Handling Imbalanced Data in Road Crash Severity Prediction by Machine Learning Algorithms

Crash severity is undoubtedly a fundamental aspect of a crash event. Although machine learning algorithms for predicting crash severity have recently gained interest by the academic community, there is a significant trend towards neglecting the fact that crash datasets are acutely imbalanced. Overlo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Infrastructures (Basel) Jg. 5; H. 7; S. 61
Hauptverfasser: Fiorentini, Nicholas, Losa, Massimo
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Basel MDPI AG 20.07.2020
Schlagworte:
ISSN:2412-3811, 2412-3811
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Crash severity is undoubtedly a fundamental aspect of a crash event. Although machine learning algorithms for predicting crash severity have recently gained interest by the academic community, there is a significant trend towards neglecting the fact that crash datasets are acutely imbalanced. Overlooking this fact generally leads to weak classifiers for predicting the minority class (crashes with higher severity). In this paper, in order to handle imbalanced accident datasets and provide a better prediction for the minority class, the random undersampling the majority class (RUMC) technique is used. By employing an imbalanced and a RUMC-based balanced training set, we propose the calibration, validation, and evaluation of four different crash severity predictive models, including random tree, k-nearest neighbor, logistic regression, and random forest. Accuracy, true positive rate (recall), false positive rate, true negative rate, precision, F1-score, and the confusion matrix have been calculated to assess the performance. Outcomes show that RUMC-based models provide an enhancement in the reliability of the classifiers for detecting fatal crashes and those causing injury. Indeed, in imbalanced models, the true positive rate for predicting fatal crashes and those causing injury spans from 0% (logistic regression) to 18.3% (k-nearest neighbor), while for the RUMC-based models, it spans from 52.5% (RUMC-based logistic regression) to 57.2% (RUMC-based k-nearest neighbor). Organizations and decision-makers could make use of RUMC and machine learning algorithms in predicting the severity of a crash occurrence, managing the present, and planning the future of their works.
AbstractList Crash severity is undoubtedly a fundamental aspect of a crash event. Although machine learning algorithms for predicting crash severity have recently gained interest by the academic community, there is a significant trend towards neglecting the fact that crash datasets are acutely imbalanced. Overlooking this fact generally leads to weak classifiers for predicting the minority class (crashes with higher severity). In this paper, in order to handle imbalanced accident datasets and provide a better prediction for the minority class, the random undersampling the majority class (RUMC) technique is used. By employing an imbalanced and a RUMC-based balanced training set, we propose the calibration, validation, and evaluation of four different crash severity predictive models, including random tree, k-nearest neighbor, logistic regression, and random forest. Accuracy, true positive rate (recall), false positive rate, true negative rate, precision, F1-score, and the confusion matrix have been calculated to assess the performance. Outcomes show that RUMC-based models provide an enhancement in the reliability of the classifiers for detecting fatal crashes and those causing injury. Indeed, in imbalanced models, the true positive rate for predicting fatal crashes and those causing injury spans from 0% (logistic regression) to 18.3% (k-nearest neighbor), while for the RUMC-based models, it spans from 52.5% (RUMC-based logistic regression) to 57.2% (RUMC-based k-nearest neighbor). Organizations and decision-makers could make use of RUMC and machine learning algorithms in predicting the severity of a crash occurrence, managing the present, and planning the future of their works.
