Building machine-learning models for reducing the severity of bicyclist road traffic injuries
•Identifying a feature list to enter into a variety of machine-learning classification algorithms that predict the class of bicyclist injury severity.•Identifying the “best” machine-learning algorithm on the basis of having the highest levels of accuracy, precision, recall, and F1 score.•Comparing t...
Uloženo v:
| Vydáno v: | Transportation engineering (Oxford) Ročník 12; s. 100179 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Ltd
01.06.2023
Elsevier |
| Témata: | |
| ISSN: | 2666-691X, 2666-691X |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | •Identifying a feature list to enter into a variety of machine-learning classification algorithms that predict the class of bicyclist injury severity.•Identifying the “best” machine-learning algorithm on the basis of having the highest levels of accuracy, precision, recall, and F1 score.•Comparing the different models that predict the class of bicyclist injury severity.
Predicting the severity of injuries caused by traffic accidents is an important undertaking because it may lead to establishing regulations increasing road-user safety. Bicyclists are a particularly susceptible category of road users, which is especially troubling considering the environmental, financial, and health benefits of this mode of transportation. As a result, this study aims to apply machine learning to identify risk variables that may result in serious biker injuries in the case of an accident.
Machine-learning models make no assumptions about the connections between variables. Hence, it has been argued that machine-learning approaches produce better outcomes than statistical procedures. This study selects the “best” machine-learning classification system from a vast pool of similar algorithms to predict the severity of bicycling injuries. Machine learning allows the system to learn from experience and improve without being too programmed.
We first use a variety of feature selection algorithms to identify a list of features related to the accident and the environment that have the greatest impact on the severity of bicyclist injuries. This feature list is then used as input data to various machine-learning algorithms that predict the class of bicyclist injury severity at one of three levels (fatal, serious, and slight). The “best” machine-learning algorithm is identified on the basis of having the highest levels of accuracy, precision, recall, and F1 score. The current models were developed and trained based on Israeli road-traffic accident data from 2009 to 2019, meaning that new models would need to be developed for other geographical locations. In addition, the models would need to be updated to take account of the changing relationships between motorists, bicyclists, and the environment. Nevertheless, the proposed methodology has universal applicability. |
|---|---|
| AbstractList | •Identifying a feature list to enter into a variety of machine-learning classification algorithms that predict the class of bicyclist injury severity.•Identifying the “best” machine-learning algorithm on the basis of having the highest levels of accuracy, precision, recall, and F1 score.•Comparing the different models that predict the class of bicyclist injury severity.
Predicting the severity of injuries caused by traffic accidents is an important undertaking because it may lead to establishing regulations increasing road-user safety. Bicyclists are a particularly susceptible category of road users, which is especially troubling considering the environmental, financial, and health benefits of this mode of transportation. As a result, this study aims to apply machine learning to identify risk variables that may result in serious biker injuries in the case of an accident.
Machine-learning models make no assumptions about the connections between variables. Hence, it has been argued that machine-learning approaches produce better outcomes than statistical procedures. This study selects the “best” machine-learning classification system from a vast pool of similar algorithms to predict the severity of bicycling injuries. Machine learning allows the system to learn from experience and improve without being too programmed.
