期刊文献+

基于无偏灰色残差理论的铁路客运量预测研究 被引量:9

A Research on Railway Transportation Prediction based on Unbiased Grey Residual Theory
下载PDF
导出
摘要 铁路客运量作为铁路客运市场体系中的重要指标,反映铁路客运基本情况和发展水平,体现铁路在综合交通运输体系中的地位和作用。为了科学准确地预测"十三五"时期铁路客运量,在分析铁路客运量主要影响因素的基础上,构建基于无偏灰色残差理论的铁路客运量预测模型。以24年铁路客运量数据为例,通过对比支持向量机SVM预测与RBF神经网络预测的结果,验证基于无偏灰色残差理论的铁路客运量预测模型预测精度较高,进而运用此模型预测铁路客运量未来5年的数据,为铁路客运生产组织和发展规划提供理论依据。 Railway passenger volume,as an important index in the railway passenger transport market system,reflects the basic situation and development level of railway passenger transport,as well as its position and role in the comprehensive transportation system.To predict railway passenger volume scientifically and accurately during 13th Five-Year Plan period,a prediction model of railway passenger volume based on unbiased grey residual theory is constructed on the basis of analyzing the main influencing factors of railway passenger volume.Taking the 24-year railway passenger volume data as an example,by comparing the results of SVM prediction with RBF neural network prediction,it is verified that the prediction accuracy of the railway passenger volume prediction model based on unbiased grey residual theory is higher,and then the data of railway passenger volume in the next five years are predicted through this model,which provides a theoretical basis for railway passenger production organization and development planning.
作者 吴华稳 WU Huawen(School of Transportation,Beijing Jiaotong University,Beijing 100044,China;Research Institute of China Railway Information Technology Co.,Ltd.,Beijing 100844,China;Market Monitoring and Evaluation Center of the State Railway Administration,Beijing 100891,China)
出处 《铁道运输与经济》 北大核心 2019年第5期121-126,共6页 Railway Transport and Economy
基金 国家铁路局科技研究计划项目(KF2014-26)
关键词 铁路 SVM RBF神经网络 残差理论 客运量预测 Railway SVM RBF Neural Network Residual Theory Passenger Traffic Forecast
  • 相关文献

参考文献9

二级参考文献48

  • 1王艳辉,贾利民,王卓,秦勇.基于时空序列的铁路客运量数据挖掘预测[J].中国铁道科学,2005,26(4):130-135. 被引量:13
  • 2焦中信,李小芳.利用齐次马尔科夫链预测股票价格走势[J].中国商界,2008(11):32-32. 被引量:8
  • 3邵昀泓,赵阳,王炜.城市公交客运量的灰色预测研究[J].交通运输工程与信息学报,2005,3(4):33-37. 被引量:12
  • 4刘小丽.提高铁路货车使用效率的思考[J].铁道运输与经济,2006,28(9):41-42. 被引量:2
  • 5[2]PACKARDNH.Geometry from a Time Series[J].PhysRevLett,1980,459:712~716.
  • 6[4]傅立.灰色系统理论于应用[M].北京:科学技术文献出版社,1992.
  • 7[8]Hsin-His Lai Fom design of product image grey relational analysis and neural network models[J].Computers & Operations Research 2005(32):2689~2771.
  • 8Texas Transportation Institute.Traffic data collection and progress of management[R].The Federal Highway of Administration, 2002..
  • 9M Lu, K Wevers.Application of grey relational analysis for evaluating road traffic safety measures: advanced driver assistance systems against infrastructure redesign[J].IET Intelligent Transport Systems, 2007, 1(1): 3-14..
  • 10Hsu LC, Wang CH.Forecasting integrated circuit output using muitivariate grey model and grey relational analysis[J].Expert Systems with Applications, 2009, 36: 29-35.

共引文献212

同被引文献65

引证文献9

二级引证文献25

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部