Route travel time estimation using low-frequency floating car data
2013 (English)In: 2013 16th International IEEE Conference on Intelligent Transportation Systems - (ITSC): Intelligent Transportation Systems for All Modes, IEEE conference proceedings, 2013, 2292-2297 p.Conference paper (Refereed)
The paper develops a non-parametric method for route travel time estimation using low-frequency floating car data (FCD). While most previous work has focused on link travel time estimation, the method uses FCD observations directly for estimating the travel time distribution on a defined route. A list of potential biases associated with FCD is presented and discussed. For each source of bias, a correction method for the observations is proposed. The estimation method is implemented using FCD data from taxis in Stockholm, Sweden. Estimates are compared to observed travel times for two routes equipped with automatic number plate recognition (ANPR) cameras. The mean travel time estimates incorporating all bias corrections perform equally well or better than the link-based approach in terms of RMSE, and estimated percentiles show a good match to ANPR.
Place, publisher, year, edition, pages
IEEE conference proceedings, 2013. 2292-2297 p.
Transport Systems and Logistics
IdentifiersURN: urn:nbn:se:kth:diva-138257DOI: 10.1109/ITSC.2013.6728569ISI: 000346481000367ScopusID: 2-s2.0-84894335977ISBN: 978-1-4799-2914-6OAI: oai:DiVA.org:kth-138257DiVA: diva2:680658
2013 16th International IEEE Conference on Intelligent Transportation Systems - (ITSC), October 6-9, 2013 – Kurhaus – The Hague, The Netherlands
QC 20140218. TSC import 2408 2013-12-172013-12-182013-12-182015-12-03Bibliographically approved