Author Fiorentini, Nicholas
Losa, Massimo
Author_xml – sequence: 1
  givenname: Nicholas
  orcidid: 0000-0002-8769-8610
  surname: Fiorentini
  fullname: Fiorentini, Nicholas
– sequence: 2
  givenname: Massimo
  surname: Losa
  fullname: Losa, Massimo
BookMark eNqFkVuLFDEQhYOs4LruX5CAz6O5dnfAl2W87MCI4uXBp1CdVGYy9CRrklmYf2-PI7KI4FMVxTlfFaeekouUExLynLOXUhr2KqZQoLZycO1QsGrWM9bxR-RSKC4WcuD84kH_hFzXumOMCTb0w8AvyfdbSH6KaUNX-xEmSA49fQMNaEz0cwZPlzN_S7_gPZbYjvRTQR9diznR8Ug_gNvGhHSNUNKJcjNt8qzb7usz8jjAVPH6d70i3969_bq8Xaw_vl8tb9YLJ03fFqDNKJ3pNPPBBzkgY04DRxSux87AqIORTCpujGA6KONRKa-56KXWyLi8Iqsz12fY2bsS91CONkO0vwa5bCyUFt2EdpQeROc8jMIoNWcQNAySz-vHTnYqzKwXZ9ZdyT8OWJvd5UNJ8_lWKNH1fNCczarurHIl11ow_NnKmT19xf77K7Px9V9GFxucsmwF4vQ_-0-DYZtD
CitedBy_id crossref_primary_10_1007_s12530_023_09563_4
crossref_primary_10_1016_j_aap_2022_106769
crossref_primary_10_3390_computers13020049
crossref_primary_10_1109_ACCESS_2024_3366990
crossref_primary_10_1371_journal_pone_0269022
crossref_primary_10_3390_ijerph18041966
crossref_primary_10_1016_j_aap_2021_106240
crossref_primary_10_3390_sym12101620
crossref_primary_10_1016_j_amar_2025_100405
crossref_primary_10_1016_j_engappai_2024_109086
crossref_primary_10_1016_j_eswa_2023_121118
crossref_primary_10_1016_j_jth_2023_101671
crossref_primary_10_1080_17457300_2021_1928233
crossref_primary_10_1142_S0218126625300090
crossref_primary_10_1680_jtran_24_00071
crossref_primary_10_1038_s41598_022_25361_5
crossref_primary_10_1007_s41062_024_01626_y
crossref_primary_10_3103_S1060992X23040082
crossref_primary_10_1016_j_compbiomed_2022_106393
crossref_primary_10_1371_journal_pone_0262941
crossref_primary_10_3233_IDA_216398
crossref_primary_10_1080_19439962_2024_2311408
crossref_primary_10_1177_03611981241239962
crossref_primary_10_1177_03611981221090519
crossref_primary_10_3390_info11120557
crossref_primary_10_1371_journal_pone_0281901
crossref_primary_10_1016_j_aap_2021_106496
crossref_primary_10_3390_su12155972
crossref_primary_10_1038_s41598_025_08935_x
crossref_primary_10_3390_computers14050186
crossref_primary_10_1371_journal_pone_0255828
crossref_primary_10_3390_ijerph17207466
crossref_primary_10_1007_s00521_022_07769_2
crossref_primary_10_1080_12265934_2024_2346166
crossref_primary_10_3390_app122211354
crossref_primary_10_1080_17457300_2023_2202660
crossref_primary_10_1177_03611981221111367
crossref_primary_10_1016_j_aap_2021_106094
crossref_primary_10_1016_j_aap_2021_106090
crossref_primary_10_1080_03081060_2023_2177651
crossref_primary_10_1007_s40999_025_01108_x
crossref_primary_10_1080_03081060_2023_2216202
crossref_primary_10_1371_journal_pone_0314133
crossref_primary_10_1109_ACCESS_2025_3571837
crossref_primary_10_1016_j_procs_2024_05_192
crossref_primary_10_3390_math13020310
crossref_primary_10_1016_j_trpro_2023_11_051
crossref_primary_10_3390_su15139878
crossref_primary_10_3390_app12020856
crossref_primary_10_1007_s12145_024_01649_0
crossref_primary_10_3390_info15030145
crossref_primary_10_1007_s00138_022_01284_z
crossref_primary_10_1016_j_aap_2021_106149
crossref_primary_10_1016_j_eswa_2024_124602
crossref_primary_10_1177_03611981211033278
crossref_primary_10_1007_s13177_024_00440_1
crossref_primary_10_1016_j_heliyon_2023_e21187
crossref_primary_10_1080_13588265_2022_2028471
crossref_primary_10_3390_ijerph17207598
crossref_primary_10_14254_jsdtl_2022_7_2_1
crossref_primary_10_1016_j_aap_2023_107271
