T-CONV: A Convolutional Neural Network for Multi-scale Taxi Trajectory Prediction

Precise destination prediction of taxi trajectories can benefit many intelligent location based services such as accurate ad for passengers. Traditional prediction approaches, which treat trajectories as one-dimensional sequences and process them in single scale, fail to capture the diverse two-dime...

Full description

Saved in:
Bibliographic Details
Published in:International Conference on Big Data and Smart Computing pp. 82 - 89
Main Authors: Lv, Jianming, Li, Qing, Sun, Qinghui, Wang, Xintong
Format: Conference Proceeding
Language:English
Published: IEEE 01.01.2018
Subjects:
ISSN:2375-9356
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Precise destination prediction of taxi trajectories can benefit many intelligent location based services such as accurate ad for passengers. Traditional prediction approaches, which treat trajectories as one-dimensional sequences and process them in single scale, fail to capture the diverse two-dimensional patterns of trajectories in different spatial scales. In this paper, we propose T-CONV which models trajectories as two-dimensional images, and adopts multi-layer convolutional neural networks to combine multi-scale trajectory patterns to achieve precise prediction. Furthermore, we conduct gradient analysis to visualize the multi-scale spatial patterns captured by T-CONV and extract the areas with distinct influence on the ultimate prediction. Finally, we integrate multiple local enhancement convolutional fields to explore these important areas deeply for better prediction. Comprehensive experiments based on real trajectory data show that T-CONV can achieve higher accuracy than the state-of-the-art methods.
AbstractList Precise destination prediction of taxi trajectories can benefit many intelligent location based services such as accurate ad for passengers. Traditional prediction approaches, which treat trajectories as one-dimensional sequences and process them in single scale, fail to capture the diverse two-dimensional patterns of trajectories in different spatial scales. In this paper, we propose T-CONV which models trajectories as two-dimensional images, and adopts multi-layer convolutional neural networks to combine multi-scale trajectory patterns to achieve precise prediction. Furthermore, we conduct gradient analysis to visualize the multi-scale spatial patterns captured by T-CONV and extract the areas with distinct influence on the ultimate prediction. Finally, we integrate multiple local enhancement convolutional fields to explore these important areas deeply for better prediction. Comprehensive experiments based on real trajectory data show that T-CONV can achieve higher accuracy than the state-of-the-art methods.
Author Sun, Qinghui
Li, Qing
Wang, Xintong
Lv, Jianming
Author_xml – sequence: 1
  givenname: Jianming
  surname: Lv
  fullname: Lv, Jianming
– sequence: 2
  givenname: Qing
  surname: Li
  fullname: Li, Qing
– sequence: 3
  givenname: Qinghui
  surname: Sun
  fullname: Sun, Qinghui
– sequence: 4
  givenname: Xintong
  surname: Wang
  fullname: Wang, Xintong
BookMark eNotjEtOwzAUAA0Cibb0ArDxBVz87NiJ2ZWIn1RakALb6iWxkUsaV04C9PZ8V7OZmTE5akNrCTkDPgPg5uLKv-Zhu5sJDtmMcy7ggIxByUxLnRhxSEZCpooZqfQJmXbd5tsBo41I-Yg8FSxfLV8u6ZzmoX0PzdD70GJDl3aIv-g_QnyjLkT6MDS9Z12FjaUFfnpaRNzYqg9xTx-jrX31056SY4dNZ6f_nJDnm-siv2OL1e19Pl8wD6nqWSWtclgZROSlsi7TtkSdcSx5hrUTpTQC6koLoSUkEkpQaLSrFaokcbKWE3L-9_XW2vUu-i3G_TqTOgUO8gt2sVJ9