We first use a variety of feature selection algorithms to identify a list of features related to the accident and the environment that have the greatest impact on the severity of bicyclist injuries. This feature list is then used as input data to various machine-learning algorithms that predict the class of bicyclist injury severity at one of three levels (fatal, serious, and slight). The “best” machine-learning algorithm is identified on the basis of having the highest levels of accuracy, precision, recall, and F1 score. The current models were developed and trained based on Israeli road-traffic accident data from 2009 to 2019, meaning that new models would need to be developed for other geographical locations. In addition, the models would need to be updated to take account of the changing relationships between motorists, bicyclists, and the environment. Nevertheless, the proposed methodology has universal applicability. Predicting the severity of injuries caused by traffic accidents is an important undertaking because it may lead to establishing regulations increasing road-user safety. Bicyclists are a particularly susceptible category of road users, which is especially troubling considering the environmental, financial, and health benefits of this mode of transportation. As a result, this study aims to apply machine learning to identify risk variables that may result in serious biker injuries in the case of an accident.Machine-learning models make no assumptions about the connections between variables. Hence, it has been argued that machine-learning approaches produce better outcomes than statistical procedures. This study selects the “best” machine-learning classification system from a vast pool of similar algorithms to predict the severity of bicycling injuries. Machine learning allows the system to learn from experience and improve without being too programmed.We first use a variety of feature selection algorithms to identify a list of features related to the accident and the environment that have the greatest impact on the severity of bicyclist injuries. This feature list is then used as input data to various machine-learning algorithms that predict the class of bicyclist injury severity at one of three levels (fatal, serious, and slight). The “best” machine-learning algorithm is identified on the basis of having the highest levels of accuracy, precision, recall, and F1 score. The current models were developed and trained based on Israeli road-traffic accident data from 2009 to 2019, meaning that new models would need to be developed for other geographical locations. In addition, the models would need to be updated to take account of the changing relationships between motorists, bicyclists, and the environment. Nevertheless, the proposed methodology has universal applicability. |
| ArticleNumber | 100179 |
| Author | Rosenbloom, Tova Elalouf, Amir Birfir, Slava |
| Author_xml | – sequence: 1 givenname: Slava surname: Birfir fullname: Birfir, Slava – sequence: 2 givenname: Amir surname: Elalouf fullname: Elalouf, Amir email: amir.elalouf@biu.ac.il – sequence: 3 givenname: Tova surname: Rosenbloom fullname: Rosenbloom, Tova |
| BookMark | eNp9kE2LFDEQhhtZwXXdX-Cl_0CP-ehOTw4edNF1YcGLghcJ1ZXKbDW9iSSZhfn39swoiIc9pXjheSv1vG4uYorUNG-l2Eghzbt5UzPF3UYJpddEyNG-aC6VMaYzVv64-Gd-1VyXMgsh1FaKrR4vm58f97x4jrv2EfCBI3ULQY6nIHlaShtSbjP5PR6z-kBtoSfKXA9tCu3EeMCFS21zAt_WDCEwthznfWYqb5qXAZZC13_eq-b750_fbr50919v724-3HeolbWd194GC3KEfvIAA0xKUu-3QSkzDdhLFGD1SKjBGOFHAk2IRGhVb71BfdXcnXt9gtn9yvwI-eASsDsFKe8c5Mq4kJuUGgIRaY2hn4Zxa6SRCAMKFOtWWLvsuQtzKiVTcMgVKqe4XseLk8IdtbvZnbS7o3Z31r6y-j_271-ep96fqVU3PTFlV5ApInnOhHW9gZ_lfwOuoaIF |
| CitedBy_id | crossref_primary_10_1007_s11116_024_10468_7 crossref_primary_10_1139_cjce_2023_0503 crossref_primary_10_1016_j_aap_2024_107677 crossref_primary_10_1080_17457300_2024_2335478 crossref_primary_10_1080_19427867_2024_2408920 crossref_primary_10_1680_jmuen_25_00005 crossref_primary_10_1016_j_treng_2025_100318 crossref_primary_10_3390_app14093570 crossref_primary_10_1061_JCCEE5_CPENG_5980 crossref_primary_10_1016_j_tbs_2024_100962 crossref_primary_10_1080_19439962_2025_2471300 |
| Cites_doi | 10.3141/2083-13 10.1016/j.autcon.2015.11.003 10.1016/j.ergon.2015.09.012 10.1016/j.aap.2016.02.011 10.1016/j.trf.2015.12.016 10.1016/j.tra.2010.02.001 10.1016/j.jsr.2019.04.008 10.1016/j.jsr.2021.09.005 10.1016/j.aap.2015.09.003 10.1016/j.patcog.2012.10.001 10.1016/j.aap.2020.105597 10.1016/j.cor.2018.02.021 10.1016/j.jsr.2021.02.009 10.1016/j.ssci.2008.01.006 10.1016/j.jsr.2020.02.006 10.1016/j.jprocont.2014.01.012 10.1109/TKDE.2009.191 10.1016/j.aap.2008.11.002 10.1016/j.aap.2011.03.025 10.1038/nature14539 10.1016/j.trf.2013.12.009 10.3390/en15030791 10.1016/j.jns.2013.08.004 10.1016/j.aap.2018.08.025 10.1016/j.ress.2011.03.006 10.1016/j.aap.2008.02.003 10.3390/su142316048 10.1016/j.aap.2021.106510 10.1016/j.autcon.2016.05.016 |
