Parameter-Transferred Irreducible LSTM for Traffic Data Imputation

We propose an imputation algorithm for missing spatiotemporal data based on long short-term memory (LSTM) model factorization in a traffic environment where the roadside units (RSUs) collect traffic speed data. We considered a scenario where data collection by RSUs occurs for each road segment, but...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE sensors journal Jg. 24; H. 14; S. 22178 - 22188
Hauptverfasser: Kwon, Jungmin, Park, Hyunggon
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 15.07.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
ISSN:1530-437X, 1558-1748
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract We propose an imputation algorithm for missing spatiotemporal data based on long short-term memory (LSTM) model factorization in a traffic environment where the roadside units (RSUs) collect traffic speed data. We considered a scenario where data collection by RSUs occurs for each road segment, but the absence of RSUs results in an incomplete dataset. To enhance imputation accuracy, we mitigate the risk of error propagation of model training on the entire dataset and take into account the spatiotemporal correlation of the dataset. The proposed algorithm can reduce the dimensionality of the input dataset by employing an adjacency matrix to identify data both highly correlated and connected to the target road segment, subsequently transforming parallel datasets into a serial format. Then, we extrapolate the missing data using an irreducible LSTM model, which is a factorization of a standard LSTM model. To enhance imputation performance, we also adopt spatial interpolation on extrapolated data across multiple paths that lead to the target road segment. Extensive experiment results using synthetic and real-world datasets confirm that the proposed algorithm outperforms other imputation algorithms in terms of imputation accuracy measured by the root mean square error (RMSE) and the mean absolute error (MAE) as well as the space complexity measured by the number of model parameters. In particular, the experiments with real-world datasets show that the proposed algorithm consistently achieves high imputation accuracy across a wide range of traffic scenarios, including actual traffic congestion and rapid traffic fluctuations.
AbstractList We propose an imputation algorithm for missing spatiotemporal data based on long short-term memory (LSTM) model factorization in a traffic environment where the roadside units (RSUs) collect traffic speed data. We considered a scenario where data collection by RSUs occurs for each road segment, but the absence of RSUs results in an incomplete dataset. To enhance imputation accuracy, we mitigate the risk of error propagation of model training on the entire dataset and take into account the spatiotemporal correlation of the dataset. The proposed algorithm can reduce the dimensionality of the input dataset by employing an adjacency matrix to identify data both highly correlated and connected to the target road segment, subsequently transforming parallel datasets into a serial format. Then, we extrapolate the missing data using an irreducible LSTM model, which is a factorization of a standard LSTM model. To enhance imputation performance, we also adopt spatial interpolation on extrapolated data across multiple paths that lead to the target road segment. Extensive experiment results using synthetic and real-world datasets confirm that the proposed algorithm outperforms other imputation algorithms in terms of imputation accuracy measured by the root mean square error (RMSE) and the mean absolute error (MAE) as well as the space complexity measured by the number of model parameters. In particular, the experiments with real-world datasets show that the proposed algorithm consistently achieves high imputation accuracy across a wide range of traffic scenarios, including actual traffic congestion and rapid traffic fluctuations.
Author Kwon, Jungmin
Park, Hyunggon
Author_xml – sequence: 1
  givenname: Jungmin
