Journal of South China University of Technology (Natural Science Edition) ›› 2016, Vol. 44 ›› Issue (8): 131-138.doi: 10.3969/j.issn.1000-565X.2016.08.019

• Traffic & Transportation Engineering • Previous Articles     Next Articles

A Travel Time Forecasting Model Based on Baseline Drift Correction

ZHU Guang-Yu1,2,33 DU Chong1,2 ZHANG Peng4   

  1. 1.Key Laboratory of Urban Transportation Complex Systems Theory and Technology of the Ministry of Education,Beijing Jiaotong University,Beijing 100044,China; 2.Center of Cooperative Innovation for Beijing Metropolitan Transportation,Beijing 100022,China; 3.Key Laboratory of System Control and Information Processing of the Ministry of Education,Shanghai Jiaotong University,Shanghai 200240,China; 4.Beijing Municipality Key Laboratory of Urban Traffic Operation Simulation and Decision Support,Beijing Transportation Research Center,Beijing 100073,China
  • Received:2015-11-30 Revised:2016-04-22 Online:2016-08-25 Published:2016-07-04
  • Contact: 朱广宇( 1972-) ，男，副教授，主要从事智能交通系统、交通系统工程研究． E-mail:gyzhu@bjtu.edu.cn
  • About author:朱广宇( 1972-) ，男，副教授，主要从事智能交通系统、交通系统工程研究．
  • Supported by:
    Supported by the General Program of National Natural Science Foundation of China( 61572069， 61503022) and the National Key Technology Research and Development Program of the Ministry of Science and Technology of China ( 2014BAG01B02)

PDF

271

Abstract: Road travel time and its forecasting value are the important bases of urban traffic management and traffic information service,and they are also an important reference for travelers to choose their reasonable traveling routes.In this paper,first,a calculation algorithm and a preprocessing method of urban travel time data are presented.Then,the status of the baseline drift in road travel time series is analyzed,and a method to correct the baseline drift is put forward by utilizing the wavelet analysis method,so as to reduce the noise of travel time series.Finally,a road travel time forecasting model is constructed based on the auto-regressive and moving average ( ARMA) model,and it is proved to be valid and accurate by using actual data.

Key words: floating car, travel time forecasting, baseline drift, wavelet analysis, auto-regressive and moving average model

CLC Number: