Automated Identification of Linked Trips at Trip Level Using Electronic Fare Collection Data

Understanding the behavior of public transport passengers is key to providing a system from which passengers will derive the maximum benefit. One method of analyzing this behavior is with the use of passenger boarding data, stored in a database. Such a database may be improved by enriching the already existing dataset by applying specific algorithms. This paper describes an iterative classification algorithm that classifies passenger boardings at trip level into two categories; transfer journeys (linked trips) and single journeys. The dataset used was from an urban public transport operator with a large fleet (over 1000 buses) and data of 48 million magnetic strip card boardings from 1998 and 1999. This paper details the proposed iterative classification algorithm as well as various validation methods such as survey based verification, simple random sampling and Monte Carlo simulations. The outcome of the algorithm is positive and serves the successful identification of transfer journeys at trip level. The algorithm is fast, robust and produces results with an acceptable error rate even when larger amounts of noise is introduced to the EFC data set. This newly created attribute can then be re-used for other automated processes based on Electronic Fare Collection (EFC) data such as Origin/Destination identification at trip level. Furthermore detailed analyses on transfer node identification and volume, waiting time at transfer nodes and passenger behavioral studies can be created as linked trip information at trip level exists.

Language

  • English

Media Info

  • Media Type: DVD
  • Features: Figures; References; Tables;
  • Pagination: 18p
  • Monograph Title: TRB 88th Annual Meeting Compendium of Papers DVD

Subject/Index Terms

Filing Info

  • Accession Number: 01127221
  • Record Type: Publication
  • Report/Paper Numbers: 09-2417
  • Files: TRIS, TRB
  • Created Date: Apr 28 2009 8:09AM