Crash injury severity analysis using a two-layer Stacking framework

•A two-layer Stacking model is proposed to predict crash injury severity.•The fist layer combines three classification methods: RF, AdaBoost and GBDT.•The second layer predicts crash injury severity based on a Logistic Regression model.•Several traditional models are compared in binary and multi cla...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Accident analysis and prevention Ročník 122; s. 226 - 238
Hlavní autoři: Tang, Jinjun, Liang, Jian, Han, Chunyang, Li, Zhibin, Huang, Helai
Médium: Journal Article
Jazyk:angličtina
Vydáno: England Elsevier Ltd 01.01.2019
Témata:
ISSN:0001-4575, 1879-2057, 1879-2057
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract •A two-layer Stacking model is proposed to predict crash injury severity.•The fist layer combines three classification methods: RF, AdaBoost and GBDT.•The second layer predicts crash injury severity based on a Logistic Regression model.•Several traditional models are compared in binary and multi classification experiments.•Prediction results show the Stacking model can achieve better performance. Crash injury severity analysis is useful for traffic management agency to further understand severity of crashes. A two-layer Stacking framework is proposed in this study to predict the crash injury severity: The fist layer integrates advantages of three base classification methods: RF (Random Forests), AdaBoost (Adaptive Boosting), and GBDT (Gradient Boosting Decision Tree); the second layer completes classification of crash injury severity based on a Logistic Regression model. A total of 5538 crashes were recorded at 326 freeway diverge areas. In the model calibration, several parameters including the number of trees in three base classification methods, learning rate, and regularization coefficient are optimized via a systematic grid search approach. In the model validation, the performance of the Stacking model is compared with several traditional models including the Support Vector Machine (SVM), Multi-Layer Perceptron (MLP) and Random Forests (RF) in the multi classification experiments. The prediction results show that Stacking model achieves superior performance evaluated by two indicators: accuracy and recall. Furthermore, all the factors used in severity prediction are classified into different categories according to their influence on the results, and sensitivity analysis of several significant factors is finally implemented to explore the impact of their value variation on the prediction accuracy.
AbstractList Crash injury severity analysis is useful for traffic management agency to further understand severity of crashes. A two-layer Stacking framework is proposed in this study to predict the crash injury severity: The fist layer integrates advantages of three base classification methods: RF (Random Forests), AdaBoost (Adaptive Boosting), and GBDT (Gradient Boosting Decision Tree); the second layer completes classification of crash injury severity based on a Logistic Regression model. A total of 5538 crashes were recorded at 326 freeway diverge areas. In the model calibration, several parameters including the number of trees in three base classification methods, learning rate, and regularization coefficient are optimized via a systematic grid search approach. In the model validation, the performance of the Stacking model is compared with several traditional models including the Support Vector Machine (SVM), Multi-Layer Perceptron (MLP) and Random Forests (RF) in the multi classification experiments. The prediction results show that Stacking model achieves superior performance evaluated by two indicators: accuracy and recall. Furthermore, all the factors used in severity prediction are classified into different categories according to their influence on the results, and sensitivity analysis of several significant factors is finally implemented to explore the impact of their value variation on the prediction accuracy.Crash injury severity analysis is useful for traffic management agency to further understand severity of crashes. A two-layer Stacking framework is proposed in this study to predict the crash injury severity: The fist layer integrates advantages of three base classification methods: RF (Random Forests), AdaBoost (Adaptive Boosting), and GBDT (Gradient Boosting Decision Tree); the second layer completes classification of crash injury severity based on a Logistic Regression model. A total of 5538 crashes were recorded at 326 freeway diverge areas. In the model calibration, several parameters including the number of trees in three base classification methods, learning rate, and regularization coefficient are optimized via a systematic grid search approach. In the model validation, the performance of the Stacking model is compared with several traditional models including the Support Vector Machine (SVM), Multi-Layer Perceptron (MLP) and Random Forests (RF) in the multi classification experiments. The prediction results show that Stacking model achieves superior performance evaluated by two indicators: accuracy and recall. Furthermore, all the factors used in severity prediction are classified into different categories according to their influence on the results, and sensitivity analysis of several significant factors is finally implemented to explore the impact of their value variation on the prediction accuracy.
•A two-layer Stacking model is proposed to predict crash injury severity.•The fist layer combines three classification methods: RF, AdaBoost and GBDT.•The second layer predicts crash injury severity based on a Logistic Regression model.•Several traditional models are compared in binary and multi classification experiments.•Prediction results show the Stacking model can achieve better performance. Crash injury severity analysis is useful for traffic management agency to further understand severity of crashes. A two-layer Stacking framework is proposed in this study to predict the crash injury severity: The fist layer integrates advantages of three base classification methods: RF (Random Forests), AdaBoost (Adaptive Boosting), and GBDT (Gradient Boosting Decision Tree); the second layer completes classification of crash injury severity based on a Logistic Regression model. A total of 5538 crashes were recorded at 326 freeway diverge areas. In the model calibration, several parameters including the number of trees in three base classification methods, learning rate, and regularization coefficient are optimized via a systematic grid search approach. In the model validation, the performance of the Stacking model is compared with several traditional models including the Support Vector Machine (SVM), Multi-Layer Perceptron (MLP) and Random Forests (RF) in the multi classification experiments. The prediction results show that Stacking model achieves superior performance evaluated by two indicators: accuracy and recall. Furthermore, all the factors used in severity prediction are classified into different categories according to their influence on the results, and sensitivity analysis of several significant factors is finally implemented to explore the impact of their value variation on the prediction accuracy.
Crash injury severity analysis is useful for traffic management agency to further understand severity of crashes. A two-layer Stacking framework is proposed in this study to predict the crash injury severity: The fist layer integrates advantages of three base classification methods: RF (Random Forests), AdaBoost (Adaptive Boosting), and GBDT (Gradient Boosting Decision Tree); the second layer completes classification of crash injury severity based on a Logistic Regression model. A total of 5538 crashes were recorded at 326 freeway diverge areas. In the model calibration, several parameters including the number of trees in three base classification methods, learning rate, and regularization coefficient are optimized via a systematic grid search approach. In the model validation, the performance of the Stacking model is compared with several traditional models including the Support Vector Machine (SVM), Multi-Layer Perceptron (MLP) and Random Forests (RF) in the multi classification experiments. The prediction results show that Stacking model achieves superior performance evaluated by two indicators: accuracy and recall. Furthermore, all the factors used in severity prediction are classified into different categories according to their influence on the results, and sensitivity analysis of several significant factors is finally implemented to explore the impact of their value variation on the prediction accuracy.
