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


4.2. WHALE WATCHER EXPERT SYSTEM

Acquired Intelligence, Ministry of Fisheries and Oceans Canada
Canada, 1995

The Whale Watcher Expert System contains a simple taxonomic knowledge base on whales. The primary resource for this knowledge was a booklet that was produced by Fisheries and Oceans Canada. The system will prompt the user for observations it believes are pertinent. Queries are produced in a rule-driven, backward-chaining manner and presented as selection menus on the screen. Hence, the dialog is very simple. Questions of the kind: "Did the whale have a hump on its back?" are characteristic for the type of interaction that it pursues. You are expected to select either "yes," "no," or "unknown" from the accompanying menu. After a series of questions, the system reaches a conclusion and presents it to the user. Obviously, the knowledge base that it possesses is not a big step from the rule-based taxonomy system that Winston first built. What makes it powerful is the combination with multimedia and the fact that it is available to the public on the Internet. In spite of the original intention of making the system a demo to illustrate the capabilities of an expert system shell, the system illustrates very well its application to natural resource management. The early expert systems operated in a way that could be defined as telephone support systems. This is much like the one described for the maceral analysis above. Interaction depends on a form of communication that is typical for people that try to solve problems in a remote fashion, unable to observe the things that the problem owner can see. The Whale Watcher Expert System produces pictures, movies, and sounds to support its communication with the user. Hence, the users become more aware of the context that the query assumes.

The fact that this simple system is publicly available illustrates an important issue on its own. Biologists and others concerned with the state of our wildlife resources depend on the interest and commitment of the public. A person cannot be everywhere to observe and to determine. For years the professionals have been dependent on the often informal reports and observations called in by amateurs. Though having value as a first-line detection system, the inputs received vary in quality. The Whale Watcher Expert System shows that it is possible to efficiently deploy and distribute a simple knowledge-based system that can support amateurs at the time when they report ( provided that they apply E-mail for this purpose). The effect should be obvious. More reliable reports that improve the conveyance of a particular impression.

The system uses simple rules accompanied by an object-oriented approach. The interface is accommodated in HTML so that it can be browsed and viewed by tools such as the Netscape version 2.0 or higher. CGI constructions support the menus used for questioning. The Whale Watcher Expert System was created by means of the Acquire shell that is customized for Web interaction.

5. MANAGEMENT OF WATER RESOURCES

5.1. INTRODUCTION

Water is the most important natural resource on earth. The "blue planet" is distinguished from the other orbs in our solar system by the fact that much of the surface is covered with water. Water is the essence for all life and the constant subject of concern both in political debates as well as in science. Its scarcity in one region and its abundance in others have challenged Man since his origin. Contamination of drinking water has been a major issue for both health organizations and community planners. The increasing pollution from growing industry and modern farming has added to the concern for our water resources, both locally and globally. Indeed, the management of these resources has become extremely difficult. Great difficulties arise from the diverse and often conflicting use of the same water resources for purposes such as irrigation, drinking, fishing, bird and animal habitat preservation, power production, waste permission, and floating traffic. The knowledge required to understand and manage all aspects of our water resources is both diverse and vast. The need for more acute decision support, advise, as well as efficient knowledge sharing has inspired both researchers and domain professionals to exploit the use of expert systems for this purpose. Since the late 1980s an increasing activity is seen in this field. Yet most tangible results appear to have surfaced after the turn of the decade. Development trends have followed the same pattern as that illustrated for mineral exploration. However, the core is constituted by the traditional rule-based approach using a backward-chaining inference strategy. As in other domains, this has been augmented by multiple interfaces. Databases, GIS, simulation models, multi-media, and the WWW are typical companions to the rule-based knowledge base. In terms of application, many of the expert systems directed toward water resource management tend to blend resource issues with an agricultural inclination. Since farming is a major beneficiary, this is not surprising. In Table 3 we have included a list of some representative systems. A selection of these will be discussed in more detail.


TABLE 3
Systems Dealing with Management of Water Resources
 
Year
reported
Name of system Domain knowledge Technology applied Reference
 
1990 Li et al. Weed control in Florida waters
using herbicide
Intelligent databases, production
rules
(Li 90)
1992 Rhykerd et al. Lead contamination detection in
drinking water
Production rules, frames (Rhykerd 92)
1993 Booty et al. Point source water quality
modeling
Production rules (Booty 94)
1994 Expert GIS Water resource planning GIS, rule-based system, network
model
(McKinney 94)
1994 Lam et al Watershed management and
planning; Information retrieval
Intelligent database, production
rules
(Lam 95)
1996 STEWARD Water quality control Production rules, hypertext,
WorldWideWeb
(PennState 96)
1996 CORMIX Analysis of discharge and water
mixing conditions
Production rules, quantitative
models
(Doneker 96)
1997 COLOSS Support for management of
Columbia River resources
Decision-support, production
rules
(Doneker 96)


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.