USE OF NEURAL NETWORK/DYNAMIC ALGORITHMS TO PREDICT BUS TRAVEL TIMES UNDER CONGESTED CONDITIONS

Automatic Passenger Counter (APC) systems have been implemented in various public transit systems to obtain various types of real-time information such as vehicle locations, travel times, and occupancies. Such information has great potential as input data for a variety of applications including performance evaluation, operations management, and service planning. In this study, a dynamic model for predicting bus arrival times is developed using data collected by a real-world APC system. The model consists of two major elements. The first one is an artificial neural network model for predicting bus travel time between time points for a trip occurring at given time-of-day, day-of-week, and weather condition. The second one is a Kalman filter based dynamic algorithm to adjust the arrival time prediction using up-to-the-minute bus location (operational) information. Test runs show that the developed model is quite powerful in dealing with variations in bus arrival times along the service route.

• Record URL:
  http://www.nj.gov/transportation/business/research/reports/FHWA-NJ-2003-019.pdf
• Record URL:
  https://ntlrepository.blob.core.windows.net/lib/24000/24700/24792/UseDynamicToPredictBusTimes.pdf
• 
• Summary URL:
  http://www.nj.gov/transportation/business/research/reports/FHWA-NJ-2003-019-TB.pdf
• Corporate Authors:

  New Jersey Institute of Technology, Newark

  National Center for Transportation and Industrial Productivity
  Newark, NJ  United States  07102-1982

  New Jersey Department of Transportation

  1035 Parkway Avenue
  Trenton, NJ  United States  08625

  Federal Highway Administration

  1200 New Jersey Avenue, SE
  Washington, DC  United States  20590
• Authors:
  • Chien, SI-J
  • Chen, M
  • Liu, X
• Publication Date: 2003-11

Language

• English

Media Info

• Features: Figures; References; Tables;
• Pagination: 100 p.

Subject/Index Terms

• TRT Terms: Algorithms; Kalman filtering; Mathematical models; Mathematical prediction; Neural networks; Real time information; Schedule maintenance; Traffic congestion; Transit buses; Travel time
• Uncontrolled Terms: Arrival time; Automated passenger counters
• Subject Areas: Data and Information Technology; Maintenance and Preservation; Operations and Traffic Management; Public Transportation;

Filing Info

• Accession Number: 00982126
• Record Type: Publication
• Report/Paper Numbers: FHWA-NJ-2003-019,, Final Report
• Files: NTL, TRIS, USDOT, STATEDOT
• Created Date: Nov 10 2004 12:00AM