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


5. FUTURE TRENDS AND SUMMARY

Surveys of experts systems show that the majority of the expert system applications were in manufacturing, business, and medicine. In the late 1980s, there was a growth of expert system applications in the business and industrial areas, which increased from 10% of the market in 1986 to 60% in 1993.

The predominant type of expert systems (30%) is diagnosis systems, which help people to locate problems in a complex system. Interpretation and prescription systems are both more than 15%. The predominant role of expert systems has been diagnosis; in fact, that it the role most experts play in everyday life.

One reason for the large amount of diagnostic systems is because they are relatively easy to develop. Most diagnostic problems have a finite list of possible solutions and a manageable problem space. Another reason has to do with practical considerations. Most organizations prefer to take a low-risk solution when introducing new technology. Systems having the maximum chance of success at a low risk are easily accepted. Diagnostic systems are in this category.

Early expert systems took many experts and time to build. The MYCIN system was developed during the mid-1970s and took approximiately 20 person-years to complete. The major reason for the extended time was the lack of software development tools. The 1980s saw the proliferation of expert system shells. These software tools made expert systems development much easier and substantially reduced development life cycle. This is a trend that should continue in the future. In particular, there should be more UIMS tools for expert systems to simplify the design, implementation, and evaluation of expert system interfaces.

Surveys also predicted a shift from stand-alone expert systems to embedded intelligent agents. An embedded expert system builds on the existing functionality of existing software by performing some task in a more intelligent fashion. For example, with the exponential growth of the Internet and the World-Wide Web, future expert system applications would need to be integrated with various information management systems. Designers of expert system interfaces therefore will face a wider range of cognitive and social issues to increase the chance of success of an expert system in a larger context.

The number of expert system application domains are constantly increasing. Expert systems not only give advice and recommendations, but also provide a valuable source of knowledge and expertise for learning and training. Therefore, research in expert system user interface needs to focus on how to adapt an expert system user interface to a diverse group of users and adapt the system behavior to ever-changing requirements of users over an extended period of time.

REFERENCES

Berry, Dianne and Hart, Anna (Eds.). Expert Systems: Human Issues, Cambridge, MA: MIT
Press, 1990.
Berry, Dianne (1994). Involving users in expert system development, Expert Systems, 11, 1,
23-28.
Bose, Ranjit (1996). Intelligent agents framework for developing knowledge-based decision
support systems for collaborative organizational processes, Expert Systems with Applications, 11, 3, 247-261.
Casey, A. (1993). Planning interactive explanations, International Journal of
Man-Machine Studies, 38(2), 169-199.
Cheng, Billy, Liao, Qun, Park, Nam-ki, Tubaishat, Mohammed, Yu Ching Sheng, and
Yu, Jyh Hao (1996). Lymph Node Pathology Expert System, http://www-scf.usc.edu/~bcheng/es/es.html, University of Southern California, School of Business.
Clancey, B. C. and Shortliffe, E. H. (Eds.) (1984). Readings in Medical Artificial
Intelligence: The First Decade, Reading, MA: Addison-Wesley.
Duchessi, Peter and O'Keefe, Robert (1995). Understanding expert systems success and failure,
Expert Systems with Applications, 9, 2, 123-133.
Hendler, James (Ed.) (May 1988). Expert Systems: The User Interface, Norwood, NJ: Ablex
Publishing Corp.
McTear, M. F. (1993). User modelling for adaptive computer-systems: a survey of
recent developments, Artificial Intelligence Review, 7(3/4), 157-184.
Wilkins, David (1996). Knowledge based systems group, http://www-kbs.ai.uiuc.edu.


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.