{"id":"https://openalex.org/W4400202924","doi":"https://doi.org/10.3390/a17070284","title":"Ensemble Learning with Pre-Trained Transformers for Crash Severity Classification: A Deep NLP Approach","display_name":"Ensemble Learning with Pre-Trained Transformers for Crash Severity Classification: A Deep NLP Approach","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4400202924","doi":"https://doi.org/10.3390/a17070284"},"language":"en","primary_location":{"id":"doi:10.3390/a17070284","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a17070284","pdf_url":"https://www.mdpi.com/1999-4893/17/7/284/pdf?version=1719742111","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/17/7/284/pdf?version=1719742111","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099111595","display_name":"Shadi Jaradat","orcid":"https://orcid.org/0000-0001-6322-2792"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Shadi Jaradat","raw_affiliation_strings":["Centre for Accident Research & Road Safety, Queensland University of Technology, Brisbane, QLD 4000, Australia","Centre of Data Science, Queensland University of Technology, Brisbane, QLD 4000, Australia"],"affiliations":[{"raw_affiliation_string":"Centre for Accident Research & Road Safety, Queensland University of Technology, Brisbane, QLD 4000, Australia","institution_ids":["https://openalex.org/I160993911"]},{"raw_affiliation_string":"Centre of Data Science, Queensland University of Technology, Brisbane, QLD 4000, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015158048","display_name":"Richi Nayak","orcid":"https://orcid.org/0000-0002-9954-0159"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Richi Nayak","raw_affiliation_strings":["Centre of Data Science, Queensland University of Technology, Brisbane, QLD 4000, Australia","School of Computer Science, Queensland University of Technology, Brisbane, QLD 4000, Australia"],"affiliations":[{"raw_affiliation_string":"Centre of Data Science, Queensland University of Technology, Brisbane, QLD 4000, Australia","institution_ids":["https://openalex.org/I160993911"]},{"raw_affiliation_string":"School of Computer Science, Queensland University of Technology, Brisbane, QLD 4000, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015632736","display_name":"Alexander Paz","orcid":"https://orcid.org/0000-0002-1217-9808"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Alexander Paz","raw_affiliation_strings":["School of Civil Engineering, Queensland University of Technology, Brisbane, QLD 4000, Australia"],"affiliations":[{"raw_affiliation_string":"School of Civil Engineering, Queensland University of Technology, Brisbane, QLD 4000, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048069896","display_name":"Mohammed Elhenawy","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Mohammed Elhenawy","raw_affiliation_strings":["Centre for Accident Research & Road Safety, Queensland University of Technology, Brisbane, QLD 4000, Australia"],"affiliations":[{"raw_affiliation_string":"Centre for Accident Research & Road Safety, Queensland University of Technology, Brisbane, QLD 4000, Australia","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048069896","https://openalex.org/A5099111595"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":3.9297,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93397816,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"17","issue":"7","first_page":"284","last_page":"284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10370","display_name":"Traffic and Road Safety","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10370","display_name":"Traffic and Road Safety","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11824","display_name":"Injury Epidemiology and Prevention","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7980730533599854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7841063737869263},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.7151732444763184},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.7120034098625183},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7005661725997925},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.5882452726364136},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5438197255134583},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.5340225696563721},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.508983850479126},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.4424320459365845},{"id":"https://openalex.org/keywords/crash","display_name":"Crash","score":0.42927515506744385},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41037869453430176},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37464702129364014},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.2975173890590668},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.10985246300697327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7980730533599854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7841063737869263},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.7151732444763184},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.7120034098625183},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7005661725997925},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.5882452726364136},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5438197255134583},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.5340225696563721},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.508983850479126},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.4424320459365845},{"id":"https://openalex.org/C183469790","wikidata":"https://www.wikidata.org/wiki/Q333501","display_name":"Crash","level":2,"score":0.42927515506744385},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41037869453430176},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37464702129364014},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2975173890590668},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.10985246300697327},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/a17070284","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a17070284","pdf_url":"https://www.mdpi.com/1999-4893/17/7/284/pdf?version=1719742111","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d07ac18df04a46dbbcc749232714c0e8","is_oa":true,"landing_page_url":"https://doaj.org/article/d07ac18df04a46dbbcc749232714c0e8","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 