Driving Safety Risk Prediction Using Cost-Sensitive With Nonnegativity-Constrained Autoencoders Based on Imbalanced Naturalistic Driving Data

A large number of studies have shown that most vehicle collisions are caused by drivers' abnormal operations. To ensure the safety of all people on the road network as much as possible, it is crucial to be able to predict the drivers' driving safety risks in real time. In this paper, we pr...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on intelligent transportation systems Ročník 20; číslo 12; s. 4450 - 4465
Hlavní autoři:	Chen, Jie, Wu, ZhongCheng, Zhang, Jun
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.12.2019 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L 1/<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L 2-Nonnegativity-constrained autoencoder <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L 1/<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L 2-nonnegativity-constrained Focal Loss Accident reconstruction Accidents adaptive search Automobile safety class imbalance Computer crashes Drivers driving safety risk prediction Feature extraction naturalistic driving study Real-time systems Risk levels Roads Safety Sliding Time series analysis Vehicle safety Vehicles Windows (intervals)
ISSN:	1524-9050, 1558-0016
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	A large number of studies have shown that most vehicle collisions are caused by drivers' abnormal operations. To ensure the safety of all people on the road network as much as possible, it is crucial to be able to predict the drivers' driving safety risks in real time. In this paper, we propose a novel cost-sensitive L 1 /L 2 -nonnegativity-constrained deep autoencoder network for driving safety risk prediction. Unfortunately, with existing research methods, the size of the sliding time window is too large, the feature extraction is relatively subjective, and class imbalances occur, which leads to low identification accuracy, long prediction times, and poor applicability. We first propose using a three-layer L 1 /L 2 -nonnegativity-constrained autoencoder to adaptively search the optimal size of the sliding window and then construct a deep L 1 /L 2 -nonnegativity-constrained autoencoder network to automatically extract the hidden features of the driving behaviors. Finally, we build a new L 1 /L 2 -nonnegativityconstrained focal loss classifier to predict the driving behaviors under different safety risk levels. The results from the public 100-Car naturalistic driving study dataset indicate that our method can effectively find the optimal window size, reduce the data volume and reconstruction error, and extract more distinctive features. Furthermore, this method effectively curbs the class imbalance, improves the driving safety risk prediction performance, reduces overfitting, shortens the prediction time, and improves the timeliness.
AbstractList	A large number of studies have shown that most vehicle collisions are caused by drivers’ abnormal operations. To ensure the safety of all people on the road network as much as possible, it is crucial to be able to predict the drivers’ driving safety risks in real time. In this paper, we propose a novel cost-sensitive [Formula Omitted]-nonnegativity-constrained deep autoencoder network for driving safety risk prediction. Unfortunately, with existing research methods, the size of the sliding time window is too large, the feature extraction is relatively subjective, and class imbalances occur, which leads to low identification accuracy, long prediction times, and poor applicability. We first propose using a three-layer [Formula Omitted]-nonnegativity-constrained autoencoder to adaptively search the optimal size of the sliding window and then construct a deep [Formula Omitted]-nonnegativity-constrained autoencoder network to automatically extract the hidden features of the driving behaviors. Finally, we build a new [Formula Omitted]-nonnegativity-constrained focal loss classifier to predict the driving behaviors under different safety risk levels. The results from the public 100-Car naturalistic driving study dataset indicate that our method can effectively find the optimal window size, reduce the data volume and reconstruction error, and extract more distinctive features. Furthermore, this method effectively curbs the class imbalance, improves the driving safety risk prediction performance, reduces overfitting, shortens the prediction time, and improves the timeliness. A large number of studies have shown that most vehicle collisions are caused by drivers' abnormal operations. To ensure the safety of all people on the road network as much as possible, it is crucial to be able to predict the drivers' driving safety risks in real time. In this paper, we propose a novel cost-sensitive L 1 /L 2 -nonnegativity-constrained deep autoencoder network for driving safety risk prediction. Unfortunately, with existing research methods, the size of the sliding time window is too large, the feature extraction is relatively subjective, and class imbalances occur, which leads to low identification accuracy, long prediction times, and poor applicability. We first propose using a three-layer L 1 /L 2 -nonnegativity-constrained autoencoder to adaptively search the optimal size of the sliding window and then construct a deep L 1 /L 2 -nonnegativity-constrained autoencoder network to automatically extract the hidden features of the driving behaviors. Finally, we build a new L 1 /L 2 -nonnegativityconstrained focal loss classifier to predict the driving behaviors under different safety risk levels. The results from the public 100-Car naturalistic driving study dataset indicate that our method can effectively find the optimal window size, reduce the data volume and reconstruction error, and extract more distinctive features. Furthermore, this method effectively curbs the class imbalance, improves the driving safety risk prediction performance, reduces overfitting, shortens the prediction time, and improves the timeliness.
