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.
Use of Neural Network/Dynamic Algorithms to Predict Bus Travel Times Under Congested Conditions
2003
108 pages
Report
Keine Angabe
Englisch
Transportation & Traffic Planning , Algebra, Analysis, Geometry, & Mathematical Logic , Computer Software , Travel time , Dynamic models , Schedules , Reliability , Software , Patterns , Data collection , Literature reviews , Model development , Time points , Prediction , Automatic Passenger Counter(APC) , Bus arrival times , Kalman filter based dynamic algorithm , Artificial neural network
Real-time estimation of arterial travel time under congested conditions
Taylor & Francis Verlag | 2012
|A hazard-based model to derive travel time under congested conditions
Elsevier | 2023
|Improved matrix estimation under congested conditions
Online Contents | 1995
|Dynamic origin–destination demand flow estimation under congested traffic conditions
Online Contents | 2013
|Experienced travel time prediction for congested freeways
Online Contents | 2013
|