摘要
为了提高农产品价格预测精度,提出一种改进的BP神经网络模型。先通过定性分析得到影响农产品价格波动的因子,然后采用MIV方法选择强影响力的因子作为神经网络输入节点。并采用改进的算法进行学习,寻找最优的BP网络结构。利用改进后的模型,实现了农产品价格的高精度仿真。
An improved BP neural network model is proposed to improve the precision of the prediction of agricultural products. Firstly, the factors of price fluctuation of agricultural products are gotten through the qualitative analysis and then use the MIV method to choose the strong influent factors as the input nodes of a neural network. Find the optimal structure of BP network through the improved learning algorithm, and then use the improved model to realize the agricultural high precision simulation of the product price.
出处
《唐山师范学院学报》
2014年第2期66-68,共3页
Journal of Tangshan Normal University
基金
农业部948项目(2012-z30)
关键词
农产品价格
BP神经网络
MIV
变学习率
附加动量
price of agricultural products
BP neural network
MIV
variable learning rate
momentum back propagation