Author	Chen, Jie Wu, ZhongCheng Zhang, Jun
Author_xml	– sequence: 1 givenname: Jie orcidid: 0000-0002-9605-4331 surname: Chen fullname: Chen, Jie email: cj2016@mail.ustc.edu.cn organization: Chinese Academy of Sciences, Hefei Institute of Physical Science, Hefei, China – sequence: 2 givenname: ZhongCheng surname: Wu fullname: Wu, ZhongCheng email: zcwu@iim.ac.cn organization: Chinese Academy of Sciences, Hefei Institute of Physical Science, Hefei, China – sequence: 3 givenname: Jun orcidid: 0000-0003-1321-6022 surname: Zhang fullname: Zhang, Jun email: zhang_jun@hmfl.ac.cn organization: Chinese Academy of Sciences, Hefei Institute of Physical Science, Hefei, China
BookMark	eNp9kM1OGzEUha0KpELKA1RsLLGe1PaMx_YSwk8jIYpIUJejO841NQ022A5SHqLv3BkFumDR1fU99jnH-g7JXogBCfnK2ZRzZr4t58vFVDCup0LrVmj2iRxwKXXFGG_3xrNoKsMk-0wOc34c1EZyfkD-nCf_6sMDXYDDsqV3Pv-mtwlX3hYfA73P4-Us5lItMGRf_CvSn778ojcxBHyAQfBlW81iyCWBD7iip5sSMdi4wpTpGeRBGpLmTz2sIdhhu4GySbD2uXhL3z9wDgW-kH0H64xHb3NC7i8vlrPv1fWPq_ns9LqywtSlAils7YThrUTd2laZGiW2ulHCtVpb6ZTRPSoFxvFeNL10rGcGVCNQORD1hJzscp9TfNlgLt1j3KQwVHairhkTDR8yJ4TvXtkUc07ouufknyBtO866kXo3Uu9G6t0b9cGjPnisLzCiHOms_-s83jk9Iv5r0i1Xipn6L9a9k-w
CODEN	ITISFG
CitedBy_id	crossref_primary_10_1109_TITS_2021_3086411 crossref_primary_10_1109_TITS_2022_3166275 crossref_primary_10_1007_s11831_023_10062_7 crossref_primary_10_1016_j_aap_2022_106568 crossref_primary_10_1016_j_aap_2021_106122 crossref_primary_10_1177_09544070241265633 crossref_primary_10_3390_app122211688 crossref_primary_10_1109_ACCESS_2019_2932434 crossref_primary_10_1016_j_eswa_2024_123619 crossref_primary_10_1016_j_aap_2023_107155 crossref_primary_10_1016_j_knosys_2021_107288 crossref_primary_10_1016_j_eswa_2021_115041 crossref_primary_10_1109_TITS_2021_3055545 crossref_primary_10_1007_s10489_023_04451_5 crossref_primary_10_1109_TITS_2023_3237681 crossref_primary_10_1007_s11042_023_17864_8 crossref_primary_10_1002_adfm_202405321 crossref_primary_10_1007_s00500_023_09331_1 crossref_primary_10_1016_j_aap_2020_105665 crossref_primary_10_1016_j_aap_2021_106537 crossref_primary_10_1016_j_eswa_2025_127502 crossref_primary_10_1145_3357253 crossref_primary_10_3390_designs7040100 crossref_primary_10_1109_TITS_2023_3274256 crossref_primary_10_1016_j_ijepes_2023_109512 crossref_primary_10_1016_j_rineng_2023_101025 crossref_primary_10_3390_en14040944 crossref_primary_10_1016_j_ins_2021_07_053 crossref_primary_10_1016_j_aap_2023_107269 crossref_primary_10_1016_j_trf_2024_12_020 crossref_primary_10_1109_TITS_2022_3193125 crossref_primary_10_3390_s25103213 crossref_primary_10_1631_FITEE_2000667 crossref_primary_10_1080_15472450_2025_2478469 crossref_primary_10_1109_TITS_2023_3314402 crossref_primary_10_3390_su13116102 crossref_primary_10_3390_ijerph18147534
