交通运输系统工程与信息 ›› 2008, Vol. 8 ›› Issue (1): 49-54 .

• 智能交通系统与信息技术 • 上一篇    下一篇

基于小波变换的ITS数据双侧最优化集成方法与应用

刘梦涵1;于雷*1、2;耿彦斌3;陈旭梅1   

  1. 1.北京交通大学 交通运输学院 北京100044; 2.美国得克萨斯州南方大学,休斯顿 77004; 3.交通部规划研究院 交通仿真与决策支持研究中心,北京 100029
  • 收稿日期:2007-06-13 修回日期:2007-09-04 出版日期:2008-02-25 发布日期:2008-02-25
  • 通讯作者: 刘梦涵
  • 作者简介:刘梦涵(1980-),女,四川自贡人,博士生.
  • 基金资助:
    国家十五科技攻关计划重大项目“智能交通系统关键技术开发和示范工程”中课题五——智能交通系统数据管理技术研究(2002BA404A05).

A Double-sided Optimization of ITS Data Aggregation via Wavelet Transformation

LIU Meng-han1;YU Lei 1,2;GENG Yan-bin3 ; ChEN Xu-mei1   

  1. 1. School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, China;
    2.Texas Southern University, Houston 77004, U.S.A; 3. Decision Support Research Center, Transportation Planning and Research Institute, Ministry of Communications, Beijing 100044,China
  • Received:2007-06-13 Revised:2007-09-04 Online:2008-02-25 Published:2008-02-25
  • Contact: LIU Meng-han

摘要: 通过对ITS数据的频率特性进行详细分析,近年来迅速发展的基于小波变换的数据集成方法能够高效地满足不同交通用途对数据集成的需求。但现有的集成方法仅通过ITS数据序列之间的共同特性来反映数据的本质特征,忽略了数据集成过程的信息损失问题,本文通过引入信息损失指标,建立双侧最优化的集成方法,提升了数据集成的准确性。在此基础上,开发了基于MATLAB平台的数据集成软件,以北京市三环的交通流数据为例进行了实例分析,提出实际工作中应用数据集成方法的建议。

关键词: 数据集成, 小波变换, 双侧最优化, 信息损失指标

Abstract: Based on aggregation technique analyzes the frequency characteristics of traffic flow data in details, the waveletcould meet the demands of various transportation purposes on the aggregation efficiently. However, the method reflects the essential characteristics of data only by analyzing the similarities among ITS data series,which neglects the information loss during aggregation. This Paper develops a double-sided optimization method through introducing Information-Loss Index in order to improve the accuracy during data aggregation. Based on the method, this paper develops the software implementing the algorithm based on MatLab platform, and uses the traffic flow data from the third-ring express road in Beijing as a case study. The conclusions from the paper provideds suggestions for the real applications of the data aggregation.

Key words: data aggregation, wavelet transformation, double-sided optimization, information-loss index

中图分类号: