Open    Access



Estimation of Travel Times on Signalized Arterials



Author(s)

Ivana Cavar1, Zvonko Kavran1 and Rino Bosnjak2

Full-Text PDF XML     335 Views

DOI:10.17265/1934-7359/2013.09.008

1. Faculty of Transport and Traffic Sciences, University of Zagreb, Zagreb HR-10000, Croatia
2. Faculty of Maritime Studies, University of Split, Split HR-21000, Croatia

This paper describes procedure for estimation of travel time on signalized arterial roads based on multiple data sources with application of dimensionality reduction. Travel time estimation approach incorporates forecast of transportation nodes impendence and travel time on network links. Forecasting period is two hours and the estimation is based on historical data and real time data on traffic conditions. Travel time estimation combines multivariate regression, principal component analysis, KNN (k-nearest neighbours), cross validation and EWMA (exponentially weighted moving average) methods. When comparing estimation methodologies, relevantly better results were achieved by KNN method than with EWMA method. This is true for every time interval considered except for evening time interval when signalized arterial roads were uncongested.

Intelligent transportation systems, travel time estimation, signalised arterial roads, exponentially weighted moving average, k-nearest neighbours.