Cites_doi	10.17226/14494 10.1016/j.neucom.2018.07.050 10.1109/CVPR.2008.4587630 10.1109/JAS.2017.7510814 10.1109/TVT.2014.2369522 10.1016/j.aap.2005.03.003 10.1109/JBHI.2017.2705031 10.1016/j.trc.2017.05.015 10.1007/978-3-319-39378-0_1 10.1016/j.asoc.2017.02.019 10.1109/ICMLA.2016.0132 10.1109/PST.2016.7906929 10.1016/j.aap.2006.04.012 10.1016/j.trf.2017.12.006 10.1162/neco.2006.18.7.1527 10.1109/TITS.2010.2072502 10.3141/2147-09 10.1109/TNNLS.2015.2479223 10.1109/TNNLS.2017.2770179 10.1109/TII.2018.2799928 10.1109/TITS.2015.2498408 10.1016/j.tra.2010.02.001 10.1109/TITS.2017.2700869 10.1016/j.eswa.2011.09.058 10.1109/TKDE.2008.239 10.1037/e729262011-001 10.1016/j.dss.2013.06.001 10.1016/j.aap.2016.10.006 10.1109/ICCV.2017.324 10.1109/TIE.2017.2739691 10.1145/1390156.1390294 10.1016/j.tra.2017.10.018 10.1016/j.trf.2015.10.011 10.1109/SmartCity.2015.63 10.1109/IJCNN.2016.7727349 10.1016/j.aap.2015.07.007 10.1109/TNB.2015.2403274 10.1109/TITS.2017.2649541 10.1016/j.aap.2012.06.014 10.1037/e624282011-001 10.1109/ICSMC.2008.4811498 10.1109/TMM.2017.2729019 10.1109/TKDE.2006.17 10.1109/THMS.2017.2776605 10.1109/TITS.2014.2368980 10.1109/LSP.2017.2752459 10.1109/TNNLS.2014.2310059 10.1016/j.aap.2012.05.019 10.1016/j.neunet.2017.04.012 10.1109/TITS.2017.2711046 10.1109/TITS.2018.2835523 10.1016/j.imavis.2017.01.005 10.1061/(ASCE)TE.1943-5436.0000068 10.1016/j.dss.2017.04.009 10.1109/TIP.2015.2487860 10.1109/TITS.2011.2179537 10.1109/TITS.2009.2018321 10.1109/JPROC.2016.2634938 10.1016/j.cosrev.2017.01.001 10.1177/154193120504902222
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD FR3 JQ2 KR7 L7M L~C L~D
DOI	10.1109/TITS.2018.2886280
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore Digital Library CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database Engineering Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Civil Engineering Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Civil Engineering Abstracts
Database_xml	– sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) (UW System Shared) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1558-0016
EndPage	4465
ExternalDocumentID	10_1109_TITS_2018_2886280 8617709
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 61273323 funderid: 10.13039/501100001809 – fundername: Chinese Academy of Sciences grantid: KFJ-STS-SCYD-017 funderid: 10.13039/501100002367
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AETIX AGQYO AGSQL AHBIQ AIBXA AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P PQQKQ RIA RIE RNS ZY4 AAYXX CITATION 7SC 7SP 8FD FR3 JQ2 KR7 L7M L~C L~D
ID	FETCH-LOGICAL-c293t-a52c3f29165e86c6793e5e68472f688c5f798be77a9f1b24b5f0b09a742e7fa23
IEDL.DBID	RIE
ISICitedReferencesCount	44
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000505522400016&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1524-9050
IngestDate	Sun Nov 09 06:23:51 EST 2025 Sat Nov 29 06:34:52 EST 2025 Tue Nov 18 22:41:41 EST 2025 Wed Aug 27 06:02:06 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	12