Author Tang, Jinjun
Han, Chunyang
Huang, Helai
Li, Zhibin
Liang, Jian
Author_xml – sequence: 1
  givenname: Jinjun
  surname: Tang
  fullname: Tang, Jinjun
  organization: School of Traffic and Transportation Engineering, Smart Transport Key Laboratory of Hunan Province, Central South University, Changsha, 410075, China
– sequence: 2
  givenname: Jian
  surname: Liang
  fullname: Liang, Jian
  organization: School of Traffic and Transportation Engineering, Smart Transport Key Laboratory of Hunan Province, Central South University, Changsha, 410075, China
– sequence: 3
  givenname: Chunyang
  surname: Han
  fullname: Han, Chunyang
  organization: School of Traffic and Transportation Engineering, Smart Transport Key Laboratory of Hunan Province, Central South University, Changsha, 410075, China
– sequence: 4
  givenname: Zhibin
  surname: Li
  fullname: Li, Zhibin
  email: lizhibin@seu.edu.cn
  organization: School of Transportation, Southeast University, Nanjing, 210096, China
– sequence: 5
  givenname: Helai
  orcidid: 0000-0003-2334-4124
  surname: Huang
  fullname: Huang, Helai
  organization: School of Traffic and Transportation Engineering, Smart Transport Key Laboratory of Hunan Province, Central South University, Changsha, 410075, China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/30390518$$D View this record in MEDLINE/PubMed
BookMark eNp9kD1PwzAQhi0EgvLxA1hQRpYUO4ljR0yo4kuqxADM1tm5gNs0KbZTlH-PqwIDA9PpXj3PSfcek_2u75CQc0anjLLyajEFWE8zymTcpzHZIxMmRZVmlIt9MqGUsrTggh-RY-8XcRVS8ENylNO8opzJCZnNHPj3xHaLwY2Jxw06G8YEOmhHb30yeNu9JZCEzz5tYUSXPAcwy23YOFjhZ--Wp-Sggdbj2fc8Ia93ty-zh3T-dP84u5mnpihESHMsBaOZNohQcxSy0qB1JUHSom4MLXKUUJWmNAXXuQCeSWh0ybKiNFhqnZ-Qy93dtes_BvRBraw32LbQYT94lbGs4jmtqIjoxTc66BXWau3sCtyofh6PANsBxvXeO2x-EUbVtly1ULFctS13G8UkOuKPY2yAYPsuOLDtv-b1zsRYz8aiU95Y7AzW1qEJqu7tP_YXs4uT6Q
CitedBy_id crossref_primary_10_3390_su12198158
crossref_primary_10_3390_su17157105
crossref_primary_10_1177_1687814019851391
crossref_primary_10_1680_jmuen_25_00005
crossref_primary_10_1016_j_iatssr_2025_06_001
crossref_primary_10_1093_tse_tdad014
crossref_primary_10_1016_j_aap_2023_107378
crossref_primary_10_1016_j_physa_2019_123759
crossref_primary_10_1080_13588265_2020_1858665
crossref_primary_10_1016_j_aap_2022_106681
crossref_primary_10_1371_journal_pone_0229211
crossref_primary_10_1016_j_aap_2024_107662
crossref_primary_10_1007_s11356_023_30123_5
crossref_primary_10_1080_17457300_2021_1928233
crossref_primary_10_3390_ijerph18168327
crossref_primary_10_1080_13873954_2025_2509514
crossref_primary_10_1016_j_amar_2020_100123
crossref_primary_10_3390_app142310790
crossref_primary_10_3390_su11205768
crossref_primary_10_1371_journal_pone_0281901
crossref_primary_10_1080_17457300_2025_2485040
crossref_primary_10_3390_app13010233
crossref_primary_10_1016_j_ssci_2023_106381
crossref_primary_10_1080_19439962_2020_1754983
crossref_primary_10_1016_j_eswa_2021_115658
crossref_primary_10_1109_ACCESS_2020_3040165
crossref_primary_10_3390_app15189884
crossref_primary_10_1109_ACCESS_2024_3443524
crossref_primary_10_1080_17457300_2020_1849312
crossref_primary_10_1016_j_jsr_2021_02_012
crossref_primary_10_1038_s41598_022_15693_7
crossref_primary_10_1186_s12911_020_01358_w
crossref_primary_10_1016_j_trip_2025_101457
crossref_primary_10_1155_2020_9628957
crossref_primary_10_1016_j_aap_2023_107382
crossref_primary_10_1016_j_compeleceng_2024_109101
crossref_primary_10_1080_23249935_2020_1733132
crossref_primary_10_1016_j_aap_2024_107712
crossref_primary_10_1016_j_physa_2019_02_038
crossref_primary_10_1080_19439962_2022_2026543
crossref_primary_10_1080_19427867_2025_2500817
crossref_primary_10_1007_s11053_025_10498_7
crossref_primary_10_1038_s41598_025_88896_3
crossref_primary_10_3390_app13116773
crossref_primary_10_1155_stc_6695396
crossref_primary_10_1371_journal_pone_0219344
crossref_primary_10_3390_info15030145
crossref_primary_10_1016_j_heliyon_2024_e35595
crossref_primary_10_1016_j_jsr_2025_06_028
crossref_primary_10_1109_TMECH_2020_3043471
crossref_primary_10_1016_j_aap_2021_106149
crossref_primary_10_1016_j_aap_2022_106622
crossref_primary_10_3390_app14010279
crossref_primary_10_1016_j_apgeog_2024_103440
crossref_primary_10_1016_j_aap_2021_106261
crossref_primary_10_3390_ijerph16162942
crossref_primary_10_1080_15389588_2025_2459297
crossref_primary_10_1177_03611981251337460
crossref_primary_10_1016_j_engappai_2024_109386
crossref_primary_10_1016_j_aap_2023_107271
crossref_primary_10_1016_j_eswa_2021_116389
crossref_primary_10_1016_j_jsr_2021_12_007
crossref_primary_10_1111_mice_70023
crossref_primary_10_3233_JIFS_234155
crossref_primary_10_1155_2021_8453465
crossref_primary_10_1080_19439962_2022_2098442
crossref_primary_10_1016_j_aap_2024_107603
crossref_primary_10_3390_infrastructures5070061
crossref_primary_10_1038_s41598_025_16477_5
crossref_primary_10_1016_j_petrol_2020_107314
crossref_primary_10_3390_ijerph17062066
crossref_primary_10_1080_15389588_2023_2297168
crossref_primary_10_1016_j_physa_2019_03_062
crossref_primary_10_1155_2023_7833555
crossref_primary_10_1371_journal_pone_0263030
crossref_primary_10_1155_2020_6401082
crossref_primary_10_1155_2021_5543698
crossref_primary_10_1177_03611981241302340
crossref_primary_10_1016_j_aap_2022_106617
crossref_primary_10_1016_j_ergon_2021_103192
crossref_primary_10_3390_su12020620
crossref_primary_10_1109_ACCESS_2019_2941280
