Public Transportation Bus Trajectory Prediction using Least-Squares Support Vector Machine

Nowadays, bus service becomes more and more important in the public transportation. Passengers need a more accurate time to plan their itinerary. Transit agencies need reliable data to construct the bus departure timetable and improve service quality. Therefore, a comprehensive recurrent LS-SVM modeling system is proposed to predict the bus dynamic trajectory in this paper. The study shows that the predicted results using the estimated model from LS-SVM are good agreement with the actual test results. Hence, the model can be used for bus arriving time forecasting.

  • Record URL:
  • Supplemental Notes:
    • Abstracts used with permission of ERTICO – ITS Europe.
  • Corporate Authors:

    ERTICO - ITS Europe

    Avenue Louise 326, Blue Tower, 2nd Floor
    Brussels,   Belgium  B-1050
  • Authors:
    • Lap-mou, Tam
    • Nelson, Chiang Ngoc Vai
    • Kin-hou, Lai
    • Kuok, Chi-fong
    • Li, Ke
  • Conference:
  • Publication Date: 2015


  • English

Media Info

  • Media Type: Digital/other
  • Features: Figures; Maps; Photos; References; Tables;
  • Pagination: 14p
  • Monograph Title: 22nd ITS World Congress. Proceedings

Subject/Index Terms

Filing Info

  • Accession Number: 01603781
  • Record Type: Publication
  • Report/Paper Numbers: ITS-1232
  • Files: TRIS
  • Created Date: Jun 28 2016 11:29AM