Analysis of travel time patterns in urban using taxi GPS data

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Travel time is the basic information to city life. Accurate travel time information can help people plan travel schedule and improve work efficiency. This paper proposes a method to discover travel-time patterns which can evaluate the travel efficiency in the city. The travel time data is based on the trajectories extracted from taxi GPS data. First we propose a method to recognize popular paths between origin-destination pairs, and cluster the same trajectories together meanwhile the abnormal trajectories are discarded. We treat the travel time data as time series, and Weighted Moving Average (WMA) is used to extract the normal travel time pattern. In the final part of the paper, the model is validated through the taxi GPS data of Beijing. We recognize different travel time patterns and some real examples of different paths are analyzed.

Original languageEnglish
Title of host publicationProceedings - 2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical and Social Computing, GreenCom-iThings-CPSCom 2013
Pages512-517
Number of pages6
DOIs
StatePublished - 2013
Event2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical and Social Computing, GreenCom-iThings-CPSCom 2013 - Beijing, China
Duration: 20 Aug 201323 Aug 2013

Publication series

NameProceedings - 2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical and Social Computing, GreenCom-iThings-CPSCom 2013

Conference

Conference2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical and Social Computing, GreenCom-iThings-CPSCom 2013
Country/TerritoryChina
CityBeijing
Period20/08/1323/08/13

Keywords

  • Time series
  • Trajectory mining
  • Travel time
  • Weighted moving average

Fingerprint

Dive into the research topics of 'Analysis of travel time patterns in urban using taxi GPS data'. Together they form a unique fingerprint.

Cite this