crossref_primary_10_1007_s12652_022_04441_4
crossref_primary_10_1186_s12879_024_09138_x
crossref_primary_10_1016_j_aap_2021_106034
crossref_primary_10_1016_j_energy_2025_134927
crossref_primary_10_1016_j_ssci_2025_106843
crossref_primary_10_1016_j_jsr_2025_06_011
crossref_primary_10_1016_j_aap_2024_107693
crossref_primary_10_1016_j_autcon_2022_104686
crossref_primary_10_1007_s40890_024_00212_2
crossref_primary_10_1016_j_aap_2025_108201
crossref_primary_10_1016_j_heliyon_2024_e30117
crossref_primary_10_1155_2020_4079617
crossref_primary_10_3390_su16229642
crossref_primary_10_1016_j_oceaneng_2025_122570
crossref_primary_10_3390_rs15194713
crossref_primary_10_3390_ijerph17020572
crossref_primary_10_1016_j_eswa_2023_121782
crossref_primary_10_3390_brainsci13091326
crossref_primary_10_1109_ACCESS_2019_2916691
crossref_primary_10_1371_journal_pone_0221128
crossref_primary_10_1016_j_jnlssr_2025_100250
crossref_primary_10_1016_j_aap_2020_105833
crossref_primary_10_1016_j_physa_2019_122348
crossref_primary_10_1080_23311916_2020_1762525
crossref_primary_10_1177_03611981221134629
crossref_primary_10_21597_jist_1285239
crossref_primary_10_1016_j_engappai_2024_107933
crossref_primary_10_1080_19439962_2025_2471300
crossref_primary_10_1016_j_aap_2024_107740
crossref_primary_10_1080_01441647_2021_1954108
crossref_primary_10_3390_su132212773
crossref_primary_10_1016_j_compbiomed_2022_106393
crossref_primary_10_1016_j_tra_2023_103696
crossref_primary_10_1177_14759217241270792
crossref_primary_10_3233_JAD_215654
crossref_primary_10_1002_hfm_20975
crossref_primary_10_1177_03611981221084682
crossref_primary_10_3390_app12020828
crossref_primary_10_1016_j_aap_2020_105666
crossref_primary_10_1016_j_treng_2025_100352
crossref_primary_10_3390_su11102730
crossref_primary_10_1016_j_eswa_2020_113855
crossref_primary_10_3390_ijerph16132308
crossref_primary_10_1016_j_jsr_2022_12_005
crossref_primary_10_1016_j_physa_2019_121789
crossref_primary_10_3390_ijerph182312725
crossref_primary_10_3390_ijerph17207466
crossref_primary_10_3390_s21248401
crossref_primary_10_1371_journal_pone_0214966
crossref_primary_10_1109_TWC_2021_3123948
crossref_primary_10_1016_j_jenvman_2023_118790
crossref_primary_10_1080_17457300_2023_2202660
crossref_primary_10_1155_2020_5261580
crossref_primary_10_1080_17457300_2024_2351972
crossref_primary_10_1016_j_physa_2019_03_036
crossref_primary_10_1080_23249935_2025_2511816
crossref_primary_10_1155_2020_6623739
crossref_primary_10_1080_19439962_2024_2364661
crossref_primary_10_1080_23249935_2024_2437477
crossref_primary_10_1080_17457300_2023_2267040
crossref_primary_10_3389_frai_2023_1232640
crossref_primary_10_3390_su13116102
crossref_primary_10_3390_e22111191
crossref_primary_10_1016_j_geoen_2024_212896
crossref_primary_10_1155_2021_3771640
crossref_primary_10_1080_10803548_2025_2485731
crossref_primary_10_1049_iet_its_2019_0361
crossref_primary_10_1049_itr2_70040
crossref_primary_10_1016_j_jneumeth_2020_109019
crossref_primary_10_1016_j_physa_2022_127277
crossref_primary_10_1016_j_aap_2021_106501
crossref_primary_10_1016_j_aap_2023_107119
crossref_primary_10_1108_ECAM_10_2024_1344
crossref_primary_10_1371_journal_pone_0217241
crossref_primary_10_1016_j_aap_2023_107235
crossref_primary_10_1016_j_physa_2019_123858
crossref_primary_10_14254_jsdtl_2022_7_2_1
crossref_primary_10_1177_0036850419886471
crossref_primary_10_1080_17457300_2024_2440939
crossref_primary_10_1016_j_jtrangeo_2023_103551
crossref_primary_10_1016_j_amar_2021_100182
crossref_primary_10_1155_2021_4216215
crossref_primary_10_1016_j_cscm_2022_e01653
crossref_primary_10_1016_j_amar_2021_100189
crossref_primary_10_1080_17457300_2025_2537683
crossref_primary_10_1155_2021_6652288
crossref_primary_10_3390_safety10010022
crossref_primary_10_1016_j_physa_2019_122774
crossref_primary_10_1080_17457300_2023_2180804
crossref_primary_10_3390_futuretransp2040052
crossref_primary_10_1016_j_aap_2020_105920
crossref_primary_10_1109_TITS_2025_3526217
crossref_primary_10_1016_j_trf_2023_07_014
crossref_primary_10_1177_1687814019841838
crossref_primary_10_1016_j_ssci_2024_106468
crossref_primary_10_1007_s10812_023_01491_0
crossref_primary_10_1155_2022_1716827
crossref_primary_10_1016_j_tre_2024_103678
crossref_primary_10_1016_j_aap_2025_108007
crossref_primary_10_1080_17457300_2025_2487635
crossref_primary_10_3390_electronics14173377
crossref_primary_10_3390_asi7020025
crossref_primary_10_1080_15389588_2019_1675154
crossref_primary_10_1155_2022_7239464
crossref_primary_10_1016_j_amar_2020_100153
Cites_doi 10.1016/j.aap.2014.09.006
10.1016/j.aap.2011.08.016
10.1016/j.amar.2014.09.001
10.1016/j.jsr.2009.05.003
10.1016/j.ins.2009.08.025
10.5539/mas.v7n10p11
10.1016/S0893-6080(05)80023-1
10.1177/0361198106195000104
10.1016/j.aap.2005.01.004
10.1016/j.aap.2011.05.016
10.1016/j.aap.2013.03.025
10.1016/j.aap.2012.09.006
10.1016/j.aap.2008.09.009
10.1016/j.aap.2016.02.011
10.1016/j.aap.2015.05.018
10.1016/j.aap.2010.12.026
10.1023/A:1010933404324
10.1016/j.eswa.2017.09.025
10.1214/aos/1013203451
10.3141/2024-11
10.1016/j.eswa.2009.02.039
10.1016/j.aap.2005.06.024
10.1016/j.aap.2017.08.008
10.1016/j.eswa.2013.05.027
10.1016/j.aap.2007.11.002
10.1016/j.amar.2015.11.002
10.3141/1746-02
10.1016/j.aap.2008.12.014
10.1016/j.ssci.2008.06.007
ContentType Journal Article
Copyright 2018 Elsevier Ltd
Copyright © 2018 Elsevier Ltd. All rights reserved.