  surname: Kwon
  fullname: Kwon, Jungmin
  email: jungmin.kwon@ewha.ac.kr
  organization: Department of Electronic and Electrical Engineering, Ewha Womans University, Seoul, South Korea
– sequence: 2
  givenname: Hyunggon
  orcidid: 0000-0002-5079-1504
  surname: Park
  fullname: Park, Hyunggon
  email: hyunggon.park@ewha.ac.kr
  organization: Department of Electronic and Electrical Engineering and Smart Factory Multidisciplinary Program, Ewha Womans University, Seoul, South Korea
BookMark eNp9kLtOwzAUhi1UJNrCAyAxRGJOsWMntkcoBYrKRWqR2CxfJVdtUmxn4O1JlA6IgcXHw_edyz8Bo7qpLQCXCM4Qgvzmeb14nRWwIDOMecExOwFjVJYsR5SwUf_HMCeYfp6BSYxbCBGnJR2Du3cZ5N4mG_JNkHV0NgRrsmX_ttqrnc1W681L5pqQdYBzXmf3MslsuT-0SSbf1Ofg1MldtBfHOgUfD4vN_ClfvT0u57erXBecpFwbBiU0SpWGM0e4rspKcWewIsRwAqXjlabcaK61VlJTVWGNOJSqMIpAi6fgeuh7CM1Xa2MS26YNdTdSYMgQo7C7vKPoQOnQxBisE9oPe6Yg_U4gKPrARB-Y6AMTx8A6E_0xD8HvZfj-17kaHG-t_cWXqCo4xT8GpHlO
CODEN ISJEAZ
CitedBy_id crossref_primary_10_1016_j_compeleceng_2024_109988
Cites_doi 10.1109/TITS.2021.3119638
10.1175/1520-0442(2000)013<2217:RTCSTC>2.0.CO;2
10.1109/JSEN.2017.2777786
10.1016/j.trc.2022.103826
10.1049/iet-its.2013.0052
10.1109/JIOT.2023.3297849
10.1016/j.knosys.2021.107114
10.18637/jss.v045.i03
10.1109/TBDATA.2022.3154097
10.24963/ijcai.2018/322
10.1016/j.knosys.2020.106705
10.1109/TITS.2018.2869768
10.1109/IWCMC.2016.7577067
10.1155/2019/7602792
10.1080/15472450.2020.1713772
10.3390/ijerph110909101
10.1080/13658816.2020.1725016
10.1016/j.trc.2021.103228
10.1016/j.trc.2020.102673
10.3390/en11040705
10.1007/s12652-018-0820-5
10.1109/LWC.2018.2795605
10.1016/j.neucom.2008.11.026
10.1016/j.trc.2022.103737
10.1371/journal.pone.0195957
10.1007/s10462-019-09709-4
10.1002/atr.180
10.21437/Interspeech.2016-1446
10.1109/JSEN.2020.3007809
10.1109/TITS.2020.3030546
10.1016/j.proeng.2012.09.545
10.1109/TVT.2018.2826067
10.1049/cp:19991218
10.1109/JIOT.2022.3171780
10.1109/ACCESS.2023.3264216
10.1016/j.trc.2016.09.015
10.1109/JSEN.2023.3263539
10.1007/s10618-022-00903-7
10.23919/JCC.2021.07.001
10.1109/TPAMI.2021.3066551
10.1109/JSEN.2021.3100324
10.1109/TITS.2019.2950416
10.1007/978-3-030-89880-9_34
10.3390/electronics8080896
10.1016/j.energy.2018.01.177
10.3141/1748-12
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID 97E
RIA
RIE
AAYXX
CITATION
7SP
7U5
8FD
L7M
DOI 10.1109/JSEN.2024.3392938
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Electronics & Communications Abstracts
Solid State and Superconductivity Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
DatabaseTitle CrossRef
Solid State and Superconductivity Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
Electronics & Communications Abstracts
DatabaseTitleList Solid State and Superconductivity Abstracts

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Geography
Engineering
EISSN 1558-1748
EndPage 22188
ExternalDocumentID 10_1109_JSEN_2024_3392938
10516297
Genre orig-research
GrantInformation_xml – fundername: Institute of Information and Communications Technology Planning and Evaluation through the Korean Government Development of Distributed/Cooperative AI-based 5G+ Network Data Analytics Functions and Control Technology
  grantid: 2021-0-00739
  funderid: 10.13039/501100012389
GroupedDBID -~X
0R~
29I
4.4
5GY
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
AENEX
AGQYO
AHBIQ
AJQPL
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
EBS
F5P
HZ~
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
RIA
RIE
RNS
TWZ
AAYXX
CITATION
7SP
7U5
8FD
L7M
ID FETCH-LOGICAL-c294t-cd80a0dbb5d98f49c656b9fd3b44d940af96c79dc9cccbac7b63c190ab2db40e3
IEDL.DBID RIE
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001273156700104&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1530-437X
IngestDate Mon Jun 30 07:51:22 EDT 2025
Tue Nov 18 21:47:44 EST 2025
Sat Nov 29 06:40:01 EST 2025
Wed Aug 27 02:03:43 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 14
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c294t-cd80a0dbb5d98f49c656b9fd3b44d940af96c79dc9cccbac7b63c190ab2db40e3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-5079-1504