crossref_primary_10_1016_j_jth_2025_102022
crossref_primary_10_1016_j_jsr_2021_12_007
crossref_primary_10_3390_app15010253
crossref_primary_10_1177_03611981251351888
crossref_primary_10_1080_19439962_2025_2554089
crossref_primary_10_3103_S1060992X24700103
crossref_primary_10_1109_TITS_2022_3207798
crossref_primary_10_3390_s21103377
crossref_primary_10_1177_03611981231171151
crossref_primary_10_4271_09_13_01_0006
crossref_primary_10_1080_13588265_2022_2074643
crossref_primary_10_3390_rs14143275
crossref_primary_10_3390_futuretransp2040052
crossref_primary_10_1016_j_chaos_2023_113245
crossref_primary_10_3390_ijerph192013693
crossref_primary_10_1080_08839514_2025_2452675
crossref_primary_10_1186_s12889_022_14678_5
crossref_primary_10_1155_2022_1438190
crossref_primary_10_3390_app15094793
crossref_primary_10_3390_computers11050080
crossref_primary_10_1139_cjce_2023_0503
crossref_primary_10_1080_17457300_2022_2075397
crossref_primary_10_1186_s12544_024_00686_6
crossref_primary_10_3390_app12136368
crossref_primary_10_3390_su15032352
crossref_primary_10_3390_electronics14173377
crossref_primary_10_3390_su151310668
crossref_primary_10_1007_s00521_024_10939_z
crossref_primary_10_1016_j_amar_2025_100372
Cites_doi 10.1002/for.2425
10.1080/15389588.2017.1363891
10.1109/TIT.1967.1053964
10.1109/ACCESS.2018.2874979
10.1016/j.aap.2006.04.009
10.1016/j.jth.2017.01.009
10.1037/h0072400
10.1016/j.aap.2010.10.002
10.1016/j.physa.2018.10.060
10.1007/978-3-642-25832-9_24
10.1016/j.aap.2019.01.007
10.1016/j.aap.2019.105274
10.1080/13588265.2019.1616885
10.1111/mice.12485
10.1016/j.trc.2017.11.014
10.1109/TITS.2020.2994126
10.3390/app7060476
10.1016/j.aap.2016.02.011
10.1007/978-1-4899-7993-3_565-2
10.1007/s00521-019-04695-8
10.1109/LT.2018.8368509
10.1109/JEEIT.2019.8717393
10.1177/0361198119841571
10.1016/j.aap.2011.08.016
10.3141/1746-02
10.1145/1656274.1656278
10.1016/j.aap.2018.10.016
10.1609/aaai.v30i1.10011
10.1016/j.aap.2008.04.010
10.1177/0361198119845899
10.1016/j.aap.2008.09.009
10.1016/j.ssci.2019.07.008
10.1016/j.aap.2017.08.008
10.1016/j.neucom.2013.05.059
10.1145/1007730.1007735
10.3233/IDA-2002-6504
10.1111/0885-9507.00064
10.1016/j.aap.2019.105371
10.1016/j.eswa.2013.05.027
10.1613/jair.953
10.2307/2280041
10.1109/ACCESS.2019.2903319
10.1016/j.aap.2016.08.004
10.1016/j.aap.2019.02.008
10.1016/j.aap.2005.03.019
10.1007/978-3-030-34069-8_17
ContentType Journal Article
Copyright 2020. This work is licensed under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: 2020. This work is licensed under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID AAYXX
CITATION
8FE
8FG
ABUWG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
HCIFZ
P5Z
P62
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
DOA
DOI 10.3390/infrastructures5070061
DatabaseName CrossRef
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials Local Electronic Collection Information
ProQuest Central
Technology collection
ProQuest One Community College
ProQuest Central
SciTech Premium Collection
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Publicly Available Content Database
Advanced Technologies & Aerospace Collection
Technology Collection
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest One Academic Eastern Edition
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Technology Collection
ProQuest SciTech Collection