Copyright_xml – notice: 2018 Elsevier Ltd
– notice: Copyright © 2018 Elsevier Ltd. All rights reserved.
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1016/j.aap.2018.10.016
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic

MEDLINE
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Social Welfare & Social Work
Public Health
EISSN 1879-2057
EndPage 238
ExternalDocumentID 30390518
10_1016_j_aap_2018_10_016
S0001457518308546
Genre Journal Article
GroupedDBID ---
--K
--M
-~X
..I
.~1
0R~
1B1
1RT
1~.
23M
4.4
457
4G.
53G
5GY
5RE
5VS
7-5
71M
8P~
9JM
9JN
9JO
AABNK
AACTN
AAEDT
AAEDW
AAFJI
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
ABBQC
ABDMP
ABFNM
ABIVO
ABJNI
ABLVK
ABMAC
ABMMH
ABMZM
ABNUV
ABXDB
ABYKQ
ACDAQ
ACGFS
ACHQT
ACNCT
ACNNM
ACRLP
ADBBV
ADEWK
ADEZE
ADMUD
ADTZH
AEBSH
AECPX
AEKER
AFKWA
AFTJW
AFXIZ
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHPOS
AHRSL
AI.
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
AJRQY
AKURH
AKYCK
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
ANZVX
AOMHK
ASPBG
AVARZ
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
BNPGV
CS3
EBS
EFJIC
EFLBG
EJD
ENUVR
EO8
EO9
EP2
EP3
F3I
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
HEH
HMK
HMO
HMY
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
LCYCR
M29
M3W
M3Y
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PRBVW
Q38
R2-
RIG
ROL
RPZ
SAE
SCC
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SSB
SSG
SSH
SSO
SSS
SST
SSZ
T5K
VH1
WUQ
XPP
ZCG
ZGI
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACIEU
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
CGR
CUY
CVF
ECM
EIF
NPM
7X8
ID FETCH-LOGICAL-c447t-3e67102bceead5e789babb98a804dfc043e8a96c6c45b37a528afb61246ce6bb3
ISICitedReferencesCount 213
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000453338600024&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0001-4575
1879-2057
IngestDate Wed Oct 01 13:50:59 EDT 2025
Wed Feb 19 02:33:26 EST 2025
Tue Nov 18 22:23:38 EST 2025
Sat Nov 29 04:10:20 EST 2025
Fri Feb 23 02:33:11 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Severity classification
Crash injury severity
Random Forests
Adaptive Boosting
Stacking model
Gradient Boosting Decision Tree
Language English
License Copyright © 2018 Elsevier Ltd. All rights reserved.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c447t-3e67102bceead5e789babb98a804dfc043e8a96c6c45b37a528afb61246ce6bb3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0003-2334-4124
PMID 30390518
PQID 2129530907
PQPubID 23479
PageCount 13
ParticipantIDs proquest_miscellaneous_2129530907
pubmed_primary_30390518
crossref_primary_10_1016_j_aap_2018_10_016
crossref_citationtrail_10_1016_j_aap_2018_10_016
elsevier_sciencedirect_doi_10_1016_j_aap_2018_10_016
PublicationCentury 2000
PublicationDate January 2019
2019-01-00
2019-Jan
20190101
PublicationDateYYYYMMDD 2019-01-01
PublicationDate_xml – month: 01
  year: 2019
  text: January 2019
PublicationDecade 2010
PublicationPlace England
PublicationPlace_xml – name: England
PublicationTitle Accident analysis and prevention
PublicationTitleAlternate Accid Anal Prev
PublicationYear 2019
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Abdelwahab, Abdel-Aty (bib0005) 2001; 1746
Chen, Wang, Henk (bib0050) 2009; 36
Hauer (bib0090) 1997
Xu, Wong, Choi (bib0165) 2014; 3–4
Hauer, Ng, Lovell (bib0095) 1988; 1185
Li, Liu, Wang, Xu (bib0105) 2012; 45
Ye, Pendyala, Washington, Konduri, Oh (bib0170) 2009; 47
Abellán, López, Oña (bib0010) 2013; 40
Menahem, Rokach, Elovici (bib0130) 2009; 179
Bifet, Frank, Holmes, Pfahringer (bib0035) 2010; 13
American Association of state Highway and Transportation Officials (bib0015) 2010
Mauro, Luca, Acqua (bib0125) 2013; 7
Dong, Huang, Zheng (bib0070) 2015; 82
Ma, Kockelman (bib0110) 2006; 1950
Ye, Pendyala, Shankar, Konduri (bib0175) 2013; 57
Barua, El-Basyouny, Islam (bib0030) 2016; 9
Wolpert (bib0160) 1992; 5
Zeng, Huang (bib0180) 2014; 73
Anderson (bib0020) 2009; 41
Harb, Yan, Radwan, Su (bib0085) 2009; 41
Das, Abdel-Aty, Pande (bib0060) 2009; 40
Pei, Wong, Sze (bib0140) 2011; 43
Breiman (bib0045) 2001; 45
Schaffer (bib0145) 1994; vol. 89
Delen, Sharda, Bessonov (bib0065) 2006; 38
