Adaptive Travel-Time Estimation: A Case for Custom Predicate Selection

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

1 Citation (Scopus)

Abstract

Travel-time estimation for paths in a road network often relies on pre-computed histograms that are usually available on a road segment level. Then the pre-computed histograms of the segments of a path are convolved to obtain a histogram that estimates the travel time. With the growing sizes of trajectory datasets, it becomes possible to compute histograms for increasingly longer sub-paths. Since pre-computation is infeasible for all sub-paths in a road network, we propose computing histograms on-the-fly, i.e., during routing. Such an on-the-fly method must filter the underlying trajectory dataset by spatio-temporal predicates to obtain the relevant trajectories and offers the opportunity to apply additional filtering predicates to the trajectories with little overhead. We report on a study showing that considerable improvements in accuracy of the histograms obtained for paths can be obtained by choosing filtering predicates that not only adapt to the intended start of a trip, but also to the driver and the weather. We also make the cases for a sub-path partitioning based on segment categories since there are significant differences between road types when applying our on-the-fly method.
Original languageEnglish
Title of host publicationProceedings - 19th IEEE International Conference on Mobile Data Management, MDM 2018
Number of pages10
PublisherIEEE
Publication date13 Jul 2018
Pages96-105
ISBN (Print)978-1-5386-4134-7
ISBN (Electronic)978-1-5386-4133-0
DOIs
Publication statusPublished - 13 Jul 2018
Event19th IEEE International Conference on Mobile Data Management, MDM 2018 - Aalborg, Denmark
Duration: 25 Jun 201828 Jun 2018

Conference

Conference19th IEEE International Conference on Mobile Data Management, MDM 2018
CountryDenmark
CityAalborg
Period25/06/201828/06/2018
SponsorAalborg University, Center for Data-Intensive Systems (DAISY), Aalborg University, IEEE, IEEE Technical Committee on Data Engineering (TCDE), Otto Monsted Foundation
SeriesIEEE International Conference on Mobile Data Management (MDM)
ISSN2375-0324

Fingerprint

Travel time
Trajectories

Keywords

  • query processing
  • trajectory databases
  • travel time estimation

Cite this

Waury, R., Jensen, C. S., & Torp, K. (2018). Adaptive Travel-Time Estimation: A Case for Custom Predicate Selection. In Proceedings - 19th IEEE International Conference on Mobile Data Management, MDM 2018 (pp. 96-105). IEEE. IEEE International Conference on Mobile Data Management (MDM) https://doi.org/10.1109/MDM.2018.00026
Waury, Robert ; Jensen, Christian Søndergaard ; Torp, Kristian. / Adaptive Travel-Time Estimation : A Case for Custom Predicate Selection. Proceedings - 19th IEEE International Conference on Mobile Data Management, MDM 2018. IEEE, 2018. pp. 96-105 (IEEE International Conference on Mobile Data Management (MDM)).
@inproceedings{9773e5fa33cf411089d4e74f1e3831db,
title = "Adaptive Travel-Time Estimation: A Case for Custom Predicate Selection",
abstract = "Travel-time estimation for paths in a road network often relies on pre-computed histograms that are usually available on a road segment level. Then the pre-computed histograms of the segments of a path are convolved to obtain a histogram that estimates the travel time. With the growing sizes of trajectory datasets, it becomes possible to compute histograms for increasingly longer sub-paths. Since pre-computation is infeasible for all sub-paths in a road network, we propose computing histograms on-the-fly, i.e., during routing. Such an on-the-fly method must filter the underlying trajectory dataset by spatio-temporal predicates to obtain the relevant trajectories and offers the opportunity to apply additional filtering predicates to the trajectories with little overhead. We report on a study showing that considerable improvements in accuracy of the histograms obtained for paths can be obtained by choosing filtering predicates that not only adapt to the intended start of a trip, but also to the driver and the weather. We also make the cases for a sub-path partitioning based on segment categories since there are significant differences between road types when applying our on-the-fly method.",
keywords = "query processing, trajectory databases, travel time estimation",
author = "Robert Waury and Jensen, {Christian S{\o}ndergaard} and Kristian Torp",
year = "2018",
month = "7",
day = "13",
doi = "10.1109/MDM.2018.00026",
language = "English",
isbn = "978-1-5386-4134-7",
pages = "96--105",
booktitle = "Proceedings - 19th IEEE International Conference on Mobile Data Management, MDM 2018",
publisher = "IEEE",
address = "United States",