ProQuest Central China
ProQuest Central
Advanced Technologies & Aerospace Database
ProQuest One Applied & Life Sciences
ProQuest One Academic UKI Edition
ProQuest Central Korea
ProQuest Central (New)
ProQuest One Academic
ProQuest One Academic (New)
DatabaseTitleList
Publicly Available Content Database
CrossRef
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Open Access Full Text
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: PIMPY
  name: ProQuest Publicly Available Content
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2412-3811
ExternalDocumentID oai_doaj_org_article_b3da26cdab2944208f5a8313c9b6364f
10_3390_infrastructures5070061
GroupedDBID 8FE
8FG
AADQD
AAFWJ
AAYXX
ADBBV
AFFHD
AFKRA
AFPKN
AFZYC
ALMA_UNASSIGNED_HOLDINGS
ARAPS
BCNDV
BENPR
BGLVJ
CCPQU
CITATION
GROUPED_DOAJ
HCIFZ
MODMG
M~E
OK1
P62
PHGZM
PHGZT
PIMPY
PQGLB
PROAC
ABUWG
AZQEC
DWQXO
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
ID FETCH-LOGICAL-c397t-a59b3c9650dfdf38e00c5a1ee2c7e69ab5f93034199205f49de44d5127355e013
IEDL.DBID DOA
ISICitedReferencesCount 102
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000623637800009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2412-3811
IngestDate Fri Oct 03 12:51:12 EDT 2025
Sun Nov 09 08:27:15 EST 2025
Tue Nov 18 22:52:07 EST 2025
Sat Nov 29 07:15:38 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 7
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c397t-a59b3c9650dfdf38e00c5a1ee2c7e69ab5f93034199205f49de44d5127355e013
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-8769-8610
OpenAccessLink https://doaj.org/article/b3da26cdab2944208f5a8313c9b6364f
PQID 2426718510
PQPubID 2055405
ParticipantIDs doaj_primary_oai_doaj_org_article_b3da26cdab2944208f5a8313c9b6364f
proquest_journals_2426718510
crossref_primary_10_3390_infrastructures5070061
crossref_citationtrail_10_3390_infrastructures5070061
PublicationCentury 2000
PublicationDate 2020-07-20
PublicationDateYYYYMMDD 2020-07-20
PublicationDate_xml – month: 07
  year: 2020
  text: 2020-07-20
  day: 20
PublicationDecade 2020
PublicationPlace Basel
PublicationPlace_xml – name: Basel
PublicationTitle Infrastructures (Basel)
PublicationYear 2020
Publisher MDPI AG
Publisher_xml – name: MDPI AG
References Li (ref_11) 2008; 40
(ref_23) 2013; 40
Theofilatos (ref_18) 2019; 2673
ref_58
ref_57
Mosteller (ref_55) 1968; Volume 2
ref_56
ref_10
Tang (ref_8) 2019; 132
ref_53
ref_52
ref_51
ref_19
Chawla (ref_42) 2002; 16
Singh (ref_6) 2018; 171
Tang (ref_32) 2019; 122
Cover (ref_50) 1967; 13
ref_59
Iranitalab (ref_28) 2017; 108
Xiao (ref_16) 2019; 517
Wang (ref_14) 2019; 124
Delen (ref_15) 2017; 4
Hall (ref_46) 2009; 11
ref_25
Harb (ref_13) 2009; 41
Cateni (ref_2) 2014; 135
ref_21
ref_20
Haleem (ref_12) 2011; 43
ref_29
Li (ref_31) 2012; 45
Zhang (ref_9) 2020; 35
Larson (ref_54) 1931; 22
ref_35
ref_34
Mokhtarimousavi (ref_22) 2019; 2673
ref_30
Zhang (ref_5) 1997; 12
ref_39
ref_38
ref_37
ref_47
Chen (ref_26) 2016; 90
ref_45
ref_44
ref_43
ref_41
ref_40
ref_1
Chang (ref_24) 2006; 38
Wu (ref_36) 2018; 19
ref_3
ref_49
ref_48
Laaha (ref_17) 2019; 127
ref_4
Singh (ref_7) 2016; 96
Alkheder (ref_27) 2017; 36
Krishnaveni (ref_33) 2011; 23
References_xml – volume: 36
  start-page: 100
  year: 2017
  ident: ref_27
  article-title: Severity Prediction of Traffic Accident Using an Artificial Neural Network
  publication-title: J. Forecast.
