Upload
peregrine-floyd
View
212
Download
0
Embed Size (px)
Citation preview
Jonathan St ClairComputer Science Honours
2003
Supporting harvest prediction
using
artificial intelligence techniques
Jonathan St [email protected] 10th September 2003
Background
Jonathan St [email protected] 10th September 2003
Overview On going research done to better predict harvest
figures Often historical data is incomplete thus making
prediction difficult
Jonathan St [email protected] 10th September 2003
Complex Adaptive Systems
Too many variables for management to optimise production for both short and long term production
Not possible for management to work through every possible scenario
Seasonal variations difficult to predict
Jonathan St [email protected] 10th September 2003
Objectives
To identify aspects which could be meaningfully enhanced by the use of AI techniques
To select the most promising opportunity within the prediction and planning of the farm and
Describe the environment and its challenges in detail. Select the most appropriate AI technique/s and describe their
application to the problem. Illustrate how the farm management will benefit from this
application of technology to the business.
Jonathan St [email protected] 10th September 2003
Deliverables
Interim report describing area of application for AI (I&J)
Software design document (UCT & I&J)
Final report (UCT & I&J)
Software prototype (UCT & I&J)
Jonathan St [email protected] 10th September 2003
Impact
Enable management to quickly and reliably assess the impact of changing any of a number of variables
Increase the ability of the farm management to prepare themselves to meet a particular demand in the best possible way
Jonathan St [email protected] 10th September 2003
Success Factors
The software must be shown to endorse or contradict decisions made using the current management system
A number of test cases, of the farmers choosing, will be constructed to allow for the farmer to make judgements in the normal fashion
The AI system will be tested on the same cases and if it is shown that the system is consistently more correct, the system will be deemed successful
Jonathan St [email protected] 10th September 2003
Related Work Robert M. Dorazio and Fred A. Johnson, Bayesian and Decision Theory – A
Coherent Framework for Decision Making in Natural Resource Management.
Andrew Wilson, Consumer Demand and the Future of the Supply Chain
Anet Potgieter, “Complex Adaptive Systems, Emergence and Engineering: The Basics.”
Anet Potgieter, “Bayesian Behaviour Networks as Hyperstructures”
Fred Johnson & Ken Williams, “Protocol and Practice in the Adaptive Management of Waterfowl Harvests”, http://www.consecol.org/vol3/iss1/art8/
Nils J. Nilsson, “Artificial Intelligence: A new Synthesis” ISBN 1-55860-535-5, 37 -55, 343 – 346
Jonathan St [email protected] 10th September 2003