Freund, Schapire (bib0075) 1996
Chen, Zhang, Qian, Tarefder, Tian (bib0055) 2016; 90
Mahalel (bib0120) 1986; 1068
Oña, López, Abellán (bib0135) 2013; 50
Wang, Quddus, Ison (bib0155) 2011; 43
Tang, Liu, Zhang, Ke, Zou (bib0150) 2018; 91
Barua, El-Basyouny, Islam (bib0025) 2014; 3
Bijleveld (bib0040) 2005; 37
Friedman (bib0080) 2001; 29
Iranitalab, Khattak (bib0100) 2017; 108
Ma, Kockelman, Damien (bib0115) 2008; 40
Zhang, Xie (bib0185) 2007
Breiman (10.1016/j.aap.2018.10.016_bib0045) 2001; 45
Abdelwahab (10.1016/j.aap.2018.10.016_bib0005) 2001; 1746
Hauer (10.1016/j.aap.2018.10.016_bib0090) 1997
Mahalel (10.1016/j.aap.2018.10.016_bib0120) 1986; 1068
Mauro (10.1016/j.aap.2018.10.016_bib0125) 2013; 7
Ye (10.1016/j.aap.2018.10.016_bib0175) 2013; 57
Anderson (10.1016/j.aap.2018.10.016_bib0020) 2009; 41
Schaffer (10.1016/j.aap.2018.10.016_bib0145) 1994; vol. 89
American Association of state Highway and Transportation Officials (10.1016/j.aap.2018.10.016_bib0015) 2010
Wang (10.1016/j.aap.2018.10.016_bib0155) 2011; 43
Menahem (10.1016/j.aap.2018.10.016_bib0130) 2009; 179
Freund (10.1016/j.aap.2018.10.016_bib0075) 1996
Pei (10.1016/j.aap.2018.10.016_bib0140) 2011; 43
Chen (10.1016/j.aap.2018.10.016_bib0055) 2016; 90
Harb (10.1016/j.aap.2018.10.016_bib0085) 2009; 41
Iranitalab (10.1016/j.aap.2018.10.016_bib0100) 2017; 108
Li (10.1016/j.aap.2018.10.016_bib0105) 2012; 45
Das (10.1016/j.aap.2018.10.016_bib0060) 2009; 40
Dong (10.1016/j.aap.2018.10.016_bib0070) 2015; 82
Friedman (10.1016/j.aap.2018.10.016_bib0080) 2001; 29
Delen (10.1016/j.aap.2018.10.016_bib0065) 2006; 38
Wolpert (10.1016/j.aap.2018.10.016_bib0160) 1992; 5
Ye (10.1016/j.aap.2018.10.016_bib0170) 2009; 47
Barua (10.1016/j.aap.2018.10.016_bib0025) 2014; 3
Barua (10.1016/j.aap.2018.10.016_bib0030) 2016; 9
Tang (10.1016/j.aap.2018.10.016_bib0150) 2018; 91
Chen (10.1016/j.aap.2018.10.016_bib0050) 2009; 36
Ma (10.1016/j.aap.2018.10.016_bib0110) 2006; 1950
Hauer (10.1016/j.aap.2018.10.016_bib0095) 1988; 1185
Zeng (10.1016/j.aap.2018.10.016_bib0180) 2014; 73
Zhang (10.1016/j.aap.2018.10.016_bib0185) 2007
Abellán (10.1016/j.aap.2018.10.016_bib0010) 2013; 40
Ma (10.1016/j.aap.2018.10.016_bib0115) 2008; 40
Bifet (10.1016/j.aap.2018.10.016_bib0035) 2010; 13
Bijleveld (10.1016/j.aap.2018.10.016_bib0040) 2005; 37
Oña (10.1016/j.aap.2018.10.016_bib0135) 2013; 50
Xu (10.1016/j.aap.2018.10.016_bib0165) 2014; 3–4
References_xml – year: 2010
  ident: bib0015
  article-title: Highway Safety Manual
– volume: 41
  start-page: 359
  year: 2009
  end-page: 364
  ident: bib0020
  article-title: Kernel density estimation and k-means clustering to profile road accident hotspots
  publication-title: Accid. Anal. Prev.
– year: 1997
  ident: bib0090
  article-title: Observational Before–After Studies in Road Safety
– volume: 91
  start-page: 452
  year: 2018
  end-page: 463
  ident: bib0150
  article-title: Lane-changes prediction based on adaptive fuzzy neural network
  publication-title: Expert Syst. Appl.
– volume: 43
  start-page: 1979
  year: 2011
  end-page: 1990
  ident: bib0155
  article-title: Predicting accident frequency at their severity levels and its application in site ranking using a two-stage mixed multivariate model
  publication-title: Accid. Anal. Prev.
– volume: 3–4
  start-page: 1
  year: 2014
  end-page: 10
  ident: bib0165
  article-title: A two-stage bivariate logistic-Tobit model for the safety analysis of signalized intersections
  publication-title: Anal. Methods Accid. Res.
– volume: 73
  start-page: 351
  year: 2014
  end-page: 358
  ident: bib0180
  article-title: A stable and optimized neural network model for crash injury severity prediction
  publication-title: Accid. Anal. Prev.
– volume: 40
  start-page: 317
  year: 2009
  end-page: 327
  ident: bib0060
  article-title: Using conditional inference forests to identify the factors affecting crash severity on arterial corridors
  publication-title: J. Saf. Res.
– volume: 108
  start-page: 27
  year: 2017
  end-page: 36
  ident: bib0100
  article-title: Comparison of four statistical and machine learning methods for crash severity prediction
  publication-title: Accid. Anal. Prev.