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-c293t-a52c3f29165e86c6793e5e68472f688c5f798be77a9f1b24b5f0b09a742e7fa23
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-1321-6022 0000-0002-9605-4331
PQID	2330024179
PQPubID	75735
PageCount	16
ParticipantIDs	crossref_primary_10_1109_TITS_2018_2886280 proquest_journals_2330024179 ieee_primary_8617709 crossref_citationtrail_10_1109_TITS_2018_2886280
PublicationCentury	2000
PublicationDate	2019-12-01
PublicationDateYYYYMMDD	2019-12-01
PublicationDate_xml	– month: 12 year: 2019 text: 2019-12-01 day: 01
PublicationDecade	2010
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on intelligent transportation systems
PublicationTitleAbbrev	TITS
PublicationYear	2019
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	ref57 ref13 sta (ref2) 2015; 15 ref56 ref12 hinton (ref63) 1993 ref59 ref15 ref58 ref14 ref53 ref52 ref55 ref54 campbell (ref37) 2012 hendricks (ref10) 2001 ref16 ref19 ref18 dot (ref35) 2010 neale (ref39) 2005 ref51 ref50 treat (ref9) 1979 ref46 ref45 ref48 ref47 ref44 ref43 ref49 ref8 ref7 (ref11) 2006 krizhevsky (ref1) 2012 ref81 martinelli (ref66) 2017 hanowski (ref42) 2006; 49 ref80 ref79 ref78 klauer (ref34) 2006 masnadi-shirazi (ref73) 2015 ref36 ref75 ref74 ref30 ref77 ref32 (ref3) 2013 ervin (ref33) 2005 (ref40) 2010 ref38 (ref6) 2004 john (ref31) 2013 dingus (ref41) 2006 ref71 ref70 ref72 masko (ref76) 2015 ref68 ref24 ref67 ref26 ref69 ref25 ref64 ref20 mackay (ref5) 2000; 44 ref22 ref65 ref21 finch (ref4) 1994 ref28 marotta (ref17) 2017; 24 ref29 santini (ref23) 2010 fugiglando (ref27) 2018 ayinde (ref82) 2018 ref60 ref62 ref61
References_xml	– ident: ref36 doi: 10.17226/14494 – ident: ref59 doi: 10.1016/j.neucom.2018.07.050 – ident: ref72 doi: 10.1109/CVPR.2008.4587630 – year: 2018 ident: ref27 article-title: Driving behavior analysis through CAN bus data in an uncontrolled environment publication-title: IEEE Trans Intell Transp Syst – year: 2013 ident: ref3 publication-title: Global Status Report on Road Safety 2013 – year: 2010 ident: ref35 article-title: An analysis of driver inattention using a case-crossover approach on 100-car data: Final report – start-page: 338 year: 2013 ident: ref31 article-title: Estimating continuous distributions in Bayesian classifiers publication-title: Proc 11th Conf Uncertainty Artif Intell – ident: ref13 doi: 10.1109/JAS.2017.7510814 – ident: ref15 doi: 10.1109/TVT.2014.2369522 – ident: ref8 doi: 10.1016/j.aap.2005.03.003 – ident: ref70 doi: 10.1109/JBHI.2017.2705031 – ident: ref32 doi: 10.1016/j.trc.2017.05.015 – start-page: 3 year: 1993 ident: ref63 article-title: Autoencoders, minimum description length and Helmholtz free energy publication-title: Proc Adv Neural Inf Process Syst – year: 2010 ident: ref40 publication-title: Naturalistic Driving Observing Everyday Driving Behavior – ident: ref58 doi: 10.1007/978-3-319-39378-0_1 – start-page: 30 year: 2012 ident: ref37 publication-title: The SHRP 2 naturalistic driving study Addressing driver performance and behavior in traffic safety – ident: ref61 doi: 10.1016/j.asoc.2017.02.019 – year: 2004 ident: ref6 publication-title: World report on road traffic injury prevention – ident: ref71 doi: 10.1109/ICMLA.2016.0132 – year: 1994 ident: ref4 article-title: Speed_speed limits and accidents – start-page: 1 year: 2005 ident: ref39 article-title: An overview of the 100-car naturalistic study and findings – ident: ref67 doi: 10.1109/PST.2016.7906929 – ident: ref25 doi: 10.1016/j.aap.2006.04.012 – ident: ref21 doi: 10.1016/j.trf.2017.12.006 – ident: ref64 doi: 10.1162/neco.2006.18.7.1527 – ident: ref16 doi: 10.1109/TITS.2010.2072502 – ident: ref45 doi: 10.3141/2147-09 – ident: ref48 doi: 10.1109/TNNLS.2015.2479223 – ident: ref57 doi: 10.1109/TNNLS.2017.2770179 – ident: ref77 doi: 10.1109/TII.2018.2799928 – ident: ref74 doi: 10.1109/TITS.2015.2498408 – ident: ref24 doi: 10.1016/j.tra.2010.02.001 – ident: ref26 doi: 10.1109/TITS.2017.2700869 – ident: ref29 doi: 10.1016/j.eswa.2011.09.058 – ident: ref69 doi: 10.1109/TKDE.2008.239 – year: 2006 ident: ref34 article-title: The impact of driver inattention on near-crash/crash risk: An analysis using the 100-car naturalistic driving study data doi: 10.1037/e729262011-001 – ident: ref28 doi: 10.1016/j.dss.2013.06.001 – ident: ref18 doi: 10.1016/j.aap.2016.10.006 – ident: ref60 doi: 10.1109/ICCV.2017.324 – ident: ref80 doi: 10.1109/TIE.2017.2739691 – ident: ref62 doi: 10.1145/1390156.1390294 – ident: ref20 doi: 10.1016/j.tra.2017.10.018 – ident: ref38 doi: 10.1016/j.trf.2015.10.011 – year: 2017 ident: ref66 article-title: Human behavior characterization for driving style recognition in vehicle system publication-title: Comput Elect Eng – year: 2015 ident: ref76 publication-title: The impact of imbalanced training data for convolutional neural networks – ident: ref55 doi: 10.1109/SmartCity.2015.63 – ident: ref68 doi: 10.1109/IJCNN.2016.7727349 – year: 2005 ident: ref33 article-title: Automotive collision avoidance system field operational test report: Methodology and results – ident: ref47 doi: 10.1016/j.aap.2015.07.007 – ident: ref75 doi: 10.1109/TNB.2015.2403274 – year: 2010 ident: ref23 publication-title: OBD-II Functions monitors and diagnostic techniques – year: 2015 ident: ref73 publication-title: Cost-sensitive learning in support vector machines – ident: ref51 doi: 10.1109/TITS.2017.2649541 – year: 2001 ident: ref10 article-title: The relative frequency of unsafe driving acts in serious traffic crashes – year: 2006 ident: ref11 article-title: Report to congress on the large truck crash causation study – ident: ref19 doi: 10.1016/j.aap.2012.06.014 – year: 2006 ident: ref41 article-title: The 100-car naturalistic driving study, phase II-Results of the 100-car field