PQID 3081870392
PQPubID 75733
PageCount 11
ParticipantIDs ieee_primary_10516297
proquest_journals_3081870392
crossref_citationtrail_10_1109_JSEN_2024_3392938
crossref_primary_10_1109_JSEN_2024_3392938
PublicationCentury 2000
PublicationDate 2024-07-15
PublicationDateYYYYMMDD 2024-07-15
PublicationDate_xml – month: 07
  year: 2024
  text: 2024-07-15
  day: 15
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE sensors journal
PublicationTitleAbbrev JSEN
PublicationYear 2024
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref12
ref15
ref14
Karevan (ref36) 2018
ref10
Cao (ref39)
ref17
ref16
Reza (ref44)
ref19
ref18
ref51
ref50
ref46
ref45
ref48
ref47
ref42
ref41
ref43
ref49
ref8
Abadi (ref53)
ref7
ref9
ref4
ref3
ref6
ref5
Kingma (ref52) 2014
ref40
ref35
ref34
ref31
ref30
ref33
ref32
ref2
ref1
ref38
ref24
ref23
ref26
ref25
ref20
ref22
ref21
ref28
Xingjian (ref37); 28
ref27
ref29
Subramaniam (ref11)
References_xml – ident: ref41
  doi: 10.1109/TITS.2021.3119638
– ident: ref46
  doi: 10.1175/1520-0442(2000)013<2217:RTCSTC>2.0.CO;2
– ident: ref4
  doi: 10.1109/JSEN.2017.2777786
– ident: ref20
  doi: 10.1016/j.trc.2022.103826
– ident: ref8
  doi: 10.1049/iet-its.2013.0052
– start-page: 187
  volume-title: Proc. 32nd Int. Conf. Very Large Data Bases
  ident: ref11
  article-title: Online outlier detection in sensor data using non-parametric models
– ident: ref32
  doi: 10.1109/JIOT.2023.3297849
– ident: ref29
  doi: 10.1016/j.knosys.2021.107114
– ident: ref51
  doi: 10.18637/jss.v045.i03
– ident: ref31
  doi: 10.1109/TBDATA.2022.3154097
– ident: ref34
  doi: 10.24963/ijcai.2018/322
– ident: ref43
  doi: 10.1016/j.knosys.2020.106705
– ident: ref14
  doi: 10.1109/TITS.2018.2869768
– ident: ref6
  doi: 10.1109/IWCMC.2016.7577067
– ident: ref26
  doi: 10.1155/2019/7602792
– ident: ref21
  doi: 10.1080/15472450.2020.1713772
– ident: ref24
  doi: 10.3390/ijerph110909101
– ident: ref25
  doi: 10.1080/13658816.2020.1725016
– ident: ref45
  doi: 10.1016/j.trc.2021.103228
– volume: 28
  start-page: 802
  volume-title: Proc. 28th Int. Conf. Neural Inf. Process. Syst. (NIPS)
  ident: ref37
  article-title: Convolutional LSTM network: A machine learning approach for precipitation nowcasting
– ident: ref28
  doi: 10.1016/j.trc.2020.102673
– ident: ref16
  doi: 10.3390/en11040705
– ident: ref1
  doi: 10.1007/s12652-018-0820-5
– ident: ref17
  doi: 10.1109/LWC.2018.2795605
– ident: ref50
  doi: 10.1016/j.neucom.2008.11.026
– ident: ref30
  doi: 10.1016/j.trc.2022.103737
– ident: ref23
  doi: 10.1371/journal.pone.0195957
– ident: ref18
  doi: 10.1007/s10462-019-09709-4
– ident: ref22
  doi: 10.1002/atr.180
– year: 2014
  ident: ref52
  article-title: Adam: A method for stochastic optimization
  publication-title: arXiv:1412.6980
– ident: ref12
  doi: 10.21437/Interspeech.2016-1446
– ident: ref38
  doi: 10.1109/JSEN.2020.3007809
– start-page: 265
  volume-title: Proc. 12th USENIX Symp. Oper. Syst. Design Implement.
  ident: ref53
  article-title: TensorFlow: A system for large-scale machine learning
– ident: ref15
  doi: 10.1109/TITS.2020.3030546
– ident: ref49
  doi: 10.1016/j.proeng.2012.09.545
– ident: ref7
  doi: 10.1109/TVT.2018.2826067
– ident: ref33
  doi: 10.1049/cp:19991218
– year: 2018
  ident: ref36
  article-title: Spatio-temporal stacked LSTM for temperature prediction in weather forecasting
  publication-title: arXiv:1811.06341
– ident: ref19
  doi: 10.1109/JIOT.2022.3171780
– start-page: 6775
  volume-title: Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)
  ident: ref39
  article-title: BRITS: Bidirectional recurrent imputation for time series
– ident: ref10
  doi: 10.1109/ACCESS.2023.3264216
– ident: ref9
  doi: 10.1016/j.trc.2016.09.015
– ident: ref3
  doi: 10.1109/JSEN.2023.3263539
– ident: ref42
  doi: 10.1007/s10618-022-00903-7
– ident: ref2
  doi: 10.23919/JCC.2021.07.001
– ident: ref27
  doi: 10.1109/TPAMI.2021.3066551
– ident: ref40
  doi: 10.1109/JSEN.2021.3100324
– ident: ref48
  doi: 10.1109/TITS.2019.2950416
– ident: ref35
  doi: 10.1007/978-3-030-89880-9_34
– volume-title: Proc. Int. Conf. Artif. Intell.
