Trip-oriented travel time prediction (TOTTP) with historical vehicle trajectories

Tao Xu; Xiang Li; Christophe Claramunt

doi:10.1007/s11707-016-0634-8

Trip-oriented travel time prediction (TOTTP) with historical vehicle trajectories

Tao Xu
, Xiang Li^*
, Christophe Claramunt

^*Corresponding author for this work

School of Geographic Sciences

Research output: Contribution to journal › Article › peer-review

28 Scopus citations

Abstract

Accurate travel time prediction is undoubtedly of importance to both traffic managers and travelers. In highly-urbanized areas, trip-oriented travel time prediction (TOTTP) is valuable to travelers rather than traffic managers as the former usually expect to know the travel time of a trip which may cross over multiple road sections. There are two obstacles to the development of TOTTP, including traffic complexity and traffic data coverage.With large scale historical vehicle trajectory data and meteorology data, this research develops a BPNN-based approach through integrating multiple factors affecting trip travel time into a BPNN model to predict trip-oriented travel time for OD pairs in urban network. Results of experiments demonstrate that it helps discover the dominate trends of travel time changes daily and weekly, and the impact of weather conditions is non-trivial.

Original language	English
Pages (from-to)	253-263
Number of pages	11
Journal	Frontiers of Earth Science
Volume	12
Issue number	2
DOIs	https://doi.org/10.1007/s11707-016-0634-8
State	Published - 1 Jun 2018

Keywords

Back Propagation Neural Networks (BPNN)
historical vehicle trajectories
trip-oriented travel time prediction (TOTTP)
urban network

Access to Document

10.1007/s11707-016-0634-8

Cite this

@article{4d4999ea4d7841aeb9bdd2b77bfe6fe6,

title = "Trip-oriented travel time prediction (TOTTP) with historical vehicle trajectories",

abstract = "Accurate travel time prediction is undoubtedly of importance to both traffic managers and travelers. In highly-urbanized areas, trip-oriented travel time prediction (TOTTP) is valuable to travelers rather than traffic managers as the former usually expect to know the travel time of a trip which may cross over multiple road sections. There are two obstacles to the development of TOTTP, including traffic complexity and traffic data coverage.With large scale historical vehicle trajectory data and meteorology data, this research develops a BPNN-based approach through integrating multiple factors affecting trip travel time into a BPNN model to predict trip-oriented travel time for OD pairs in urban network. Results of experiments demonstrate that it helps discover the dominate trends of travel time changes daily and weekly, and the impact of weather conditions is non-trivial.",

keywords = "Back Propagation Neural Networks (BPNN), historical vehicle trajectories, trip-oriented travel time prediction (TOTTP), urban network",

author = "Tao Xu and Xiang Li and Christophe Claramunt",

note = "Publisher Copyright: {\textcopyright} 2017, Higher Education Press and Springer-Verlag Berlin Heidelberg.",

year = "2018",

month = jun,

day = "1",

doi = "10.1007/s11707-016-0634-8",

language = "英语",

volume = "12",

pages = "253--263",

journal = "Frontiers of Earth Science",

issn = "2095-0195",

publisher = "Higher Education Press Limited Company",

number = "2",

}

TY - JOUR

T1 - Trip-oriented travel time prediction (TOTTP) with historical vehicle trajectories

AU - Xu, Tao

AU - Li, Xiang

AU - Claramunt, Christophe

PY - 2018/6/1

Y1 - 2018/6/1

N2 - Accurate travel time prediction is undoubtedly of importance to both traffic managers and travelers. In highly-urbanized areas, trip-oriented travel time prediction (TOTTP) is valuable to travelers rather than traffic managers as the former usually expect to know the travel time of a trip which may cross over multiple road sections. There are two obstacles to the development of TOTTP, including traffic complexity and traffic data coverage.With large scale historical vehicle trajectory data and meteorology data, this research develops a BPNN-based approach through integrating multiple factors affecting trip travel time into a BPNN model to predict trip-oriented travel time for OD pairs in urban network. Results of experiments demonstrate that it helps discover the dominate trends of travel time changes daily and weekly, and the impact of weather conditions is non-trivial.

AB - Accurate travel time prediction is undoubtedly of importance to both traffic managers and travelers. In highly-urbanized areas, trip-oriented travel time prediction (TOTTP) is valuable to travelers rather than traffic managers as the former usually expect to know the travel time of a trip which may cross over multiple road sections. There are two obstacles to the development of TOTTP, including traffic complexity and traffic data coverage.With large scale historical vehicle trajectory data and meteorology data, this research develops a BPNN-based approach through integrating multiple factors affecting trip travel time into a BPNN model to predict trip-oriented travel time for OD pairs in urban network. Results of experiments demonstrate that it helps discover the dominate trends of travel time changes daily and weekly, and the impact of weather conditions is non-trivial.

KW - Back Propagation Neural Networks (BPNN)

KW - historical vehicle trajectories

KW - trip-oriented travel time prediction (TOTTP)

KW - urban network

UR - https://www.scopus.com/pages/publications/85015012520

U2 - 10.1007/s11707-016-0634-8

DO - 10.1007/s11707-016-0634-8

M3 - 文章

AN - SCOPUS:85015012520

SN - 2095-0195

VL - 12

SP - 253

EP - 263

JO - Frontiers of Earth Science

JF - Frontiers of Earth Science

IS - 2

ER -

Trip-oriented travel time prediction (TOTTP) with historical vehicle trajectories

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this