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:
- Record URL:
-
- Summary URL:
-
Corporate Authors:
New Jersey Institute of Technology, Newark
National Center for Transportation and Industrial Productivity
Newark, NJ United States 07102-1982New Jersey Department of Transportation
1035 Parkway Avenue
Trenton, NJ United States 08625Federal 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