17, Iss 7, p 284 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/a17070284","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a17070284","pdf_url":"https://www.mdpi.com/1999-4893/17/7/284/pdf?version=1719742111","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6100000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400202924.pdf"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W80463681","https://openalex.org/W1933479155","https://openalex.org/W1965398296","https://openalex.org/W1966716734","https://openalex.org/W1974830732","https://openalex.org/W1976526581","https://openalex.org/W2005445120","https://openalex.org/W2007019606","https://openalex.org/W2012838480","https://openalex.org/W2054965269","https://openalex.org/W2076978163","https://openalex.org/W2100372437","https://openalex.org/W2133654650","https://openalex.org/W2148970256","https://openalex.org/W2153579005","https://openalex.org/W2167243426","https://openalex.org/W2167917621","https://openalex.org/W2168809519","https://openalex.org/W2342118450","https://openalex.org/W2395579298","https://openalex.org/W2509631465","https://openalex.org/W2546546968","https://openalex.org/W2762466482","https://openalex.org/W2891768540","https://openalex.org/W2917286209","https://openalex.org/W2931789502","https://openalex.org/W2944077210","https://openalex.org/W2966304865","https://openalex.org/W2976765180","https://openalex.org/W2981915020","https://openalex.org/W2988412621","https://openalex.org/W2989220192","https://openalex.org/W3001105617","https://openalex.org/W3037324494","https://openalex.org/W3041192002","https://openalex.org/W3044754756","https://openalex.org/W3087802854","https://openalex.org/W3101282851","https://openalex.org/W3113202420","https://openalex.org/W3128326203","https://openalex.org/W3133792808","https://openalex.org/W3156333129","https://openalex.org/W3171501718","https://openalex.org/W3183252725","https://openalex.org/W4205767597","https://openalex.org/W4248018214","https://openalex.org/W6607259140","https://openalex.org/W6653387014","https://openalex.org/W6679761827","https://openalex.org/W6728697715","https://openalex.org/W6759533311","https://openalex.org/W6761528492","https://openalex.org/W6778883912","https://openalex.org/W6781086118"],"related_works":["https://openalex.org/W2946409105","https://openalex.org/W3152932816","https://openalex.org/W2985392712","https://openalex.org/W4388996947","https://openalex.org/W3133567596","https://openalex.org/W2798009317","https://openalex.org/W3203949288","https://openalex.org/W4320058722","https://openalex.org/W4382201653","https://openalex.org/W4200051975"],"abstract_inverted_index":{"Transfer":[0],"learning":[1,58,61,99],"has":[2],"gained":[3],"significant":[4],"traction":[5],"in":[6,169,217],"natural":[7],"language":[8,17],"processing":[9],"due":[10],"to":[11,50,151,194],"the":[12,85,94,138,145,153,160,170,181,187,191,197,208,237],"emergence":[13],"of":[14,96,180,224],"state-of-the-art":[15],"pre-trained":[16],"models":[18,62,133,168,192,216],"(PLMs).":[19],"Unlike":[20],"traditional":[21],"word":[22,65],"embedding":[23,66],"methods":[24],"such":[25],"as":[26],"TF-IDF":[27],"and":[28,33,59,72,105,112,119,172,202,228,231,257],"Word2Vec,":[29,71,111],"PLMs":[30],"are":[31,121,134,250],"context-dependent":[32],"outperform":[34],"conventional":[35],"techniques":[36],"when":[37],"fine-tuned":[38,122],"for":[39,166,207,226,233,253],"specific":[40],"tasks.":[41,262],"This":[42],"paper":[43],"proposes":[44],"an":[45,148,221],"innovative":[46],"hard":[47],"voting":[48],"classifier":[49],"enhance":[51],"crash":[52,82,254],"severity":[53,255],"classification":[54,130,179,256,261],"by":[55],"combining":[56],"machine":[57,98],"deep":[60],"with":[63,109,123,196,247],"various":[64],"techniques,":[67],"including":[68],"BERT,":[69],"RoBERTa,":[70],"TF-IDF.":[73],"Our":[74],"study":[75],"involves":[76],"two":[77],"comprehensive":[78],"experiments":[79],"using":[80,147],"motorists\u2019":[81],"data":[83,155,248],"from":[84,159],"Missouri":[86],"State":[87],"Highway":[88],"Patrol.":[89],"The":[90,141,157,211],"first":[91],"experiment":[92,143],"evaluates":[93],"performance":[95,165,206],"three":[97],"models\u2014XGBoost":[100],"(XGB),":[101],"random":[102],"forest":[103],"(RF),":[104],"naive":[106],"Bayes":[107],"(NB)\u2014paired":[108],"TF-IDF,":[110],"BERT":[113,118],"feature":[114],"extraction":[115],"techniques.":[116],"Additionally,":[117],"RoBERTa":[120],"a":[124,177],"Bidirectional":[125],"Long":[126],"Short-Term":[127],"Memory":[128],"(Bi-LSTM)":[129],"model.":[131],"All":[132],"initially":[135],"evaluated":[136],"on":[137,236],"original":[139,161],"dataset.":[140,239],"second":[142],"repeats":[144],"evaluation":[146],"augmented":[149,188,238],"dataset":[150,162],"address":[152],"severe":[154],"imbalance.":[156],"results":[158],"show":[163],"strong":[164],"all":[167],"\u201cFatal\u201d":[171,227],"\u201cPersonal":[173,229],"Injury\u201d":[174,230],"classes":[175],"but":[176],"poor":[178],"minority":[182,209],"\u201cProperty":[183,234],"Damage\u201d":[184,235],"class.":[185,210],"In":[186],"dataset,":[189],"while":[190],"continued":[193],"excel":[195],"majority":[198],"classes,":[199],"only":[200],"XGB/TFIDF":[201],"BERT-LSTM":[203],"showed":[204],"improved":[205],"ensemble":[212,244],"model":[213],"outperformed":[214],"individual":[215],"both":[218],"datasets,":[219],"achieving":[220],"F1":[222],"score":[223],"99%":[225],"62%":[232],"These":[240],"findings":[241],"suggest":[242],"that":[243],"models,":[245],"combined":[246],"augmentation,":[249],"highly":[251],"effective":[252],"potentially":[258],"other":[259],"textual":[260]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}