  ident: ref44
  article-title: A convolutional recurrent autoencoder for spatio-temporal missing data imputation
– ident: ref5
  doi: 10.3390/electronics8080896
– ident: ref13
  doi: 10.1016/j.energy.2018.01.177
– ident: ref47
  doi: 10.3141/1748-12
SSID ssj0019757
Score 2.415746
Snippet We propose an imputation algorithm for missing spatiotemporal data based on long short-term memory (LSTM) model factorization in a traffic environment where...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 22178
SubjectTerms Accuracy
Algorithms
Complexity theory
Data collection
Data imputation
Data models
Datasets
Error analysis
extrapolation
Factorization
Interpolation
Long short term memory
long short-term memory (LSTM)
Missing data
parameter transfer
Parameters
Roads
Roads & highways
Roadsides
Root-mean-square errors
Segments
Sensors
spatial interpolation
Spatiotemporal data
Traffic congestion
Traffic information
Traffic speed
Training
Title Parameter-Transferred Irreducible LSTM for Traffic Data Imputation
URI https://ieeexplore.ieee.org/document/10516297
https://www.proquest.com/docview/3081870392
Volume 24
WOSCitedRecordID wos001273156700104&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
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1558-1748
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0019757
  issn: 1530-437X
  databaseCode: RIE
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB5UBPXgW1xf9OBJqKZN2jRHn6josrAKeyvJJMEFWWXtCv57kzTKgih4KT0kpcyXSb5kMt8AHGaZdjSAOQQqFCnjGlNZapEWxgvwWeNIeUD6jne71WAgejFZPeTCGGPC5TNz7F9DLF-_4MQflTkPL7IyF3wWZjkv22St75CB4EHW03kwSRnlgxjCzIg4ue1fdt1WMGfH1NMBn4sytQiFqio_puKwvlyt_PPPVmE5EsnktEV-DWbMaB2WpuQF12EhVjh_-tiAs57017CcFdOwPFkzHhud3PjnBIfq2SR3_Yf7xHHYxDXwwhLJhWxkcuOrPgT4NuHx6vLh_DqN9RNSzAVrUtQVkUQrVWhRWSbQcTclrKaKMS0YkVaUyIVGgYhKIlclRUcQpMq1YsTQLZgbvYzMNiTUcKOtVbKizuu1lJRmmVKSWml5iaYD5MugNUZxcV_j4rkOmwwiao9B7TGoIwYdOPru8toqa_zVeNMbfapha-8O7H3BVkfne6upl-lzM5nId37ptguL_uv-jDYr9mCuGU_MPszjezN8Gx-EcfUJ0vjLKQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB58gXrwWbFadQ-ehNXsJrvZHH1itS2FVuhtSSYJClKltoL_3iRdpSAKXpY9JOwyXyb5ksl8A3CcJNrRAOYQKFDEjGuMZa5FnBkvwGeNI-UB6RbvdIrBQHSrZPWQC2OMCZfPzKl_DbF8_YITf1TmPDxL8lTweVjMGEvJNF3rO2ggeBD2dD5MYkb5oApiJkSc3fWuO24zmLJT6gmBz0aZWYZCXZUfk3FYYW7W__lvG7BWUcnofIr9JsyZ4RaszggMbsFyVeP88WMbLrrSX8RydozDAmXNaGR01PTPCT6pZxO1ev125Fhs5Bp4aYnoSo5l1PR1HwKANXi4ue5f3sZVBYUYU8HGMeqCSKKVyrQoLBPo2JsSVlPFmBaMSCty5EKjQEQlkaucoqMIUqVaMWLoDiwMX4ZmFyJquNHWKllQ5_daSkqTRClJrbQ8R1MH8mXQEit5cV_l4rkM2wwiSo9B6TEoKwzqcPLd5XWqrfFX45o3-kzDqb3r0PiCrazc762kXqjPzWUi3ful2xEs3_bbrbLV7Nzvw4r_kj-xTbIGLIxHE3MAS_g-fnobHYYx9gmNFc5w
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=article&rft.atitle=Parameter-Transferred+Irreducible+LSTM+for+Traffic+Data+Imputation&rft.jtitle=IEEE+sensors+journal&rft.au=Kwon%2C+Jungmin&rft.au=Park%2C+Hyunggon&rft.date=2024-07-15&rft.issn=1530-437X&rft.eissn=1558-1748&rft.volume=24&rft.issue=14&rft.spage=22178&rft.epage=22188&rft_id=info:doi/10.1109%2FJSEN.2024.3392938&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JSEN_2024_3392938
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1530-437X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1530-437X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1530-437X&client=summon