– start-page: 148
  year: 1996
  end-page: 156
  ident: bib0075
  article-title: Experiments with a new boosting algorithm
  publication-title: Proceedings of the 13th International Conference on Machine Learning
– volume: 38
  start-page: 434
  year: 2006
  end-page: 444
  ident: bib0065
  article-title: Identifying significant predictors of injury severity in traffic accidents using a series of artificial neural networks
  publication-title: Accid. Anal. Prev.
– start-page: 92
  year: 2007
  end-page: 99
  ident: bib0185
  article-title: Forecasting of short-term freeway volume with v-support vector machines
  publication-title: Transp. Res. Record
– volume: 179
  start-page: 4097
  year: 2009
  end-page: 4122
  ident: bib0130
  article-title: Troika – an improved stacking schema for classification tasks
  publication-title: Inf. Sci. (Ny)
– volume: 57
  start-page: 140
  year: 2013
  end-page: 149
  ident: bib0175
  article-title: A simultaneous equations model of crash frequency by severity level for freeway sections
  publication-title: Accid. Anal. Prev.
– volume: 1746
  start-page: 6
  year: 2001
  end-page: 13
  ident: bib0005
  article-title: Development of artificial neural network models to predict driver injury severity in traffic accidents at signalized intersections
  publication-title: Transp. Res. Rec.
– volume: 9
  start-page: 1
  year: 2016
  end-page: 15
  ident: bib0030
  article-title: Multivariate random parameters collision count data models with spatial heterogeneity
  publication-title: Anal. Methods Accid. Res.
– volume: 45
  start-page: 5
  year: 2001
  end-page: 32
  ident: bib0045
  article-title: Random forests
  publication-title: Mach. Learn.
– volume: 43
  start-page: 1160
  year: 2011
  end-page: 1166
  ident: bib0140
  article-title: A joint-probability approach to crash prediction models
  publication-title: Accid. Anal. Prev.
– volume: 1950
  start-page: 24
  year: 2006
  end-page: 34
  ident: bib0110
  article-title: Bayesian multivariate Poisson regression for models of injury count, by severity
  publication-title: Transp. Res. Rec.
– volume: 29
  start-page: 1189
  year: 2001
  end-page: 1232
  ident: bib0080
  article-title: Greedy function approximation: a gradient boosting machine
  publication-title: Ann. Stat.
– volume: 36
  start-page: 10976
  year: 2009
  end-page: 10986
  ident: bib0050
  article-title: Construct support vector machine ensemble to detect traffic incident
  publication-title: Expert Syst. Appl.
– volume: 13
  start-page: 225
  year: 2010
  end-page: 240
  ident: bib0035
  article-title: Accurate ensembles for data streams: combining restricted hoeffding trees using stacking
  publication-title: J. Mach. Learn. Res.
– volume: 47
  start-page: 443
  year: 2009
  end-page: 452
  ident: bib0170
  article-title: A simultaneous equations model of crash frequency by collision type for rural intersections
  publication-title: Saf. Sci.
– volume: vol. 89
  year: 1994
  ident: bib0145
  article-title: Cross-validation, stacking and Bi-level stacking: meta-methods for classification learning
  publication-title: Selecting Models from Data. Lecture Notes in Statistics
– volume: 40
  start-page: 6047
  year: 2013
  end-page: 6054
  ident: bib0010
  article-title: Analysis of traffic accident severity using decision rules via decision trees
  publication-title: Expert Syst. Appl.
– volume: 45
  start-page: 478
  year: 2012
  end-page: 486
  ident: bib0105
  article-title: Using support vector machine models for crash injury severity analysis
  publication-title: Accid. Anal. Prev.
– volume: 82
  start-page: 192
  year: 2015
  end-page: 198
  ident: bib0070
  article-title: Support vector machine in crash prediction at the level of traffic analysis zones: assessing the spatial proximity effects
  publication-title: Accid. Anal. Prev.
– volume: 50
  start-page: 1151
  year: 2013
  end-page: 1160
  ident: bib0135
  article-title: Extracting decision rules from police accident reports through decision trees
  publication-title: Accid. Anal. Prev.
– volume: 5
  start-page: 241
  year: 1992
  end-page: 259
  ident: bib0160
  article-title: Stacked generalization
  publication-title: Neural Netw.
– volume: 41
  start-page: 98
  year: 2009
  end-page: 107
  ident: bib0085
  article-title: Exploring precrash maneuvers using classification trees and random forests
  publication-title: Accid. Anal. Prev.
– volume: 40
  start-page: 964
  year: 2008
  end-page: 975
  ident: bib0115
  article-title: A multivariate Poisson-lognormal regression model for prediction of crash counts by severity, using Bayesian methods
  publication-title: Accid. Anal. Prev.
– volume: 1068
  start-page: 85
  year: 1986
  end-page: 89
  ident: bib0120
  article-title: A note on accident risk
  publication-title: Transp. Res. Rec.
– volume: 37
  start-page: 591
  year: 2005
  end-page: 600
  ident: bib0040
  article-title: The covariance between the number of accidents and the number of victims in multivariate analysis of accident related outcomes
  publication-title: Accid. Anal. Prev.
– volume: 90
  start-page: 128
  year: 2016
  end-page: 139
  ident: bib0055
  article-title: Investigating driver injury severity patterns in rollover crashes using support vector machine models
  publication-title: Accid. Anal. Prev.
– volume: 3
  start-page: 28
  year: 2014
  end-page: 43
  ident: bib0025
  article-title: A full Bayesian multivariate count data model of collision severity with spatial correlation
  publication-title: Anal. Methods Accid. Res.
– volume: 1185
  start-page: 48
  year: 1988
  end-page: 61
  ident: bib0095
  article-title: Estimation of safety at signalized intersections
  publication-title: Transp. Res. Rec.
– volume: 7
  start-page: 11
  year: 2013
  end-page: 19
  ident: bib0125
  article-title: Using a K-means clustering algorithm to examine patterns of vehicle crashes in before-after analysis
  publication-title: Mod. Appl. Sci.