  doi: 10.1002/for.2425
– volume: 19
  start-page: 179
  year: 2018
  ident: ref_36
  article-title: An evaluation scheme for assessing the effectiveness of intersection movement assist (IMA) on improving traffic safety
  publication-title: Traffic Inj. Prev.
  doi: 10.1080/15389588.2017.1363891
– volume: 13
  start-page: 21
  year: 1967
  ident: ref_50
  article-title: Nearest Neighbor Pattern Classification
  publication-title: IEEE Trans. Inf. Theory
  doi: 10.1109/TIT.1967.1053964
– ident: ref_30
  doi: 10.1109/ACCESS.2018.2874979
– volume: 38
  start-page: 1019
  year: 2006
  ident: ref_24
  article-title: Analysis of traffic injury severity: An application of non-parametric classification tree techniques
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2006.04.009
– volume: 4
  start-page: 118
  year: 2017
  ident: ref_15
  article-title: Investigating injury severity risk factors in automobile crashes with predictive analytics and sensitivity analysis methods
  publication-title: J. Transp. Heal.
  doi: 10.1016/j.jth.2017.01.009
– volume: 22
  start-page: 45
  year: 1931
  ident: ref_54
  article-title: The shrinkage of the coefficient of multiple correlation
  publication-title: J. Educ. Psychol.
  doi: 10.1037/h0072400
– volume: 43
  start-page: 461
  year: 2011
  ident: ref_12
  article-title: Analyzing angle crashes at unsignalized intersections using machine learning techniques
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2010.10.002
– ident: ref_1
– volume: Volume 2
  start-page: 80
  year: 1968
  ident: ref_55
  article-title: Data Analysis, Including Statistics
  publication-title: The Handbook of Social Psychology
– volume: 517
  start-page: 29
  year: 2019
  ident: ref_16
  article-title: SVM and KNN ensemble learning for traffic incident detection
  publication-title: Phys. A Stat. Mech. its Appl.
  doi: 10.1016/j.physa.2018.10.060
– ident: ref_49
  doi: 10.1007/978-3-642-25832-9_24
– volume: 124
  start-page: 180
  year: 2019
  ident: ref_14
  article-title: Expressway crash risk prediction using back propagation neural network: A brief investigation on safety resilience
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2019.01.007
– volume: 132
  start-page: 105274
  year: 2019
  ident: ref_8
  article-title: Application of a model-based recursive partitioning algorithm to predict crash frequency
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2019.105274
– ident: ref_29
  doi: 10.1080/13588265.2019.1616885
– ident: ref_52
– ident: ref_48
– volume: 35
  start-page: 258
  year: 2020
  ident: ref_9
  article-title: An ensemble machine learning-based modeling framework for analysis of traffic crash frequency
  publication-title: Comput. Civ. Infrastruct. Eng.
  doi: 10.1111/mice.12485
– ident: ref_41
– volume: 23
  start-page: 40
  year: 2011
  ident: ref_33
  article-title: A perspective analysis of traffic accident using data mining techniques
  publication-title: Int. J. Comput. Appl.
– ident: ref_39
  doi: 10.1016/j.trc.2017.11.014
– ident: ref_35
  doi: 10.1109/TITS.2020.2994126
– ident: ref_45
– ident: ref_59
  doi: 10.3390/app7060476
– volume: 90
  start-page: 128
  year: 2016
  ident: ref_26
  article-title: Investigating driver injury severity patterns in rollover crashes using support vector machine models
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2016.02.011
– ident: ref_56
  doi: 10.1007/978-1-4899-7993-3_565-2
– ident: ref_10
  doi: 10.1007/s00521-019-04695-8
– ident: ref_20
  doi: 10.1109/LT.2018.8368509
– ident: ref_21
  doi: 10.1109/JEEIT.2019.8717393
– ident: ref_53
– volume: 2673
  start-page: 169
  year: 2019
  ident: ref_18
  article-title: Comparing Machine Learning and Deep Learning Methods for Real-Time Crash Prediction
  publication-title: Transp. Res. Rec.