| ContentType | Journal Article |
| Copyright | 2023 The Author(s) |
| Copyright_xml | – notice: 2023 The Author(s) |
| DBID | 6I. AAFTH AAYXX CITATION DOA |
| DOI | 10.1016/j.treng.2023.100179 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef DOAJ Open Access Full Text |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2666-691X |
| ExternalDocumentID | oai_doaj_org_article_b225feee33cf4b5786161ca5c0c021ea 10_1016_j_treng_2023_100179 S2666691X23000192 |
| GroupedDBID | 6I. AAEDW AAFTH AAXUO ACLIJ AITUG ALMA_UNASSIGNED_HOLDINGS AMRAJ EBS FDB GROUPED_DOAJ M41 M~E NCXOZ OK1 ROL 0R~ AALRI AAYWO AAYXX ACVFH ADCNI ADVLN AEUPX AFJKZ AFPUW AIGII AKBMS AKRWK AKYEP APXCP CITATION |
| ID | FETCH-LOGICAL-c3299-d3d9f9a17a4bdaa5ab21e4d8f226b5c41c0a937ec3a660d7ea3ecceec9249d6c3 |
| IEDL.DBID | DOA |
| ISSN | 2666-691X |
| IngestDate | Fri Oct 03 12:51:58 EDT 2025 Thu Nov 20 00:54:43 EST 2025 Tue Nov 18 21:47:10 EST 2025 Tue Jul 25 20:54:06 EDT 2023 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Machine-learning classification algorithms Bicyclist injury severity Transportation engineering |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c3299-d3d9f9a17a4bdaa5ab21e4d8f226b5c41c0a937ec3a660d7ea3ecceec9249d6c3 |
| OpenAccessLink | https://doaj.org/article/b225feee33cf4b5786161ca5c0c021ea |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_b225feee33cf4b5786161ca5c0c021ea crossref_citationtrail_10_1016_j_treng_2023_100179 crossref_primary_10_1016_j_treng_2023_100179 elsevier_sciencedirect_doi_10_1016_j_treng_2023_100179 |
| PublicationCentury | 2000 |
| PublicationDate | June 2023 2023-06-00 2023-06-01 |
| PublicationDateYYYYMMDD | 2023-06-01 |
| PublicationDate_xml | – month: 06 year: 2023 text: June 2023 |
| PublicationDecade | 2020 |
| PublicationTitle | Transportation engineering (Oxford) |
| PublicationYear | 2023 |
| Publisher | Elsevier Ltd Elsevier |
| Publisher_xml | – name: Elsevier Ltd – name: Elsevier |
| References | NHTSA. Traffic Safety facts. National Highway Traffic Safety Administration, Washington (DC). Report No.: DOT HS 812 681. Zhang, Cai (bib0013) 2014; 23 W. Yi, A.P.C. Chan, X. Wang, J. Wang, 2016. Development of an early-warning system for site work in hot and humid environments: automation in construction 62, February 2016, Pages 101–113. doi LeCun, Bengio, Hinton (bib0023) 2015; 521 Kaitlin Kirasich, Trace Smith, Bivin Sadler, 2018. Random forest vs logistic regression: binary classification for heterogeneous datasets random forest vs logistic regression: binary classification for heterogeneous datasets, Volume 1, 3. Kawada (bib0033) 2013; 334 Ciarapica, Giacchetta (bib0027) 2009; 47 Jeong, Jang, Bowman, Masoud (bib0036) 2018; 120 Macioszek, Granà (bib0044) 2022; 14 Chen, Zhang, Qian, Tarefder, Tian (bib0021) 2016; 90 Bahrololoom, Young, Loganc (bib0011) 2020; 144 Rivas, Paz, Martín, Matías, García, Taboada (bib0031) 2011; 96 Zhou, Roshandeh, Zhang, Ma (bib0017) 2016; 137 Lopez, Glickman, Soumerai, Hemenway (bib0018) 2017 Cun, Bengio, Hinton (bib0035) 2015; 521 Sarkar, Vinay, Raj, Maiti, Mitra (bib0026) 2019; 106 Tay, Kattan, Sun (bib0009) 2010; 4 Pan, Yang (bib0034) 2010; 22 Macioszek, Granà (bib0045) 2022; 15 Tay, Rifaat, Chin (bib0010) 2008; 40 Roshandeh, Zhou, Behnood (bib0016) 2016; 38 Jiang, Lu, Chen, Lu (bib0015) 2016; 95 Sanchez, Iglesias-Rodríguez, Riesgo, de Cos Juez (bib0024) 2016; 52 Tay, Barua, Kattan (bib0008) 2009; 41 Lord, Mannering (bib0019) 2010; 44 Tixier, Hallowell, Rajagopalan, Bowman (bib0022) 2016; 69 Dongab (bib0030) 2021; 176 Kim, Pant, Yamashita (bib0007) 2008; 2083 . Hosseinpour, Madsen, Vingaard Olesen, Lahrmann (bib0006) 2021; 77 NHTSA, 2020. Fatality data show increased traffic fatalities during pandemic. Samerei, Aghabay, Shiwakoti, Mohammadi (bib0005) 2021; 79 Yuan, Zhai, Ji, Yang, Yu, Yu (bib0046) 2022; 14 Liu, Pan, Dezert (bib0025) 2013; 46 Rahman, Abdel-Aty (bib0002) 2019; 70 Bahrololoom, Moridpour, Tay, Young (bib0014) 2017 Shang, Yang, Huang, Lyu (bib0029) 2014; 24 Liu, Khattak, Li, Nie, Ling (bib0012) 