Pest Identification System
|
The pest identification system, is a system for the identification and treatment of diseases, insects and malnutrition. The system currently covers ninteen different diseases, eleven insects, and the deficiency and excess of eight different elements
- The diseases covered by the system are: Stem Rust, Leaf Rust, Yellow Rust, BYDV (Barely Yellow Dwarf), Melanesia and Brown Necrosis, Common Root Rot, Powdery mildew, Genetic Flecking, Physiological leaf spots, Black Chaff, Covered Smut, Flag smut, Downy mildew, Glume Blotch, Basal Glume Rot, Seed Gall Nematode, Septoria leaf spot, Streak Mosiac, and Loose Smut.
- The insects covered are: Mole Cricket, Cut worm, Aphids, Leaf Miners, Grain Moth, Weevils, Thrips, Wheat stem swafly, Cnephasia, and Birds and Rats (even though they are not exactly insects).
- The elements covered are: Nitrogen, Iron, Zinc, Copper, Magnesium, Phosphorus, Potassium, Calcium and Zinc.
|
| Methodology for implementation: |
In developing the Expert system for
Diagnosis & treatment of wheat disorders in Egypt,
the Generic Task Approach to expert system development
proposed by Chandrasekaran (Chandrasekaran,
1986) has been followed. A Hierarchical Classification
problem solver has been used in implementing the Wheat
disorders expert system.
|
| Tool for implemenatation: |
The pest Identification system has been implemented using the Generic Task Tool (GT-Tool) , developed at Michigan State University (MSU). The system employs a classification based on observations visible to the user on different plant parts such as leaf discoloration, stem deformation, etc. In the GT-Tool, a classification node is represented by a table matcher where each entry in the table represents either a database variable or another matcher. Each database variable is associated with a question. A user will be presented with the question only if the database variable has never been assigned a value. The combination of possible inputs for each question denotes different rules and matching patterns. If a combination of inputs results in a match value greater than a given threshold, the node is said to be established. By asking the user a series of questions, the system is able to pursue or rule out paths in the classification tree in which the leaves represent disorders.
Basically, if a path from a root to a leaf exists, then the disorder at the leaf is present.
The system begins by asking the user which growth stage the plant is in; in this way, the system is able determine which plant parts to ask about. Further questions reveal whether a plant part is normal or not. Once a plant part is known to be abnormal, the system can ask about the specific abnormality which this part manifests. This process continues until the system reaches very specific observations on that part. At this point, if the system suspects a given disorder, it tries to establish it by asking all questions relating to that disorder, even if such observations are on another plant part.
|
| Evaluation Results: |
The following graphs show the final set of scores determined by the validation process
of version 1.0 of the system. According to the comments collected during the validation
process, a newer version 1.1 was released but has not as yet been revalidated. These
scores show the experts system's standing in comparison to the other human experts.
The expert system's disease diagnosis results are equivalent to those of the best
human expert while its treatment outperforms all those of the human experts. In the Insect's
as well as in the nutrition deficiency subsystem, the expert system's diagnosis results surpass
those of the other human experts. However, its treatment results rank third among the human experts.
|
|
|
 |