This paper demonstrates that by using GIS spatial image categorised into themes, a fuzzy logic based forecasting methodology can be performed. Fuzzy logic is best suited to this type of problem as its requisite is in handling approximate data. The methodology would allow us to: 1) predict weed population reasonably well based on approximate data, 2) take into consideration additional parameters without re-writing the algorithm, 3) refine large-scale forecasts to suit localised situations, 4) allow users to determine and inspect individual infestation factors, and 5) adapt the methodology to other weed or plant species. This paper also briefly introduces a new fuzzy If-Then operand, Case-Of, specifically used in this methodology.
Funding
Category 1 - Australian Competitive Grants (this includes ARC, NHMRC)
History
Editor
Wang L, Halgamuge S & Yao X
Start Page
524
End Page
528
Number of Pages
5
Start Date
2002-11-18
Finish Date
2002-11-22
ISBN-10
9810475209
ISBN-13
9789810475208
Location
Singapore
Publisher
Nanyang Technological University
Place of Publication
Singapore
Peer Reviewed
Yes
Open Access
No
External Author Affiliations
Faculty of Informatics and Communication; RMIT University;
Era Eligible
No
Name of Conference
1a International Conference on Fuzzy Systems and Knowledge Discovery
Parent Title
Proceedings of 1st International Conference on Fuzzy systems and knowledge discovery: Computational Intelligence for the E-Age