2020; 73 Savolainen, Mannering, Lord, Quddus (bib0020) 2011; 43 Eriksson, Niska, Forsman (bib0043) 2022; 165 Zhang (10.1016/j.treng.2023.100179_bib0013) 2014; 23 Eriksson (10.1016/j.treng.2023.100179_bib0043) 2022; 165 Ciarapica (10.1016/j.treng.2023.100179_bib0027) 2009; 47 Liu (10.1016/j.treng.2023.100179_bib0025) 2013; 46 Rahman (10.1016/j.treng.2023.100179_bib0002) 2019; 70 Tay (10.1016/j.treng.2023.100179_bib0008) 2009; 41 Sarkar (10.1016/j.treng.2023.100179_bib0026) 2019; 106 Savolainen (10.1016/j.treng.2023.100179_bib0020) 2011; 43 Jiang (10.1016/j.treng.2023.100179_bib0015) 2016; 95 Yuan (10.1016/j.treng.2023.100179_bib0046) 2022; 14 Pan (10.1016/j.treng.2023.100179_bib0034) 2010; 22 Dongab (10.1016/j.treng.2023.100179_bib0030) 2021; 176 Bahrololoom (10.1016/j.treng.2023.100179_bib0014) 2017 Macioszek (10.1016/j.treng.2023.100179_bib0044) 2022; 14 Bahrololoom (10.1016/j.treng.2023.100179_bib0011) 2020; 144 Sanchez (10.1016/j.treng.2023.100179_bib0024) 2016; 52 LeCun (10.1016/j.treng.2023.100179_bib0023) 2015; 521 10.1016/j.treng.2023.100179_bib0004 Jeong (10.1016/j.treng.2023.100179_bib0036) 2018; 120 10.1016/j.treng.2023.100179_bib0003 10.1016/j.treng.2023.100179_bib0001 10.1016/j.treng.2023.100179_bib0028 Lopez (10.1016/j.treng.2023.100179_bib0018) 2017 10.1016/j.treng.2023.100179_bib0040 Cun (10.1016/j.treng.2023.100179_bib0035) 2015; 521 Liu (10.1016/j.treng.2023.100179_bib0012) 2020; 73 Roshandeh (10.1016/j.treng.2023.100179_bib0016) 2016; 38 Tixier (10.1016/j.treng.2023.100179_bib0022) 2016; 69 10.1016/j.treng.2023.100179_bib0042 10.1016/j.treng.2023.100179_bib0041 Kawada (10.1016/j.treng.2023.100179_bib0033) 2013; 334 Samerei (10.1016/j.treng.2023.100179_bib0005) 2021; 79 Macioszek (10.1016/j.treng.2023.100179_bib0045) 2022; 15 Tay (10.1016/j.treng.2023.100179_bib0010) 2008; 40 Shang (10.1016/j.treng.2023.100179_bib0029) 2014; 24 Kim (10.1016/j.treng.2023.100179_bib0007) 2008; 2083 Zhou (10.1016/j.treng.2023.100179_bib0017) 2016; 137 Tay (10.1016/j.treng.2023.100179_bib0009) 2010; 4 Rivas (10.1016/j.treng.2023.100179_bib0031) 2011; 96 Chen (10.1016/j.treng.2023.100179_bib0021) 2016; 90 10.1016/j.treng.2023.100179_bib0039 Lord (10.1016/j.treng.2023.100179_bib0019) 2010; 44 Hosseinpour (10.1016/j.treng.2023.100179_bib0006) 2021; 77 10.1016/j.treng.2023.100179_bib0038 |
| References_xml | – volume: 79 start-page: 246 year: 2021 end-page: 256 ident: bib0005 article-title: Using latent class clustering and binary logistic regression to model Australian cyclist injury severity in motor vehicle–bicycle crashes publication-title: J. Safety Res. – volume: 41 start-page: 227 year: 2009 end-page: 233 ident: bib0008 article-title: Factors contributing to hit-and-run in fatal crashes publication-title: Accid. Anal. Prev. – volume: 23 start-page: 113 year: 2014 end-page: 124 ident: bib0013 article-title: Factors contributing to hit-and-run crashes in China publication-title: Transp. Res. Part F Traffic Psychol. Behav. – volume: 95 start-page: 373 year: 2016 end-page: 380 ident: bib0015 article-title: Hit-and-run crashes in urban river-crossing road tunnels publication-title: Accid. Anal. Prev. Traffic Saf. China – volume: 43 start-page: 1666 year: 2011 end-page: 1676 ident: bib0020 article-title: The statistical analysis of highway crash-injury severities: a review and assessment of methodological alternatives publication-title: Accid. Anal. Prev. – volume: 176 year: 2021 ident: bib0030 article-title: Multi class SVM algorithm with active learning for network traffic classification publication-title: Expert Syst. Appl. – reference: NHTSA, 2020. Fatality data show increased traffic fatalities during pandemic. – volume: 24 start-page: 223 year: 2014 end-page: 233 ident: bib0029 article-title: Data-driven soft sensor development based on deep learning technique publication-title: J. Process Control – volume: 4 year: 2010 ident: bib0009 article-title: Logistic model of hit and run crashes in Calgary publication-title: Can. J. Transport. – volume: 120 start-page: 250 year: 2018 end-page: 261 ident: bib0036 article-title: Classification of motor vehicle crash injury severity: a hybrid approach for imbalanced data publication-title: Accid. Anal. Prev. – volume: 521 start-page: 436 year: 2015 end-page: 444 ident: bib0035 article-title: Deep learning publication-title: Nature – volume: 521 start-page: 436 year: 2015 end-page: 444 ident: bib0023 