experiment doi: 10.1037/e624282011-001 – ident: ref12 doi: 10.1109/ICSMC.2008.4811498 – start-page: 1097 year: 2012 ident: ref1 article-title: ImageNet classification with deep convolutional neural networks publication-title: Proc Adv Neural Inf Process Syst – ident: ref78 doi: 10.1109/TMM.2017.2729019 – ident: ref65 doi: 10.1109/TKDE.2006.17 – ident: ref54 doi: 10.1109/THMS.2017.2776605 – ident: ref14 doi: 10.1109/TITS.2014.2368980 – volume: 15 start-page: 286 year: 2015 ident: ref2 article-title: Global status report on road safety publication-title: Injury Prevention – ident: ref49 doi: 10.1109/LSP.2017.2752459 – ident: ref50 doi: 10.1109/TNNLS.2014.2310059 – year: 2018 ident: ref82 publication-title: Building efficient ConvNets using redundant feature pruning – ident: ref7 doi: 10.1016/j.aap.2012.05.019 – ident: ref52 doi: 10.1016/j.neunet.2017.04.012 – ident: ref53 doi: 10.1109/TITS.2017.2711046 – ident: ref56 doi: 10.1109/TITS.2018.2835523 – ident: ref81 doi: 10.1016/j.imavis.2017.01.005 – ident: ref46 doi: 10.1061/(ASCE)TE.1943-5436.0000068 – volume: 44 start-page: 75 year: 2000 ident: ref5 article-title: Age and gender effects on injury outcome for restrained occupants in frontal crashes: A comparison of UK and US data bases publication-title: Annu Proc Assoc Adv Automot Med – year: 1979 ident: ref9 article-title: Tri-level study of the causes of traffic accidents – ident: ref30 doi: 10.1016/j.dss.2017.04.009 – ident: ref79 doi: 10.1109/TIP.2015.2487860 – ident: ref44 doi: 10.1109/TITS.2011.2179537 – ident: ref43 doi: 10.1109/TITS.2009.2018321 – ident: ref22 doi: 10.1109/JPROC.2016.2634938 – volume: 24 start-page: 35 year: 2017 ident: ref17 article-title: Cyber-insurance survey publication-title: Comput Sci Rev doi: 10.1016/j.cosrev.2017.01.001 – volume: 49 start-page: 1989 year: 2006 ident: ref42 article-title: The 100-car naturalistic driving study: A descriptive analysis of light vehicle-heavy vehicle interactions from the light vehicle driver's perspective, data analysis results publication-title: Proc Human Factors Ergonom Soc Annu Meeting doi: 10.1177/154193120504902222
SSID	ssj0014511
Score	2.4978013
Snippet	A large number of studies have shown that most vehicle collisions are caused by drivers' abnormal operations. To ensure the safety of all people on the road... A large number of studies have shown that most vehicle collisions are caused by drivers’ abnormal operations. To ensure the safety of all people on the road...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	4450
SubjectTerms	<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L 1/<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L 2-Nonnegativity-constrained autoencoder <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L 1/<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L 2-nonnegativity-constrained Focal Loss Accident reconstruction Accidents adaptive search Automobile safety class imbalance Computer crashes Drivers driving safety risk prediction Feature extraction naturalistic driving study Real-time systems Risk levels Roads Safety Sliding Time series analysis Vehicle safety Vehicles Windows (intervals)
