Assessing the Predictability of Scheduled-Vehicle Travel Times

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

8 Citations (Scopus)

Abstract

One of the most desired and challenging services in collective transport systems is the real-time prediction of the near-future travel times of scheduled vehicles, especially public buses, thus improving the experience of the transportation users, who may be able to better schedule their travel, and also enabling system operators to perform real-time monitoring. While travel-time prediction has been researched extensively during the past decade, the accuracies of existing techniques fall short of what is desired, and proposed mathematical prediction models are often not transferable to other systems because the properties of the travel-time-related data of vehicles are highly context-dependent, making the models difficult to fit. We propose a framework for evaluating various predictability types of the data independently of the model, and we also compare predictability analysis results of travel times with the actual prediction errors for real bus trajectories. We have applied the proposed framework to real-time data collected from buses operating in Copenhagen, Denmark.
Original languageEnglish
Title of host publicationProceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems
Number of pages4
PublisherAssociation for Computing Machinery
Publication date2009
Pages416-419
ISBN (Electronic)978-1-60558-649-6
Publication statusPublished - 2009
EventACM SIGSPATIAL International Conference on Advances in Geographic Information Systems - Seattle, United States
Duration: 4 Nov 20096 Nov 2009
Conference number: 17

Conference

ConferenceACM SIGSPATIAL International Conference on Advances in Geographic Information Systems
Number17
CountryUnited States
CitySeattle
Period04/11/200906/11/2009

Fingerprint

Travel time
Trajectories
Monitoring

Cite this

Tiesyte, D., & Jensen, C. S. (2009). Assessing the Predictability of Scheduled-Vehicle Travel Times. In Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (pp. 416-419). Association for Computing Machinery.
Tiesyte, Dalia ; Jensen, Christian Søndergaard. / Assessing the Predictability of Scheduled-Vehicle Travel Times. Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Association for Computing Machinery, 2009. pp. 416-419
@inproceedings{ca62e950ed7511deb63d000ea68e967b,
title = "Assessing the Predictability of Scheduled-Vehicle Travel Times",
abstract = "One of the most desired and challenging services in collective transport systems is the real-time prediction of the near-future travel times of scheduled vehicles, especially public buses, thus improving the experience of the transportation users, who may be able to better schedule their travel, and also enabling system operators to perform real-time monitoring. While travel-time prediction has been researched extensively during the past decade, the accuracies of existing techniques fall short of what is desired, and proposed mathematical prediction models are often not transferable to other systems because the properties of the travel-time-related data of vehicles are highly context-dependent, making the models difficult to fit. We propose a framework for evaluating various predictability types of the data independently of the model, and we also compare predictability analysis results of travel times with the actual prediction errors for real bus trajectories. We have applied the proposed framework to real-time data collected from buses operating in Copenhagen, Denmark.",
author = "Dalia Tiesyte and Jensen, {Christian S{\o}ndergaard}",
year = "2009",
language = "English",
pages = "416--419",
booktitle = "Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems",
publisher = "Association for Computing Machinery",
address = "United States",

}

Tiesyte, D & Jensen, CS 2009, Assessing the Predictability of Scheduled-Vehicle Travel Times. in Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Association for Computing Machinery, pp. 416-419, Seattle, United States, 04/11/2009.

Assessing the Predictability of Scheduled-Vehicle Travel Times. / Tiesyte, Dalia; Jensen, Christian Søndergaard.

Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Association for Computing Machinery, 2009. p. 416-419.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Assessing the Predictability of Scheduled-Vehicle Travel Times

AU - Tiesyte, Dalia

AU - Jensen, Christian Søndergaard

PY - 2009

Y1 - 2009

N2 - One of the most desired and challenging services in collective transport systems is the real-time prediction of the near-future travel times of scheduled vehicles, especially public buses, thus improving the experience of the transportation users, who may be able to better schedule their travel, and also enabling system operators to perform real-time monitoring. While travel-time prediction has been researched extensively during the past decade, the accuracies of existing techniques fall short of what is desired, and proposed mathematical prediction models are often not transferable to other systems because the properties of the travel-time-related data of vehicles are highly context-dependent, making the models difficult to fit. We propose a framework for evaluating various predictability types of the data independently of the model, and we also compare predictability analysis results of travel times with the actual prediction errors for real bus trajectories. We have applied the proposed framework to real-time data collected from buses operating in Copenhagen, Denmark.

AB - One of the most desired and challenging services in collective transport systems is the real-time prediction of the near-future travel times of scheduled vehicles, especially public buses, thus improving the experience of the transportation users, who may be able to better schedule their travel, and also enabling system operators to perform real-time monitoring. While travel-time prediction has been researched extensively during the past decade, the accuracies of existing techniques fall short of what is desired, and proposed mathematical prediction models are often not transferable to other systems because the properties of the travel-time-related data of vehicles are highly context-dependent, making the models difficult to fit. We propose a framework for evaluating various predictability types of the data independently of the model, and we also compare predictability analysis results of travel times with the actual prediction errors for real bus trajectories. We have applied the proposed framework to real-time data collected from buses operating in Copenhagen, Denmark.

M3 - Article in proceeding

SP - 416

EP - 419

BT - Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems

PB - Association for Computing Machinery

ER -

Tiesyte D, Jensen CS. Assessing the Predictability of Scheduled-Vehicle Travel Times. In Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Association for Computing Machinery. 2009. p. 416-419