  doi: 10.1177/0361198119841571
– volume: 45
  start-page: 478
  year: 2012
  ident: ref_31
  article-title: Using support vector machine models for crash injury severity analysis
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2011.08.016
– ident: ref_3
– ident: ref_25
  doi: 10.3141/1746-02
– volume: 11
  start-page: 10
  year: 2009
  ident: ref_46
  article-title: The WEKA data mining software
  publication-title: ACM SIGKDD Explor. Newsl.
  doi: 10.1145/1656274.1656278
– ident: ref_47
– volume: 122
  start-page: 226
  year: 2019
  ident: ref_32
  article-title: Crash injury severity analysis using a two-layer Stacking framework
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2018.10.016
– ident: ref_19
  doi: 10.1609/aaai.v30i1.10011
– volume: 40
  start-page: 1611
  year: 2008
  ident: ref_11
  article-title: Predicting motor vehicle crashes using Support Vector Machine models
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2008.04.010
– volume: 2673
  start-page: 680
  year: 2019
  ident: ref_22
  article-title: Improved Support Vector Machine Models for Work Zone Crash Injury Severity Prediction and Analysis
  publication-title: Res. Artic. Transp. Res. Rec.
  doi: 10.1177/0361198119845899
– volume: 41
  start-page: 98
  year: 2009
  ident: ref_13
  article-title: Exploring precrash maneuvers using classification trees and random forests
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2008.09.009
– ident: ref_34
  doi: 10.1016/j.ssci.2019.07.008
– volume: 108
  start-page: 27
  year: 2017
  ident: ref_28
  article-title: Comparison of four statistical and machine learning methods for crash severity prediction
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2017.08.008
– volume: 135
  start-page: 32
  year: 2014
  ident: ref_2
  article-title: A method for resampling imbalanced datasets in binary classification tasks for real-world problems
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2013.05.059
– ident: ref_44
  doi: 10.1145/1007730.1007735
– ident: ref_4
  doi: 10.3233/IDA-2002-6504
– volume: 12
  start-page: 287
  year: 1997
  ident: ref_5
  article-title: Instance-Based Learning for Highway Accident Frequency Prediction
  publication-title: Comput. Civ. Infrastruct. Eng.
  doi: 10.1111/0885-9507.00064
– ident: ref_40
  doi: 10.1016/j.aap.2019.105371
– volume: 40
  start-page: 6047
  year: 2013
  ident: ref_23
  article-title: Analysis of traffic accident severity using Decision Rules via Decision Trees
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2013.05.027
– volume: 16
  start-page: 321
  year: 2002
  ident: ref_42
  article-title: SMOTE: Synthetic minority over-sampling technique
  publication-title: J. Artif. Intell. Res.
  doi: 10.1613/jair.953
– ident: ref_51
  doi: 10.2307/2280041
– ident: ref_58
  doi: 10.1109/ACCESS.2019.2903319
– volume: 96
  start-page: 108
  year: 2016
  ident: ref_7
  article-title: M5 model tree based predictive modeling of road accidents on non-urban sections of highways in India
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2016.08.004
– volume: 127
  start-page: 134
  year: 2019
  ident: ref_17
  article-title: A comparison of statistical learning methods for deriving determining factors of accident occurrence from an imbalanced high resolution dataset
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2019.02.008
– ident: ref_37
  doi: 10.1016/j.aap.2005.03.019
– ident: ref_43
– volume: 171
  start-page: 253
  year: 2018
  ident: ref_6
  article-title: Support vector machine model for prediction of accidents on non-urban sections of highways
  publication-title: Proc. Inst. Civ. Eng. Transp.
– ident: ref_57
– ident: ref_38
  doi: 10.1007/978-3-030-34069-8_17
SSID ssj0002087881
Score 2.5047603
Snippet Crash severity is undoubtedly a fundamental aspect of a crash event. Although machine learning algorithms for predicting crash severity have recently gained...
