Dynamic bus travel time prediction using an ANN-based model

Prediction of bus travel time is one of crucial issues for passengers in letting them know their departure time from an origin and arrival time at a destination and allowing them to make decisions (e.g., postpone departure time at certain hours) and to reduce their waiting time at bus stops. This paper proposes a time series approach to predict travel time over an interval between two adjacent bus stops. We build an Artificial Neural Network (ANN) model to predict travel time over the interval. To make accurate prediction, we divide a day into 8 time-periods in calculating travel time over the interval at each time-period and also use the travel time condition at right before the target time-period in order to apply the dynamical change of travel time as well as the historical average travel time at the same time-period during the past several days. To validate the proposed method, we used bus probe data collected from November 21st to December 20th in 2013, provided by Nishitetsu Bus Company, Fukuoka, Japan. Experimental results show that our models can effectively improve prediction accuracy of travel time on the route compared to a method only using the historical average travel time.