Title	Driving Safety Risk Prediction Using Cost-Sensitive With Nonnegativity-Constrained Autoencoders Based on Imbalanced Naturalistic Driving Data
URI	https://ieeexplore.ieee.org/document/8617709 https://www.proquest.com/docview/2330024179
Volume	20
WOSCitedRecordID	wos000505522400016&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/IET Electronic Library (IEL) (UW System Shared) customDbUrl: eissn: 1558-0016 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014511 issn: 1524-9050 databaseCode: RIE dateStart: 20000101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aPOjBt1hf5OBJjGafSY4-0UsRW9Hbkk0mWtRW2q3gj_A_m0m3RVAEb7uQhCzfZmaS-fINIftKcJcnkWaRj8VZqlPOlIGUcTCpMLrMobSh2IRoteTDg7qZIYfTuzAAEMhncISPIZdv-2aER2XH0rtbgbf1ZoXIx3e1phkD1NkK2qhxyhTPJhnMiKvjznWnjSQueRRLH8CjAuQ3HxSKqvywxMG9XC79b2LLZLEOI-nJGPcVMgO9VbLwTVxwjXyeD7p4WkDb2kH1QW-7w2d6M8DEDIJBA1mAnvWHFWsjix3tHr3vVk-0heSXx7quBMOSnqGQBFh6Mqr6qHyJ7Gd66h2gpX6k69cSCZLGv7V00PEI6s90MoFzXel1cnd50Tm7YnXxBWZ8BFAxncUmcbGPHjOQucn9OoYMcu_MYpdLaTInlCxBCK1cVMZpmTlecqX9VhuE03GyQRq9fg82Cc0Sa6MIRJqV3i57AKwCLp2x1kHqn5uET-AoTK1Mjt_1UoQdClcFIlgggkWNYJMcTLu8jWU5_mq8hpBNG9ZoNcnOBPOiXrjDIk4SDFu8mdr6vdc2mfdjqzGjZYc0qsEIdsmcea-6w8Fe-Ce_AOQ-4Ws
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fb9MwELamgQQ88GsgCgP8wBPCm-PYsf04NqZVjGiiRewtcuwzqwYtatNJ-yP4n_G5aTUJhMRbItmJoy--O_s-f0fIG6t5rMrCsSLF4kw6yZn1IBkHL7V3bQVtyMUmdF2b83N7tkXebc7CAEAmn8EeXuZcfpj5JW6V7ZvkbjWe1rulpBR8dVprkzNApa2sjioks1ytc5gFt_vj4XiENC6zJ0wK4VED8oYXymVV_rDF2cEcP_i_oT0k9_tAkh6skH9EtmD6mNy7IS-4Q34dzSe4X0BHLkJ3TT9PFpf0bI6pGYSDZroAPZwtOjZCHjtaPvp10l3QGukv3_rKEgyLeuZSEhDowbKbofYl8p_p--QCA01PGv5okSLp013tspJH1n-m6wEcuc49IV-OP4wPT1hffoH5FAN0zCnhyyhS_KjAVL5KMxkUVMmdiVgZ41XU1rSgtbOxaIVsVeQtty4ttkFHJ8qnZHs6m8IzQlUZQlGAlqpNljkBECxwE30IEWS6HhC-hqPxvTY5ftf3Jq9RuG0QwQYRbHoEB-TtpsvPlTDHvxrvIGSbhj1aA7K7xrzpp-6iEWWJgUsyVM__3us1uXMy_nTanA7rjy_I3fQeu-K37JLtbr6El-S2v-omi_mr_H_-BsAq5LI
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=Driving+Safety+Risk+Prediction+Using+Cost-Sensitive+With+Nonnegativity-Constrained+Autoencoders+Based+on+Imbalanced+Naturalistic+Driving+Data&rft.jtitle=IEEE+transactions+on+intelligent+transportation+systems&rft.au=Chen%2C+Jie&rft.au=Wu%2C+ZhongCheng&rft.au=Zhang%2C+Jun&rft.date=2019-12-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1524-9050&rft.eissn=1558-0016&rft.volume=20&rft.issue=12&rft.spage=4450&rft_id=info:doi/10.1109%2FTITS.2018.2886280&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1524-9050&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1524-9050&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1524-9050&client=summon