SourceID doaj
proquest
crossref
SourceType Open Website
Aggregation Database
Enrichment Source
Index Database
StartPage 61
SubjectTerms Algorithms
Classification
Classifiers
crash severity
Crashes
Datasets
Decision making
Decision trees
k-nearest neighbor
Machine learning
machine learning classification algorithms
Neural networks
Performance evaluation
Prediction models
Property damage
random classification tree
random forest
random undersampling the majority class
Regression
Roads & highways
Studies
SummonAdditionalLinks – databaseName: Advanced Technologies & Aerospace Database
  dbid: P5Z
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT8MwDI5gcIADb8RgoBy4VuuatmtOiKfGgWniIQ0uVR7OQIJtbAOJf4_dZQMEggO3qm2kNHbsz477mbH9qOYApIqC0AkMUFCFApVCQnkrje4wzkLtimYT9WYza7dlyyfchr6scmITC0Nte4Zy5FVyJWhHUYUO-s8BdY2i01XfQmOWzRFLArVuaCV30xxLFGbElj7-MVhgdF9FqQ3UmJn1BcNZBEPkw7_4pIK6_5tlLtzN2fJ_J7rCljzQ5IdjzVhlM9BdY4uf6AfX2W2DKBbwkp8_aSpxNGD5iRop_tDllz1l-TF-xj2_AtR3ROu8NaBjHRIl12_8oqjDBO4pWjv88LGDExndPw032M3Z6fVxI_CtFgKDgGQUqERqYSTCNeusExmEoUlUDSAydUil0omT6OxiKlYNExdLC3FsESzUEa8AwshNVur2urDFuBORgDRF5B5CnEmXOSFSqdENSsBorFZmyWSxc-N5yKkdxmOO8QgJKf9ZSGVWnY7rj5k4_hxxRLKcvk1M2sWN3qCT-42Za2FVlBqrdCRjqjVwicpEDRdDpyKNXZlVJmLO_fYe5h8y3v798Q5biChAD-tojiqshFOEXTZvXkcPw8Feoa3vODX2Hw
  priority: 102
  providerName: ProQuest
Title Handling Imbalanced Data in Road Crash Severity Prediction by Machine Learning Algorithms
URI https://www.proquest.com/docview/2426718510
https://doaj.org/article/b3da26cdab2944208f5a8313c9b6364f
Volume 5
WOSCitedRecordID wos000623637800009&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: PRVAON
  databaseName: DOAJ Open Access Full Text
  customDbUrl:
  eissn: 2412-3811
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002087881
  issn: 2412-3811
  databaseCode: DOA
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2412-3811
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002087881
  issn: 2412-3811
  databaseCode: M~E
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 2412-3811
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002087881
  issn: 2412-3811
  databaseCode: P5Z
  dateStart: 20161201
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2412-3811
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002087881
  issn: 2412-3811
  databaseCode: BENPR
  dateStart: 20161201
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Publicly Available Content
  customDbUrl:
  eissn: 2412-3811
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002087881
  issn: 2412-3811
  databaseCode: PIMPY
  dateStart: 20161201