article-title: Deep learning publication-title: Nature – volume: 22 start-page: 1345 year: 2010 end-page: 1359 ident: bib0034 article-title: A survey on transfer learning publication-title: IEEE Trans. Knowl. Data Eng. – volume: 144 year: 2020 ident: bib0011 article-title: Modelling injury severity of bicyclists in bicycle-car crashes at intersections publication-title: Accid. Anal. Prev – volume: 38 start-page: 22 year: 2016 end-page: 28 ident: bib0016 article-title: Comparison of contributing factors in hit-and-run crashes with distracted and non-distracted drivers publication-title: Transp. Res. Part F Traffic Psychol. Behav. – volume: 14 year: 2022 ident: bib0044 article-title: The analysis of the factors influencing the severity of bicyclist injury in bicyclist-vehicle crashes. The analysis of the factors influencing the severity of bicyclist injury in bicyclist-vehicle crashes publication-title: Sustainability – year: 2017 ident: bib0014 article-title: Factors affecting hit and run bicycle crashes in Victoria publication-title: Australia. Presented at the Australasian Road Safety Conference, 2017, Perth, Western Australia, Australia – volume: 70 start-page: 275 year: 2019 end-page: 288 ident: bib0002 article-title: Applying machine learning approaches to analyze the vulnerable road users crashes at statewide traffic analysis zones publication-title: J. Saf. Res. – volume: 96 start-page: 739 year: 2011 end-page: 747 ident: bib0031 article-title: Explaining and predicting workplace accidents using data-mining techniques publication-title: Reliab. Eng. Syst. Saf. – volume: 77 start-page: 114 year: 2021 end-page: 124 ident: bib0006 article-title: An in-depth analysis of self-reported cycling injuries in single and multiparty bicycle crashes in Denmark publication-title: J. Saf. Res. – volume: 2083 start-page: 114 year: 2008 end-page: 121 ident: bib0007 article-title: Hit-and-run crashes: use of rough set analysis with logistic regression to capture critical attributes and determinants publication-title: Transp. Res. Rec. J. Transp. Res. Board – reference: W. Yi, A.P.C. Chan, X. Wang, J. Wang, 2016. Development of an early-warning system for site work in hot and humid environments: automation in construction 62, February 2016, Pages 101–113. doi: – volume: 69 start-page: 102 year: 2016 end-page: 114 ident: bib0022 article-title: Application of machine learning to construction injury prediction publication-title: Autom. Constr. – volume: 137 start-page: 554 year: 2016 end-page: 562 ident: bib0017 article-title: Analysis of factors contributing to hit-and-run crashes involved with improper driving behaviors publication-title: Procedia Eng Green Intelligent Transp. Syst. Saf. – volume: 46 start-page: 834 year: 2013 end-page: 844 ident: bib0025 article-title: A new belief-based K-nearest neighbor classification method publication-title: Pattern Recognit. – volume: 40 start-page: 1330 year: 2008 end-page: 1336 ident: bib0010 article-title: A logistic model of the effects of roadway, environmental, vehicle, crash and driver characteristics on hit-and-run crashes publication-title: Accid. Anal. Prev. – year: 2017 ident: bib0018 article-title: Identifying factors related to a hit-and-run after a vehicle-bicycle collision publication-title: J. Transp. Health. – volume: 106 start-page: 210 year: 2019 end-page: 224 ident: bib0026 article-title: Application of optimized machine learning techniques for prediction of occupational accidents publication-title: Comput. Operations Res. – volume: 47 start-page: 36 year: 2009 end-page: 49 ident: bib0027 article-title: Classification and prediction of occupational injury risk using soft computing techniques publication-title: Saf. Sci. – volume: 73 start-page: 25 year: 2020 end-page: 35 ident: bib0012 article-title: Bicyclist injury severity in traffic crashes: a spatial approach for geo-referenced crash data to uncover non-stationary correlates publication-title: J. Saf. Res. – reference: . – volume: 52 start-page: 92 year: 2016 end-page: 99 ident: bib0024 article-title: Applying the K-nearest neighbor technique to the classification of workers according to their risk of suffering musculoskeletal disorders publication-title: Int. J. Ind. Ergon. – volume: 165 year: 2022 ident: bib0043 article-title: Injured cyclists with focus on single-bicycle crashes and differences in injury severity in Sweden publication-title: