摘要
在分析货运量影响因素的基础上,利用BP神经网络建立新疆货运量时间序列预测网络结构模型。利用1995～2006年新疆货运量历史数据,对模型进行训练和拟合,再选用2007～2008年的历史数据作为网络模型检验样本,同时采用移动平均法、指数平滑法对新疆货运量进行预测,并对预测结果作对比分析。研究表明,采用BP神经网络预测新疆货运量比采用其他预测方法更加准确。
On the basis of studying the characteristics of freight volume,the temporal series forecast model for freight volume in Xinjiang was established based on BP Neural Network.By using the historic data of freight volume in Xinjiang during the period of 1995～2006,the network was trained and simulated.Then the historic data of 2007～2008 was tested with a model,the freight volume in Xinjiang was forecasted and comparatively analyzed by using moving average method and exponential smoothing.The result showed that BP neural network was more accurate than other prediction methods.
出处
《交通标准化》
2011年第17期144-147,共4页
Communications Standardization
关键词
新疆货运量
BP神经网络
预测
Xinjiang freight volume
BP neural network
forecast
