计算机技术与发展2011，Vol.21Issue(11)：84-88,5.
基于多层感知器网络的农作物疾病诊断系统
Study of Diagnosis for Diseases of Agricultural Crops Based on Multi-Layer Perceptrom Networks
摘要
Abstract
The manual diagnosis for the diseases of agricultural crops is often restricted by the individual ability and experiences so that one cannot obtain the precise results of diagnosis. To overcome this pitfall, the merge of expert systems with the rich pathological knowledge and the utilization of pattern recognition algorithm can significantly improve the precision of diagnosis. Therefore, it greatly increases the quantity and the quality of crop's production. A pattern recognition technique based on a multi-layer perception (MLP) neural network is applied to the diagnosis of soybean diseases. The MLP neural network, which is a novel and efficient feed-forward network, is based on the reflections of cortical neurons on the external stimulus and can be used to solve the problems of nonlinear inseparability. Firstly, nineteen typical symptoms of soybean diseases are collected, and then constructed to form an experimental sample set. Secondly, set up and train the MLP network model using back propagation algorithm. Finally, the test shows that the RBF model has high diagnosis precision and strong generalization ability.关键词
反向传播算法/多层感知器网络/疾病诊断/模式识别Key words
back propagation algorithm/multi-layer perception neural network/disease diagnosis/pattern recognition分类
信息技术与安全科学引用本文复制引用
陈晓艳,董朝轶,李永亭,刘月文..基于多层感知器网络的农作物疾病诊断系统[J].计算机技术与发展,2011,21(11):84-88,5.基金项目
2010年度内蒙古自治区教育自然科学研究重点项目(NJ 10070) （NJ 10070）
内蒙古工业大学校基金(X200416 （）
X200805) （）
