied to artificial intelligence (AI) systems, and was a key factor in the rise and success of expert systems. However, the knowledge acquisition approach led to systems with inadequate behavior in situations not covered by the expert's experience. The knowledge bases developed in this manner were often difficult to maintain, and gradually became obsolete as the target domain inevitably changed. This partly explains the many cases of otherwise successful early expert systems that gradually fell out of use.

As demonstrated in other chapters of this book, many successful responses to the knowledge acquisition challenge have been developed, including improved knowledge acquisition methodologies and tools, machine learning, and so on. In this chapter, we are concerned with another response, the so-called model-based reasoning (MBR) approach. In this approach, the expert system is seen as composed of a model of the target domain, which is used by the MBR engine to solve problems of interest to the expert system's users. The key point is that the model does not just embody an expert's heuristic experience, but somehow is a more "first-principles" description of the target domain.

In subsequent sections of this chapter, we will further motivate the MBR approach by referring to its historical development as part of AI, followed by an overview of techniques and methodologies that are available for MBR systems. We will describe some categories and examples of applications of the MBR technology. Finally, we will offer some ideas on future trends and open issues.


Previous Table of Contents Next

footer nav
Use of this site is subject certain Terms & Conditions.
Copyright (c) 1996-1999 EarthWeb, Inc.. All rights reserved. Reproduction in whole or in part in any form or medium without express written permission of EarthWeb is prohibited. Please read our privacy policy for details.