论文部分内容阅读
本文根据棉花病虫害的８０种症状，构造了一个部分连接的神经网络模型，用它对数１０种棉花病虫害进行诊断，样本正确率达１００％，使用正确率达９０％以上。系统使用简便，并可推广应用到其它类农作物上。
According to the 80 kinds of symptoms of cotton pests and diseases, this paper constructs a partially connected neural network model, which is used to diagnose several kinds of cotton pests and diseases. The correct rate of the samples is 100% and the correct rate of use is more than 90%. The system is easy to use and can be applied to other types of crops.