Predicting Bus Travel Times in Washington, DC Using Artificial Neural Networks (ANNs)

The accurate prediction of travel time is necessary to enable public transit agencies to provide patrons with efficient transit service and for patron to effectively plan their commute. Transit agencies are continuously evaluating best practices available to improve reliability of their services. The use of technology, particularly in bus transit has been critical for this purpose. This includes the use of Automatic Vehicle Location (AVL) technology, which has been instrumental in the tracking of buses in real-time. AVL technology employs Global Positioning System (GPS) installed onboard of transit buses to track its location and displaying it on a geographical map of the area. This research is aimed at developing ANN model to predict travel times of public bus transit in Washington DC.