| 基于径向基神经网络的集装箱吞吐量组合预测 |
| |
| 引用本文： | 刘志杰,季令,叶玉玲,耿志民.基于径向基神经网络的集装箱吞吐量组合预测[J].同济大学学报(自然科学版),2007,35(6):739-744. |
| |
| 作者姓名： | 刘志杰 季令 叶玉玲 耿志民 |
| |
| 作者单位： | 1. 同济大学,交通运输工程学院,上海,200092;贵州师范大学,网络中心,贵州,贵阳,550001
2. 同济大学,交通运输工程学院,上海,200092 |
| |
| 摘 要： | 利用上海港国际集装箱吞吐量的历史数据,分别采用灰色预测法和三次多项式曲线模型建立了单项预测模型.利用径向基（RBF）神经网络对两个单项预测模型结果进行了组合预测,以作为其最终的预测值.实验结果表明,采用组合方法比采用单一预测方法的预测精度有了进一步的提高.最后,应用马尔可夫链预测模型对组合预测结果进行分析,增加了结果的可信性.
|
| 关 键 词： | 港口集装箱 吞吐量预测 RBF神经网络 组合预测 马尔可夫链 |
| 文章编号： | 0253-374X（2007）06-0739-06 |
| 修稿时间： | 2006-03-09 |
Combined Forecast Method of Port Container Throughput Based on RBF Neural Network |
| |
| LIU Zhijie,JI Ling,YE Yuling,GENG Zhimin.Combined Forecast Method of Port Container Throughput Based on RBF Neural Network[J].Journal of Tongji University(Natural Science),2007,35(6):739-744. |
| |
| Authors: | LIU Zhijie JI Ling YE Yuling GENG Zhimin |
| |
| Institution: | 1. School of Transportation Engineering, Tongji University, Shanghai 200092, China; 2. Network Information Center, Guizhou Normal University, Guiyang 550001 ,China |
| |
| Abstract: | Based on the historical data of Shanghai port container throughput,forecast models are established by using grey prediction model and cubic polynomial curve prediction model.Then the two individual predictions are mixed by the radial basis function(RBF) neural network and the results as the final prediction of the port container throughput.The test results show that the prediction on the basis of the combined forecast methods is precisive.At last,marqov chain prediction model is used to valify the result. |
| |
| Keywords: | port container throughput forecast RBF neural network combined forecast marqov chain |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
