Abstract A computer program (Weed Adviser) to help extension workers identify and control 47 common weeds and their mixtures, in crops of wheat, triticale, barley and oats has been developed using the expert system shell Personal Consultant™ Plus (Texas Instruments). Weed Adviser is a rule-based expert system designed to run on IBM micro-computers and compatibles. During a consultation Weed Adviser assists in identifying a weed, offers alternative control measures (if any), indicates what treatments should not be used and provides additional herbicide information (e.g. herbicide costs, application rates and times). Weed Adviser also makes users more aware of the factors that need to be considered when selecting weed control strategies and can educate users by explaining the reasoning behind the conclusion or advice. It has already shown promise as an educational tool for advisers. The knowledge representation model used and the inference strategies chosen are described.
[1]
J. M. McKinion,et al.
Expert systems for agriculture
,
1985
.
[2]
Yud-Ren Chen,et al.
Integrating a knowledge-based meat-grading system with a voice-input device.
,
1990
.
[3]
Larry D. Gaultney,et al.
An expert system for troubleshooting tractor hydraulic systems
,
1989
.
[4]
Donald A. Waterman,et al.
A Guide to Expert Systems
,
1986
.
[5]
G. M. Pasqual,et al.
Development of a prototype expert system for identification and control of insect pests
,
1988
.
[6]
J. R. Barrett,et al.
Double Cropping Expert System
,
1988
.
[7]
Douglas K. Loh,et al.
Expert Systems in Entomology: Three Approaches to Problem Solving
,
1986
.