Accid. Anal. Prev – volume: 15 start-page: 791 year: 2022 ident: bib0045 article-title: External environmental analysis for sustainable bike-sharing system development. external environmental analysis for sustainable bike-sharing system development publication-title: Energies – volume: 14 start-page: 16048 year: 2022 ident: bib0046 article-title: Correlation analysis on accident injury and risky behavior of vulnerable road users based on bayesian general ordinal logit model publication-title: Sustainability – reference: /. – volume: 334 start-page: 197 year: 2013 ident: bib0033 article-title: The number of independent variables and events for multiple logistic regression analysis publication-title: J. Neurol. Sci. – volume: 90 start-page: 128 year: 2016 end-page: 139 ident: bib0021 article-title: Investigating driver injury severity patterns in rollover crashes using support vector machine models publication-title: Accid. Anal. Prev. – reference: Kaitlin Kirasich, Trace Smith, Bivin Sadler, 2018. Random forest vs logistic regression: binary classification for heterogeneous datasets random forest vs logistic regression: binary classification for heterogeneous datasets, Volume 1, 3. – reference: NHTSA. Traffic Safety facts. National Highway Traffic Safety Administration, Washington (DC). Report No.: DOT HS 812 681. – volume: 44 start-page: 291 year: 2010 end-page: 305 ident: bib0019 article-title: The statistical analysis of crash-frequency data: a review and assessment of methodological alternatives publication-title: Transp. Res. Part Policy Pract. – volume: 2083 start-page: 114 year: 2008 ident: 10.1016/j.treng.2023.100179_bib0007 article-title: Hit-and-run crashes: use of rough set analysis with logistic regression to capture critical attributes and determinants publication-title: Transp. Res. Rec. J. Transp. Res. Board doi: 10.3141/2083-13 – ident: 10.1016/j.treng.2023.100179_bib0028 doi: 10.1016/j.autcon.2015.11.003 – ident: 10.1016/j.treng.2023.100179_bib0004 – volume: 52 start-page: 92 year: 2016 ident: 10.1016/j.treng.2023.100179_bib0024 article-title: Applying the K-nearest neighbor technique to the classification of workers according to their risk of suffering musculoskeletal disorders publication-title: Int. J. Ind. Ergon. doi: 10.1016/j.ergon.2015.09.012 – year: 2017 ident: 10.1016/j.treng.2023.100179_bib0014 article-title: Factors affecting hit and run bicycle crashes in Victoria – volume: 90 start-page: 128 issue: Supplement C year: 2016 ident: 10.1016/j.treng.2023.100179_bib0021 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: 38 start-page: 22 year: 2016 ident: 10.1016/j.treng.2023.100179_bib0016 article-title: Comparison of contributing factors in hit-and-run crashes with distracted and non-distracted drivers publication-title: Transp. Res. Part F Traffic Psychol. Behav. doi: 10.1016/j.trf.2015.12.016 – volume: 137 start-page: 554 year: 2016 ident: 10.1016/j.treng.2023.100179_bib0017 article-title: Analysis of factors contributing to hit-and-run crashes involved with improper driving behaviors publication-title: Procedia Eng Green Intelligent Transp. Syst. Saf. – volume: 44 start-page: 291 issue: 5 year: 2010 ident: 10.1016/j.treng.2023.100179_bib0019 article-title: The statistical analysis of crash-frequency data: a review and assessment of methodological alternatives publication-title: Transp. Res. Part Policy Pract. doi: 10.1016/j.tra.2010.02.001 – volume: 70 start-page: 275 year: 2019 ident: 10.1016/j.treng.2023.100179_bib0002 article-title: Applying machine learning approaches to analyze the vulnerable road users crashes at statewide traffic analysis zones publication-title: J. Saf. Res. doi: 10.1016/j.jsr.2019.04.008 – volume: 79 start-page: 246 year: 2021 ident: 10.1016/j.treng.2023.100179_bib0005 article-title: Using latent class clustering and binary logistic regression to model Australian cyclist injury severity in motor vehicle–bicycle crashes publication-title: J. Safety Res. doi: 10.1016/j.jsr.2021.09.005 – volume: 95 start-page: 373 year: 2016 ident: 10.1016/j.treng.2023.100179_bib0015 article-title: Hit-and-run crashes in urban river-crossing road tunnels publication-title: Accid. Anal. Prev. Traffic Saf. China doi: 10.1016/j.aap.2015.09.003 – volume: 46 start-page: 834 issue: 3 year: 2013 ident: 10.1016/j.treng.2023.100179_bib0025 article-title: A new belief-based K-nearest neighbor classification method publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2012.10.001 – ident: 10.1016/j.treng.2023.100179_bib0039 – volume: 144 year: 2020 ident: 10.1016/j.treng.2023.100179_bib0011 article-title: Modelling injury severity of bicyclists in bicycle-car crashes at intersections publication-title: Accid. Anal. Prev doi: 10.1016/j.aap.2020.105597 – volume: 106 start-page: 210 year: 2019 ident: 10.1016/j.treng.2023.100179_bib0026 article-title: Application of optimized machine learning techniques for prediction of occupational accidents publication-title: Comput. Operations Res. doi: 10.1016/j.cor.2018.02.021 – ident: 10.1016/j.treng.2023.100179_bib0042 – volume: 77 start-page: 114 year: 2021 ident: 10.1016/j.treng.2023.100179_bib0006 article-title: An in-depth analysis of self-reported cycling injuries in single and multiparty bicycle crashes in Denmark publication-title: J. Saf. Res. doi: 10.1016/j.jsr.2021.02.009 – volume: 47 start-page: 36 issue: 1 year: 2009 ident: 10.1016/j.treng.2023.100179_bib0027 article-title: Classification and prediction of occupational injury risk using soft computing techniques publication-title: Saf. Sci. doi: 10.1016/j.ssci.2008.01.006 – year: 2017 ident: 10.1016/j.treng.2023.100179_bib0018 article-title: Identifying factors related to a hit-and-run after a vehicle-bicycle collision publication-title: J. Transp. Health. – ident: 10.1016/j.treng.2023.100179_bib0040 – volume: 73 start-page: 25 year: 2020 ident: 10.1016/j.treng.2023.100179_bib0012 article-title: Bicyclist injury severity in traffic crashes: a spatial approach for geo-referenced crash data to uncover non-stationary correlates publication-title: J. Saf. Res. doi: 10.1016/j.jsr.2020.02.006 – volume: 24 start-page: 223 issue: 3 year: 2014 ident: 10.1016/j.treng.2023.100179_bib0029 article-title: Data-driven soft sensor development based on deep learning technique publication-title: J. Process Control doi: 10.1016/j.jprocont.2014.01.012 – volume: 22 start-page: 1345 issue: 10 year: 2010 ident: 10.1016/j.treng.2023.100179_bib0034 article-title: A survey on transfer learning publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2009.191 – ident: 10.1016/j.treng.2023.100179_bib0003 – volume: 41 start-page: 227 issue: 2 year: 2009 ident: 10.1016/j.treng.2023.100179_bib0008 article-title: Factors contributing to hit-and-run in fatal crashes publication-title: Accid. Anal. Prev. doi: 10.1016/j.aap.2008.11.002 – volume: 43 start-page: 1666 issue: 5 year: 2011 ident: 10.1016/j.treng.2023.100179_bib0020 article-title: The statistical analysis of highway crash-injury severities: a review and assessment of methodological alternatives publication-title: Accid. Anal. Prev. doi: 10.1016/j.aap.2011.03.025 – volume: 521 start-page: 436 issue: 2015 year: 2015 ident: 10.1016/j.treng.2023.100179_bib0023 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – volume: 23 start-page: 113 year: 2014 ident: 10.1016/j.treng.2023.100179_bib0013 article-title: Factors contributing to hit-and-run crashes in China publication-title: Transp. Res. Part F Traffic Psychol. Behav. doi: 10.1016/j.trf.2013.12.009 – ident: 10.1016/j.treng.2023.100179_bib0038 – volume: 15 start-page: 791 year: 2022 ident: 10.1016/j.treng.2023.100179_bib0045 article-title: External environmental analysis for sustainable bike-sharing system development. external environmental analysis for sustainable bike-sharing system development publication-title: Energies doi: 10.3390/en15030791 – volume: 176 year: 2021 ident: 10.1016/j.treng.2023.100179_bib0030 article-title: Multi class SVM algorithm with active learning for network traffic classification publication-title: Expert Syst. Appl. – volume: 521 start-page: 436 issue: 7553 year: 2015 ident: 10.1016/j.treng.2023.100179_bib0035 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – volume: 334 start-page: 197 issue: 1–2 year: 2013 ident: 10.1016/j.treng.2023.100179_bib0033 article-title: The number of independent variables and events for multiple logistic regression analysis publication-title: J. Neurol. Sci. doi: 10.1016/j.jns.2013.08.004 – volume: 120 start-page: 250 year: 2018 ident: 10.1016/j.treng.2023.100179_bib0036 article-title: Classification of motor vehicle crash injury severity: a hybrid approach for imbalanced data publication-title: Accid. Anal. Prev. doi: 10.1016/j.aap.2018.08.025 – volume: 96 start-page: 739 issue: 7 year: 2011 ident: 