}

Waury, R, Jensen, CS & Torp, K 2018, Adaptive Travel-Time Estimation: A Case for Custom Predicate Selection. in Proceedings - 19th IEEE International Conference on Mobile Data Management, MDM 2018. IEEE, IEEE International Conference on Mobile Data Management (MDM), pp. 96-105, 19th IEEE International Conference on Mobile Data Management, MDM 2018, Aalborg, Denmark, 25/06/2018. https://doi.org/10.1109/MDM.2018.00026

Adaptive Travel-Time Estimation : A Case for Custom Predicate Selection. / Waury, Robert; Jensen, Christian Søndergaard; Torp, Kristian.

Proceedings - 19th IEEE International Conference on Mobile Data Management, MDM 2018. IEEE, 2018. p. 96-105.

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

TY - GEN

T1 - Adaptive Travel-Time Estimation

T2 - A Case for Custom Predicate Selection

AU - Waury, Robert

AU - Jensen, Christian Søndergaard

AU - Torp, Kristian

PY - 2018/7/13

Y1 - 2018/7/13

N2 - Travel-time estimation for paths in a road network often relies on pre-computed histograms that are usually available on a road segment level. Then the pre-computed histograms of the segments of a path are convolved to obtain a histogram that estimates the travel time. With the growing sizes of trajectory datasets, it becomes possible to compute histograms for increasingly longer sub-paths. Since pre-computation is infeasible for all sub-paths in a road network, we propose computing histograms on-the-fly, i.e., during routing. Such an on-the-fly method must filter the underlying trajectory dataset by spatio-temporal predicates to obtain the relevant trajectories and offers the opportunity to apply additional filtering predicates to the trajectories with little overhead. We report on a study showing that considerable improvements in accuracy of the histograms obtained for paths can be obtained by choosing filtering predicates that not only adapt to the intended start of a trip, but also to the driver and the weather. We also make the cases for a sub-path partitioning based on segment categories since there are significant differences between road types when applying our on-the-fly method.

AB - Travel-time estimation for paths in a road network often relies on pre-computed histograms that are usually available on a road segment level. Then the pre-computed histograms of the segments of a path are convolved to obtain a histogram that estimates the travel time. With the growing sizes of trajectory datasets, it becomes possible to compute histograms for increasingly longer sub-paths. Since pre-computation is infeasible for all sub-paths in a road network, we propose computing histograms on-the-fly, i.e., during routing. Such an on-the-fly method must filter the underlying trajectory dataset by spatio-temporal predicates to obtain the relevant trajectories and offers the opportunity to apply additional filtering predicates to the trajectories with little overhead. We report on a study showing that considerable improvements in accuracy of the histograms obtained for paths can be obtained by choosing filtering predicates that not only adapt to the intended start of a trip, but also to the driver and the weather. We also make the cases for a sub-path partitioning based on segment categories since there are significant differences between road types when applying our on-the-fly method.

KW - query processing

KW - trajectory databases

KW - travel time estimation

UR - http://www.scopus.com/inward/record.url?scp=85050812086&partnerID=8YFLogxK

U2 - 10.1109/MDM.2018.00026

DO - 10.1109/MDM.2018.00026

M3 - Article in proceeding

SN - 978-1-5386-4134-7

SP - 96

EP - 105

BT - Proceedings - 19th IEEE International Conference on Mobile Data Management, MDM 2018

PB - IEEE

ER -

Waury R, Jensen CS, Torp K. Adaptive Travel-Time Estimation: A Case for Custom Predicate Selection. In Proceedings - 19th IEEE International Conference on Mobile Data Management, MDM 2018. IEEE. 2018. p. 96-105. (IEEE International Conference on Mobile Data Management (MDM)). https://doi.org/10.1109/MDM.2018.00026