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT8MwDI4QcIAD4ikGA-XAtVrXpI8cYYDYYVM1QBpcqqRxBgg2tA0k_j12201DIO3CpaqiRG1t1_7cuJ8ZOwuaDkDpwPOdwAQFTcjTEYT03cpgOJSJb1zRbCLudpN-X6ULrb6oJqykBy4F1zDC6iDKrTaBkrQX7EKdiKbIlYlEJB15Xz9WC8nUS7G9lhBPevlLsMC8voH6GuuSk_UDE1mEQRS9f0SjgrT_l08uAs31NtuqECI_L-9sh63AcJdtLvAG7rGHG-JGwFPefjNUm5iD5Zd6qvnzkPdG2vIW3sUTvwU0VITZPB3TfgzpgJsv3ikKKIFX3KoDfv46GOG8p7fJPru_vrpr3XhVjwQvRyQx9XSoDMoCcZZ11okEfD8PdRMgyGOIlDahUxilJFWZ-qGTyoKUFqN8jEADEP8dsNXhaAiHjDsRCIgihNw-yES5xAkRKYPxSwGmUc0aC2eyyvKKQJz6WLxmmEiQjLO_ZVxjjfm695JCY-mKC1LFfDZRYBcDaBhZZRjZMsOosfpMkVn1Xk4yAiQYjdERHf3HNY7ZRkD5tx-jt6mzVXwQOGHr-ef0eTI-ZWsXV920d1qYJh7T8BHH0nYnffgGGAfsYw
linkProvider Directory of Open Access Journals
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1LbxMxEB6VFAl64FlEoIAPcFxlY3s36wNCpaVK1CaKoEjtabHX47RSm5QkBfVP8RuZ2UcAgeDUA7fV7nq1tj_PNzMezwC8lN2AaKyM4qDIQCEIRTbFhP1WjuhQZ7ELZbGJ3miUHR2Z8Rp8a87CcFhlIxNLQe1nBfvIO0wlJEcJQm8uPkdcNYp3V5sSGhUs9vHqK5lsi9eDXZrfV1LuvTvc6Ud1VYGoIO5dRjYxThWGNBMffFAZxnGR2C6iLHqYGuuSYEiua47LjJOgjUetPfFij6gZSWOi796Adc1gb8H6eDAcH6-8OjLOOD97dRRZKRN3CCdzW-WCvSQDmtQv1hp-YcGyWMBvXFAS3N7d_21o7sGdWpUW2xX278MaTh_Axk8JFh_CcZ-TSNClGJw7DuIs0Itdu7TidCrez6wXOzRsJ-ID0oome0SM57xxxWAV7koMy0hTFHUS2onYPptQx5cn54tN-HgtfXsErelsio9BBCUVpinZJjHqzIQsKJUaR0RvkOzNbhuSZnLzos60zgU_znKyuBgU-Z9B0YbOqt1FlWvkny3eMnZWb3Ou8PLGbD7Ja9GTO-WtTAtvnTSaoylCYjPVpcFwqUp1aMNWA6u8FmCL_Aemnvz98Qu41T8cHuQHg9H-U7gt2R0R90j4bkGLfhefwc3iy_J0MX9erxUBn64bg98BZhdTNg
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1LbxMxEB6VghAceCNCC_gAx1Uce18-oKo0RI0KUcRDKly2tnecVmqTkgSq_rX-Omb2EUAgOPXAbbW7Xq3tz_PNjMczAM9VLyAaqyIZNBkoBKHIppiw38oRHca5dKEqNpGNRvn-vhmvwUV7FobDKluZWAnqcubZR95lKiE5ShDqhiYsYtwfbJ1-ibiCFO-0tuU0aojs4fkZmW-Ll8M-zfULpQavP-zsRk2FgcgTDy8jmxinvSEtpQxl0DlK6RPbQ1Q-w9RYlwRDMj7mGE2ZhNiUGMclcWRGNI2kPdF3r8DVjGxMDiccJ59X_h0lc87UXh9K1trILiFmbuussF_JlCZFjPWHX_iwKhvwGytUVDe4_T8P0h241SjYYrteEXdhDaf34OZPaRfvw6ddTi1Bl2J44ji002Mp-nZpxdFUvJvZUuzQEB6K90jrnKwUMZ7zdhZDWLhz8baKP0XRpKadiO3jCXV8eXiyeAAfL6VvD2F9OpviIxBBK41pShaLxDg3IQ9ap8YR_RskK7TXgaSd6MI3-de5DMhxQXYYA6T4M0A60F21O60zkPyzxSvG0eptziBe3ZjNJ0UjkAqnS6tSX1qnTMwxFiGxue7RYLhUp3HowGYLsaIRa4viB74e__3xM7hOwCveDEd7G3BDsY9CZiSRN2Gd_hafwDX_bXm0mD-tFo2Ag8sG4HeYQVqZ
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=Handling+Imbalanced+Data+in+Road+Crash+Severity+Prediction+by+Machine+Learning+Algorithms&rft.jtitle=Infrastructures+%28Basel%29&rft.au=Fiorentini%2C+Nicholas&rft.au=Losa%2C+Massimo&rft.date=2020-07-20&rft.issn=2412-3811&rft.eissn=2412-3811&rft.volume=5&rft.issue=7&rft.spage=61&rft_id=info:doi/10.3390%2Finfrastructures5070061&rft.externalDBID=n%2Fa&rft.externalDocID=10_3390_infrastructures5070061
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2412-3811&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2412-3811&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2412-3811&client=summon