Comparison of Model Based and Machine Learning Approaches for Bus Arrival Time Prediction

The provision of accurate bus arrival information is critical to encourage more people to use public transport and alleviate traffic congestion. Developing a prediction scheme for bus travel times can provide such information. Prediction schemes can be data driven or may use a mathematical model that is usually less data intensive. This paper compares the performance of two methods – one being the data driven Artificial Neural Network (ANN) method and the other being the model based Kalman filter method, with regards to predicting bus travel time. The performances of both methods are evaluated using data collected from the field. It was found that the ANN based method performed slightly better in the presence of a large database but the Kalman filter method will be more advantageous when such a database is not available.

• 
• Supplemental Notes:
  • This paper was sponsored by TRB committee AP050 Bus Transit Systems.
• Corporate Authors:

  Transportation Research Board

  500 Fifth Street, NW
  Washington, DC  United States  20001
• Authors:
  • Kumar, Vivek
  • Kumar, B Anil
  • Vanajakshi, Lelitha Devi
  • Subramanian, Shankar C
• Conference:
  • Transportation Research Board 93rd Annual Meeting
  • Location: Washington DC
  • Date: 2014-1-12 to 2014-1-16
• Date: 2014

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: 14p
• Monograph Title: TRB 93rd Annual Meeting Compendium of Papers

Subject/Index Terms

• TRT Terms: Bus transit; Forecasting; Kalman filtering; Neural networks; Schedules; Travel time
• Subject Areas: Planning and Forecasting; Public Transportation; I72: Traffic and Transport Planning;

Filing Info

• Accession Number: 01520108
• Record Type: Publication
• Report/Paper Numbers: 14-2518
• Files: PRP, TRIS, TRB, ATRI
• Created Date: Mar 26 2014 10:13AM