10.1016/j.treng.2023.100179_bib0031 article-title: Explaining and predicting workplace accidents using data-mining techniques publication-title: Reliab. Eng. Syst. Saf. doi: 10.1016/j.ress.2011.03.006 – volume: 40 start-page: 1330 issue: 4 year: 2008 ident: 10.1016/j.treng.2023.100179_bib0010 article-title: A logistic model of the effects of roadway, environmental, vehicle, crash and driver characteristics on hit-and-run crashes publication-title: Accid. Anal. Prev. doi: 10.1016/j.aap.2008.02.003 – volume: 14 start-page: 16048 year: 2022 ident: 10.1016/j.treng.2023.100179_bib0046 article-title: Correlation analysis on accident injury and risky behavior of vulnerable road users based on bayesian general ordinal logit model publication-title: Sustainability doi: 10.3390/su142316048 – volume: 165 year: 2022 ident: 10.1016/j.treng.2023.100179_bib0043 article-title: Injured cyclists with focus on single-bicycle crashes and differences in injury severity in Sweden publication-title: Accid. Anal. Prev doi: 10.1016/j.aap.2021.106510 – ident: 10.1016/j.treng.2023.100179_bib0001 – volume: 4 issue: 1 year: 2010 ident: 10.1016/j.treng.2023.100179_bib0009 article-title: Logistic model of hit and run crashes in Calgary publication-title: Can. J. Transport. – volume: 69 start-page: 102 year: 2016 ident: 10.1016/j.treng.2023.100179_bib0022 article-title: Application of machine learning to construction injury prediction publication-title: Autom. Constr. doi: 10.1016/j.autcon.2016.05.016 – volume: 14 issue: 215 year: 2022 ident: 10.1016/j.treng.2023.100179_bib0044 article-title: The analysis of the factors influencing the severity of bicyclist injury in bicyclist-vehicle crashes. The analysis of the factors influencing the severity of bicyclist injury in bicyclist-vehicle crashes publication-title: Sustainability – ident: 10.1016/j.treng.2023.100179_bib0041 |
| SSID | ssj0002810837 |
| Score | 2.2205758 |
| Snippet | •Identifying a feature list to enter into a variety of machine-learning classification algorithms that predict the class of bicyclist injury... Predicting the severity of injuries caused by traffic accidents is an important undertaking because it may lead to establishing regulations increasing... |
| SourceID | doaj crossref elsevier |
| SourceType | Open Website Enrichment Source Index Database Publisher |
| StartPage | 100179 |
| SubjectTerms | Bicyclist injury severity Machine-learning classification algorithms Transportation engineering |
| Title | Building machine-learning models for reducing the severity of bicyclist road traffic injuries |
| URI | https://dx.doi.org/10.1016/j.treng.2023.100179 https://doaj.org/article/b225feee33cf4b5786161ca5c0c021ea |
| Volume | 12 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2666-691X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002810837 issn: 2666-691X databaseCode: DOA dateStart: 20200101 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: 2666-691X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002810837 issn: 2666-691X databaseCode: M~E dateStart: 20200101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV27TuwwELUQouAWiNfVXV5yQYkhibP2pmQRiAIQBaBtUOTH-GpXkEXZBYmGb2fGyaJU0NCkmDh2NDPSHMeTcxg79H1AUJAEIbPUizwFJQprjZCQeTrYkTJqLD1c6ZubwWhU3HakvqgnrKEHbhx3YjHhAgBI6UJuMb8UYhRn-i5xWJ4gQqNEF53N1CR-MkoRW9C_0liAlFBFOlpQDsXmrnkN1f9jkg6PJETUyNUpS5G9v1OdOhXnYp2ttVCRnzavuMGWoNpkfzoEglvscdiqWvPn2BQJolWBQANJ3Mw4YlJeEz0r2RDscVwLSLCOTwO3Y_funjDQvJ4az-e1IUIJPq4mJGQ322b3F-d3Z5eiFUwQTmJZEV76IhQm1Sa33pi-seih3A8CYizbd3nqEoNwBJw0SiVeg5EYQQBHmzCvnPzLlqtpBf8YVwrNFrS2g4D3vNE-6CxIkEZn1vkeyxb-Kl3LJk6iFk_lom1sUkYnl-TksnFyjx19PfTSkGl8P3xIgfgaSkzY0YD5Ubb5Uf6UHz2mFmEsW1DRgAWcavzd6ju_sfouW6Upm96yPbY8r19hn624t_l4Vh_EnMXr9cf5Jw8v9B4 |
| linkProvider | Directory of Open Access Journals |
| 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=Building+machine-learning+models+for+reducing+the+severity+of+bicyclist+road+traffic+injuries&rft.jtitle=Transportation+engineering+%28Oxford%29&rft.au=Birfir%2C+Slava&rft.au=Elalouf%2C+Amir&rft.au=Rosenbloom%2C+Tova&rft.date=2023-06-01&rft.pub=Elsevier+Ltd&rft.issn=2666-691X&rft.eissn=2666-691X&rft.volume=12&rft_id=info:doi/10.1016%2Fj.treng.2023.100179&rft.externalDocID=S2666691X23000192 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2666-691X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2666-691X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2666-691X&client=summon |