– volume: 73
  start-page: 351
  year: 2014
  ident: 10.1016/j.aap.2018.10.016_bib0180
  article-title: A stable and optimized neural network model for crash injury severity prediction
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2014.09.006
– volume: 45
  start-page: 478
  issue: 2
  year: 2012
  ident: 10.1016/j.aap.2018.10.016_bib0105
  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
– volume: 3
  start-page: 28
  year: 2014
  ident: 10.1016/j.aap.2018.10.016_bib0025
  article-title: A full Bayesian multivariate count data model of collision severity with spatial correlation
  publication-title: Anal. Methods Accid. Res.
  doi: 10.1016/j.amar.2014.09.001
– volume: 40
  start-page: 317
  issue: 4
  year: 2009
  ident: 10.1016/j.aap.2018.10.016_bib0060
  article-title: Using conditional inference forests to identify the factors affecting crash severity on arterial corridors
  publication-title: J. Saf. Res.
  doi: 10.1016/j.jsr.2009.05.003
– volume: 1068
  start-page: 85
  year: 1986
  ident: 10.1016/j.aap.2018.10.016_bib0120
  article-title: A note on accident risk
  publication-title: Transp. Res. Rec.
– volume: 179
  start-page: 4097
  issue: 24
  year: 2009
  ident: 10.1016/j.aap.2018.10.016_bib0130
  article-title: Troika – an improved stacking schema for classification tasks
  publication-title: Inf. Sci. (Ny)
  doi: 10.1016/j.ins.2009.08.025
– volume: 7
  start-page: 11
  issue: 10
  year: 2013
  ident: 10.1016/j.aap.2018.10.016_bib0125
  article-title: Using a K-means clustering algorithm to examine patterns of vehicle crashes in before-after analysis
  publication-title: Mod. Appl. Sci.
  doi: 10.5539/mas.v7n10p11
– year: 2010
  ident: 10.1016/j.aap.2018.10.016_bib0015
– volume: vol. 89
  year: 1994
  ident: 10.1016/j.aap.2018.10.016_bib0145
  article-title: Cross-validation, stacking and Bi-level stacking: meta-methods for classification learning
– volume: 5
  start-page: 241
  issue: 2
  year: 1992
  ident: 10.1016/j.aap.2018.10.016_bib0160
  article-title: Stacked generalization
  publication-title: Neural Netw.
  doi: 10.1016/S0893-6080(05)80023-1
– volume: 1950
  start-page: 24
  year: 2006
  ident: 10.1016/j.aap.2018.10.016_bib0110
  article-title: Bayesian multivariate Poisson regression for models of injury count, by severity
  publication-title: Transp. Res. Rec.
  doi: 10.1177/0361198106195000104
– volume: 37
  start-page: 591
  issue: 4
  year: 2005
  ident: 10.1016/j.aap.2018.10.016_bib0040
  article-title: The covariance between the number of accidents and the number of victims in multivariate analysis of accident related outcomes
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2005.01.004
– volume: 43
  start-page: 1979
  issue: 6
  year: 2011
  ident: 10.1016/j.aap.2018.10.016_bib0155
  article-title: Predicting accident frequency at their severity levels and its application in site ranking using a two-stage mixed multivariate model
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2011.05.016
– volume: 57
  start-page: 140
  year: 2013
  ident: 10.1016/j.aap.2018.10.016_bib0175
  article-title: A simultaneous equations model of crash frequency by severity level for freeway sections
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2013.03.025
– volume: 50
  start-page: 1151
  issue: 2
  year: 2013
  ident: 10.1016/j.aap.2018.10.016_bib0135
  article-title: Extracting decision rules from police accident reports through decision trees
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2012.09.006
– volume: 41
  start-page: 98
  issue: 1
  year: 2009
  ident: 10.1016/j.aap.2018.10.016_bib0085
  article-title: Exploring precrash maneuvers using classification trees and random forests
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2008.09.009
– volume: 90
  start-page: 128
  year: 2016
  ident: 10.1016/j.aap.2018.10.016_bib0055
  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
– volume: 82
  start-page: 192
  year: 2015
  ident: 10.1016/j.aap.2018.10.016_bib0070
  article-title: Support vector machine in crash prediction at the level of traffic analysis zones: assessing the spatial proximity effects
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2015.05.018
– volume: 43
  start-page: 1160
  issue: 3
  year: 2011
  ident: 10.1016/j.aap.2018.10.016_bib0140
  article-title: A joint-probability approach to crash prediction models
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2010.12.026
– year: 1997
  ident: 10.1016/j.aap.2018.10.016_bib0090
– volume: 13
  start-page: 225
  issue: 13
  year: 2010
  ident: 10.1016/j.aap.2018.10.016_bib0035
  article-title: Accurate ensembles for data streams: combining restricted hoeffding trees using stacking
  publication-title: J. Mach. Learn. Res.
– volume: 45
  start-page: 5
  issue: 1
  year: 2001
  ident: 10.1016/j.aap.2018.10.016_bib0045
  article-title: Random forests
  publication-title: Mach. Learn.
  doi: 10.1023/A:1010933404324
– volume: 91
  start-page: 452
  year: 2018
  ident: 10.1016/j.aap.2018.10.016_bib0150
  article-title: Lane-changes prediction based on adaptive fuzzy neural network
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2017.09.025
– volume: 29
  start-page: 1189
  issue: 5
  year: 2001
  ident: 10.1016/j.aap.2018.10.016_bib0080
  article-title: Greedy function approximation: a gradient boosting machine
  publication-title: Ann. Stat.
  doi: 10.1214/aos/1013203451
– start-page: 92
  year: 2007
  ident: 10.1016/j.aap.2018.10.016_bib0185
  article-title: Forecasting of short-term freeway volume with v-support vector machines
  publication-title: Transp. Res. Record
  doi: 10.3141/2024-11
– volume: 36
  start-page: 10976
  issue: 8
  year: 2009
  ident: 10.1016/j.aap.2018.10.016_bib0050
  article-title: Construct support vector machine ensemble to detect traffic incident
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2009.02.039
– volume: 38
  start-page: 434
  issue: 3
  year: 2006
  ident: 10.1016/j.aap.2018.10.016_bib0065
  article-title: Identifying significant predictors of injury severity in traffic accidents using a series of artificial neural networks
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2005.06.024
– volume: 108
  start-page: 27
  year: 2017
  ident: 10.1016/j.aap.2018.10.016_bib0100
  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: 1185
  start-page: 48
  year: 1988
  ident: 10.1016/j.aap.2018.10.016_bib0095
  article-title: Estimation of safety at signalized intersections
  publication-title: Transp. Res. Rec.
