摘要
通过分析影响罗非鱼价格波动的因素,利用BP神经网络良好的非线性映射特性,建立罗非鱼价格预测模型。选择时间、地理环境和经济条件因素作为输入层变量,价格作为输出单元,输入样本进行训练和仿真,对训练好的网络输入预测样本,将预测结果与市场实际价格进行比较,结果表明,该模型收敛速度快,预测精度高。该方法为水产品价格预测提供了一种新思路,有较高的应用价值。
The tilapia price prediction model was established using BP Neural Network＇s good Nonlinear mapping characteristics though analyzing the factors of influencing tilapia price fluctuation.Select different season,geographic and ecoNomic factors as variables of input layer,the price is used for the output unit,we did model training and simulation by using the input samples.We took comparison between predicted and measured data.The results showed that the model gives the fast rate of convergence and good forecasting precision.This method provides a new way to forecast the price of aquatic products and has a higher application value.
出处
《安徽农业科学》
CAS
北大核心
2010年第35期20443-20445,共3页
Journal of Anhui Agricultural Sciences
基金
农业部公益性行业科研专项(3-49)
关键词
人工神经网络
罗非鱼价格
预测
BP算法
Artificial neura1 networks
Tilapia price
Forecasting
Back propagation algorithm
