Research on Expert System of Crop Disasters Based on Neural Networks


Article Preview

In order to improve the efficiency of prediction and diagnose of crop diseases and pests, and solve the problems during the course of crop production and management, then an neural networks with weight adjustment of prediction model is proposed. The crop disasters are regarded as example, after the symptoms of disasters and features are classified, abstracted and coded, the adjustment of weight, optimization of network structure and reasonable adjustment of parameters of BP neural network are discussed, then a model is constructed to forecast the disasters of crop, the weight is used as knowledge to predict disasters of crop through studying training samples. Results have shown that the optimization expert system of crop disasters based on neural network has enhanced the ability of decision making of expert system, then greatly improved the accuracy and reliability of crop diagnosis.



Edited by:

Yuning Zhong




J. Zhu et al., "Research on Expert System of Crop Disasters Based on Neural Networks", Applied Mechanics and Materials, Vol. 235, pp. 34-38, 2012

Online since:

November 2012




[1] Jiang Wenke, Yang Yunsen etal. A cotton disease and pest prediction system based on fuzzy neural network. In: Proc of PACES95. Anhui, China, 1995: 802-804.

[2] Lemmon H, Chuk N. Cotton: A cotton crop model and expert system to support on farm decisions. In: Proc of PACES95. Anhui, China, 1995: 807- 809.

[3] Wei Gao. Study on New Evolutionary Neural Network. Proceeding Soft the Second International Conference on Machine Learning and Cybemetics, Xi'an November, 2003, 34, pp.5-8.

[4] Kayama M, etal. Modeling Generalization Capacity for a Multi-Layered Neural Network Classifier and Optimizing Its Number of hidden Units. Proc of International Joint Conference on Neural Networks, 2002, 1, pp.429-434.

[5] Jin Long, Chen Ning, Lin Zhenshan. Study and comparison of ensemble forecasting based on artificial neural network [J]. Acta meteorological sinica, 1999, 57, pp.198-207.

[6] LinW, ZhangBA. Best Learning Algorithm of Multi-layer Feed forward Neural Networks for Associative Memory. Proc of International Joint Conference on Intelligent Information Processing and Systems, 2003, pp.475-478.

[7] Mzard M, Nadal, JPP. Learning in Feed-forward Layered Networks: The Tiling Algorithm. Journal of Physics and: Mathematical General, 2003, 23, pp.2191-2203.