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/BigComp.2018.00021
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISBN 1538636492
9781538636497
EISSN 2375-9356
EndPage 89
ExternalDocumentID 8367101
Genre orig-research
GroupedDBID 6IE
6IF
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
M43
OCL
RIE
RIL
ID FETCH-LOGICAL-i175t-c3e5fac9aaa0b5ef86eba680ab08adf2b3921dc622631431b15a96fd5a544f3d3
IEDL.DBID RIE
ISICitedReferencesCount 73
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000435014000012&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:50:17 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i175t-c3e5fac9aaa0b5ef86eba680ab08adf2b3921dc622631431b15a96fd5a544f3d3
PageCount 8
ParticipantIDs ieee_primary_8367101
PublicationCentury 2000
PublicationDate 2018-Jan
PublicationDateYYYYMMDD 2018-01-01
PublicationDate_xml – month: 01
  year: 2018
  text: 2018-Jan
PublicationDecade 2010
PublicationTitle International Conference on Big Data and Smart Computing
PublicationTitleAbbrev BIGCOMP
PublicationYear 2018
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0001969270
Score 2.0374918
Snippet Precise destination prediction of taxi trajectories can benefit many intelligent location based services such as accurate ad for passengers. Traditional...
SourceID ieee
SourceType Publisher
StartPage 82
SubjectTerms Clustering algorithms
Companies
convolutional neural network
multi-scale
Neural networks
Prediction algorithms
Predictive models
Public transportation
Trajectory
Title T-CONV: A Convolutional Neural Network for Multi-scale Taxi Trajectory Prediction
URI https://ieeexplore.ieee.org/document/8367101
WOSCitedRecordID wos000435014000012&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA61ePDkoxXf5ODRtdnN5uVNi8WD1ApVeiuzeciKtNIX-u9N0m3rwYunhEASyEyYL5P5ZhC61JQJsE4nqbYmyYV_sEIWWCDEgFcAl1IeicKPotuVg4Hq1dDVmgtjrY3BZ_Y6dONfvhnreXCVtSTl3iD6t86WEHzJ1dr4UxRXmSArXgxRrbvyLdypEL4V4iVJSAf6q4JKNCCd3f9tvYeaGyYe7q1tzD6q2dEB2l2VYsDVzWyg537Sfuq-3uBb7GcuKn2CDxySb8QmRntjD1Fx5NwmUy8ci_vwVWJvr96j8_7b7xU-bsLcJnrp3PfbD0lVLSEpPQSYJZpa5kArACAFs05yWwCXBAoiwbis8EgoNZp7vEU9SEqLlIHizjBgee6ooYeoPhqP7BHCjDgTViFOu1wDkzpPtZKagQaegThGjXBCw89lQoxhdTgnfw-fop0ggqXf4gzVZ5O5PUfbejErp5OLKMUfndCgaA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA6lCnqq2opvc_BobPaR7K43LZaKda2wSm9lNg9ZkVb6Qv-9SbptPXjxlBBIAjMJ82Uy3wxCFyJgESgtiCeUJGFkHqzgWxYIlWAOgPYC7ojC3ShN434_6VXQ5YoLo5RywWfqynbdX74ciZl1lTXjgBuDaN46GywMfbpga609KglP_IgumTE0ad4Wb_ZW2QAuGzFJbULQXzVUnAlp1_63-Q5qrLl4uLeyMruoooZ7qLYsxoDLu1lHzxlpPaWv1_gGm5nz8kTBB7bpN1zj4r2xAanYsW7JxKhH4Qy-Cmws1rtz33-bvezXjZ3bQC_tu6zVIWW9BFIYEDAlIlBMg0gAgOZM6ZirHHhMIacxSO3nBgt5UnCDuAIDk7zcY5BwLRkYcepABvuoOhwN1QHCjGppV6Fa6FAAi0XoiSQWDARwH6JDVLcSGnwuUmIMSuEc_T18jrY62WN30L1PH47RtlXHwotxgqrT8Uydok0xnxaT8ZnT6A8ihaOv
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=International+Conference+on+Big+Data+and+Smart+Computing&rft.atitle=T-CONV%3A+A+Convolutional+Neural+Network+for+Multi-scale+Taxi+Trajectory+Prediction&rft.au=Lv%2C+Jianming&rft.au=Li%2C+Qing&rft.au=Sun%2C+Qinghui&rft.au=Wang%2C+Xintong&rft.date=2018-01-01&rft.pub=IEEE&rft.eissn=2375-9356&rft.spage=82&rft.epage=89&rft_id=info:doi/10.1109%2FBigComp.2018.00021&rft.externalDocID=8367101