– volume: 40
  start-page: 6047
  issue: 15
  year: 2013
  ident: 10.1016/j.aap.2018.10.016_bib0010
  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: 3–4
  start-page: 1
  year: 2014
  ident: 10.1016/j.aap.2018.10.016_bib0165
  article-title: A two-stage bivariate logistic-Tobit model for the safety analysis of signalized intersections
  publication-title: Anal. Methods Accid. Res.
– volume: 40
  start-page: 964
  issue: 3
  year: 2008
  ident: 10.1016/j.aap.2018.10.016_bib0115
  article-title: A multivariate Poisson-lognormal regression model for prediction of crash counts by severity, using Bayesian methods
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2007.11.002
– volume: 9
  start-page: 1
  year: 2016
  ident: 10.1016/j.aap.2018.10.016_bib0030
  article-title: Multivariate random parameters collision count data models with spatial heterogeneity
  publication-title: Anal. Methods Accid. Res.
  doi: 10.1016/j.amar.2015.11.002
– volume: 1746
  start-page: 6
  year: 2001
  ident: 10.1016/j.aap.2018.10.016_bib0005
  article-title: Development of artificial neural network models to predict driver injury severity in traffic accidents at signalized intersections
  publication-title: Transp. Res. Rec.
  doi: 10.3141/1746-02
– volume: 41
  start-page: 359
  issue: 3
  year: 2009
  ident: 10.1016/j.aap.2018.10.016_bib0020
  article-title: Kernel density estimation and k-means clustering to profile road accident hotspots
  publication-title: Accid. Anal. Prev.
  doi: 10.1016/j.aap.2008.12.014
– start-page: 148
  year: 1996
  ident: 10.1016/j.aap.2018.10.016_bib0075
  article-title: Experiments with a new boosting algorithm
  publication-title: Proceedings of the 13th International Conference on Machine Learning
– volume: 47
  start-page: 443
  issue: 3
  year: 2009
  ident: 10.1016/j.aap.2018.10.016_bib0170
  article-title: A simultaneous equations model of crash frequency by collision type for rural intersections
  publication-title: Saf. Sci.
  doi: 10.1016/j.ssci.2008.06.007
SSID ssj0007875
Score 2.6261854
Snippet •A two-layer Stacking model is proposed to predict crash injury severity.•The fist layer combines three classification methods: RF, AdaBoost and GBDT.•The...
Crash injury severity analysis is useful for traffic management agency to further understand severity of crashes. A two-layer Stacking framework is proposed in...
SourceID proquest
pubmed
crossref
elsevier
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 226
SubjectTerms Accidents, Traffic - classification
Accidents, Traffic - statistics & numerical data
Adaptive Boosting
Built Environment - statistics & numerical data
Crash injury severity
Decision Trees
Gradient Boosting Decision Tree
Humans
Injury Severity Score
Logistic Models
Neural Networks (Computer)
Random Forests
Severity classification
Stacking model
Support Vector Machine
Wounds and Injuries - classification
Wounds and Injuries - epidemiology
Title Crash injury severity analysis using a two-layer Stacking framework
URI https://dx.doi.org/10.1016/j.aap.2018.10.016
https://www.ncbi.nlm.nih.gov/pubmed/30390518
https://www.proquest.com/docview/2129530907
Volume 122
WOSCitedRecordID wos000453338600024&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1879-2057
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0007875
  issn: 0001-4575
  databaseCode: AIEXJ
  dateStart: 19950201
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLbYxgMSQjBuhTEZCfFAlSptnNh-rKqhgdCExIC-RceuI1qqdGpTGP-e41syhjYBEi9RayV25PPl-PPxuRDyghlA0VZpIgwvEgaCJQrlnsxkpU2RVkY6b_dP7_jJiZhO5ftg0924cgK8rsX5uTz7r6LGNhS2DZ39C3G3nWID_kah4xXFjtc_EvxkDRtrxljgbPVx3TO2PF0fYvKRrTMOQL_5vkqWgITb8k391TlURketi4x1rLWtO9p0PYTUAsFRstv6B99eO3Ln5zNvmzsYHkM46d_WPyCsnO5ed1LyZa5CNvBgjLDxT78YI9oomc4lyWtd3KfmvkLKwHhFKxAQo9Qnp241sQ9Rjrp0VFxYlkc-CcxvGt8bHxYDAJt9dCgG1ldveCm7tluvP7j9oDtnypBosmKH7I14LlEX7o3fHE3ftis4KjFf-SK8dzwNd36Blwa6is9ctV9xvOX0LrkTNhx07IFyj9ww9T657a211Aeh7ZMDH6VNP5tlBWtDX9LYgGi4TyYOU9RjikZM0YgI6jBFgbaYohFTtMXUA_Lx9dHp5DgJ1TcSzRhvkswUln0qZFEwyw0XUoFSUoBI2azSKcuMAFnoQrNcZRzykYBKIWFmBX7lSmUPyW69qs1jQlmVIdHOM5urkA25UcpgRzpV9k-WD3skjXNY6pCa3lZIWZbRB3FR4rSXdtptE7b0yKv2kTOfl-W6m1kUTBmIpSeMJaLouseeRyGWqHTtSRrUZrXdlMj3ZJ6lMuU98shLt30L5IQ255148m-DPiW3ug_rgOw26615Rm7qb818sz4kO3wqDgNefwJps7Ap
linkProvider Elsevier
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=Crash+injury+severity+analysis+using+a+two-layer+Stacking+framework&rft.jtitle=Accident+analysis+and+prevention&rft.au=Tang%2C+Jinjun&rft.au=Liang%2C+Jian&rft.au=Han%2C+Chunyang&rft.au=Li%2C+Zhibin&rft.date=2019-01-01&rft.pub=Elsevier+Ltd&rft.issn=0001-4575&rft.eissn=1879-2057&rft.volume=122&rft.spage=226&rft.epage=238&rft_id=info:doi/10.1016%2Fj.aap.2018.10.016&rft.externalDocID=S0001457518308546
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0001-4575&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0001-4575&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0001-4575&client=summon