交通运输系统工程与信息 ›› 2014, Vol. 14 ›› Issue (2): 62-67.

• 智能交通系统与信息技术 • 上一篇    下一篇

结合出行链的公交IC卡乘客下车站点判断概率模型

胡继华*1,2,邓 俊1,2,黄 泽1,2   

  1. 1.中山大学工学院,广州510275;2.广东省智能交通系统重点实验室,广州510006
  • 收稿日期:2013-09-02 修回日期:2014-01-02 出版日期:2014-04-25 发布日期:2014-07-07
  • 作者简介:胡继华(1971-),男,河南人,讲师,博士.
  • 基金资助:

    国家自然科学基金资助项目(41271181);2013年广东省安全生产专项资金项目(2013-102)

Trip-chain Based Probability Model for Identifying Alighting Stations of Smart Card Passengers

HU Ji-hua1,2, DENG Jun1,2, HUANG Ze1,2   

  1. 1. School of Engineering, Sun Yat-sen University, Guangzhou510275, China; 2. Guangdong Provincial Key Laboratory of Intelligent Transportation System, Guangzhou510006, China
  • Received:2013-09-02 Revised:2014-01-02 Online:2014-04-25 Published:2014-07-07

摘要:

综述了一票制公交IC卡乘客下车站点推断的研究现状.为充分利用乘客出行链 和站点上车客流量等信息,分析了公交出行的特征,提出了公交出行若干假设条件.在此 基础上,定义了相关集合变量来描述单个乘客的出行链,将乘客个体出行特征融入到站 点吸引权重的计算中.然后根据乘客出行链信息的完整程度,综合集计分析和非集计分析 方法建立了结合出行链的概率模型,并提出了应用模型判断乘客下车站点的算法,以及 模型检验方法.最后,以广州公交448路为例,对比了本文模型和单纯非集计分析方法的 下车站点判断结果.结果表明,本文提出的模型适用性更广,在集计分析层面具有更高的 可靠性.

关键词: 智能交通, 下车站点, OD估计, 出行链, 公交IC卡, 数据挖掘

Abstract:

This paper summarizes the research status of identifying the alighting stations of smart card passengers for flat-rate fare lines. To make best use of passenger trip chains and passenger flow of stations, it analyzes transit travel characteristics and proposes a number of assumptions. Based on these assumptions, it defines relative variables to describe passenger trip chains and considers individual characteristics for alighting attraction weighting. Then, the paper combines disaggregate analysis and aggregate analysis according to the completeness of passenger trip chains and then formulates the bus passenger alighting weight model. It also proposes the algorithm to solve the established model and a calibration method of the model. Finally, it takes Line448in Guangzhou city as an example and compared the identifying results of this new model with the identifying results of the disaggregate analysis model. The results show that the new model is more applicative in identifying the alighting stations of smart card passengers and has high reliability in a cluster analysis.

Key words: intelligent transportation, alighting station, OD estimation, trip chain, smart card, data mining

中图分类号: