{"id":"https://openalex.org/W4392460210","doi":"https://doi.org/10.3390/info15030145","title":"Comparison of Cluster-Based Sampling Approaches for Imbalanced Data of Crashes Involving Large Trucks","display_name":"Comparison of Cluster-Based Sampling Approaches for Imbalanced Data of Crashes Involving Large Trucks","publication_year":2024,"publication_date":"2024-03-05","ids":{"openalex":"https://openalex.org/W4392460210","doi":"https://doi.org/10.3390/info15030145"},"language":"en","primary_location":{"id":"doi:10.3390/info15030145","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15030145","pdf_url":"https://www.mdpi.com/2078-2489/15/3/145/pdf?version=1709629039","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"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":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/15/3/145/pdf?version=1709629039","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086980535","display_name":"Syed As-Sadeq Tahfim","orcid":"https://orcid.org/0000-0002-1024-1006"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Syed As-Sadeq Tahfim","raw_affiliation_strings":["School of Maritime Economics and Management, Dalian Maritime University, Dalian 116026, China"],"affiliations":[{"raw_affiliation_string":"School of Maritime Economics and Management, Dalian Maritime University, Dalian 116026, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102909463","display_name":"Yan Chen","orcid":"https://orcid.org/0000-0001-9294-0128"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Chen","raw_affiliation_strings":["School of Maritime Economics and Management, Dalian Maritime University, Dalian 116026, China"],"affiliations":[{"raw_affiliation_string":"School of Maritime Economics and Management, Dalian Maritime University, Dalian 116026, China","institution_ids":["https://openalex.org/I43313876"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086980535"],"corresponding_institution_ids":["https://openalex.org/I43313876"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":3.5879,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.92099351,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"15","issue":"3","first_page":"145","last_page":"145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10370","display_name":"Traffic and Road Safety","score":0.9987000226974487,"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":0.9987000226974487,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9801999926567078,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/truck","display_name":"Truck","score":0.8496123552322388},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.6027312874794006},{"id":"https://openalex.org/keywords/cluster-sampling","display_name":"Cluster sampling","score":0.5575220584869385},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5468754768371582},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4604336619377136},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3732687830924988},{"id":"https://openalex.org/keywords/transport-engineering","display_name":"Transport engineering","score":0.36429110169410706},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3622671961784363},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.28626006841659546},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2092873454093933},{"id":"https://openalex.org/keywords/automotive-engineering","display_name":"Automotive engineering","score":0.0961475670337677},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.07769551873207092},{"id":"https://openalex.org/keywords/environmental-health","display_name":"Environmental health","score":0.0773138701915741},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.05413776636123657}],"concepts":[{"id":"https://openalex.org/C52121051","wikidata":"https://www.wikidata.org/wiki/Q43193","display_name":"Truck","level":2,"score":0.8496123552322388},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.6027312874794006},{"id":"https://openalex.org/C183380357","wikidata":"https://www.wikidata.org/wiki/Q1776598","display_name":"Cluster sampling","level":3,"score":0.5575220584869385},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5468754768371582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4604336619377136},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3732687830924988},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.36429110169410706},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3622671961784363},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.28626006841659546},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2092873454093933},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0961475670337677},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.07769551873207092},{"id":"https://openalex.org/C99454951","wikidata":"https://www.wikidata.org/wiki/Q932068","display_name":"Environmental health","level":1,"score":0.0773138701915741},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05413776636123657},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"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/info15030145","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15030145","pdf_url":"https://www.mdpi.com/2078-2489/15/3/145/pdf?version=1709629039","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"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":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4b63caa47e8a45b590445dee6bbaabde","is_oa":true,"landing_page_url":"https://doaj.org/article/4b63caa47e8a45b590445dee6bbaabde","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":"Information, Vol 15, Iss 3, p 145 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info15030145","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15030145","pdf_url":"https://www.mdpi.com/2078-2489/15/3/145/pdf?version=1709629039","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"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":"Information","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392460210.pdf"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W1998443375","https://openalex.org/W2007019606","https://openalex.org/W2080285081","https://openalex.org/W2086927126","https://openalex.org/W2087240369","https://openalex.org/W2097521902","https://openalex.org/W2099454382","https://openalex.org/W2101234009","https://openalex.org/W2104933073","https://openalex.org/W2123458540","https://openalex.org/W2128965734","https://openalex.org/W2132735659","https://openalex.org/W2148143831","https://openalex.org/W2149230623","https://openalex.org/W2155653793","https://openalex.org/W2157941646","https://openalex.org/W2509631465","https://openalex.org/W2562319768","https://openalex.org/W2594918460","https://openalex.org/W2750591756","https://openalex.org/W2762668685","https://openalex.org/W2765108094","https://openalex.org/W2792545433","https://openalex.org/W2889331935","https://openalex.org/W2897805291","https://openalex.org/W2899037650","https://openalex.org/W2899434936","https://openalex.org/W2901772120","https://openalex.org/W2911964244","https://openalex.org/W2919821184","https://openalex.org/W2942548795","https://openalex.org/W2945388018","https://openalex.org/W2947982105","https://openalex.org/W2990580840","https://openalex.org/W2991074212","https://openalex.org/W2996309201","https://openalex.org/W3037342254","https://openalex.org/W3039504676","https://openalex.org/W3042932150","https://openalex.org/W3044740104","https://openalex.org/W3087783715","https://openalex.org/W3091123608","https://openalex.org/W3145857728","https://openalex.org/W3155649056","https://openalex.org/W3166835977","https://openalex.org/W4230212260","https://openalex.org/W4280608029","https://openalex.org/W4353015314","https://openalex.org/W4362501134","https://openalex.org/W6634022324","https://openalex.org/W6635474240","https://openalex.org/W6675354045","https://openalex.org/W6677480971","https://openalex.org/W6756490639","https://openalex.org/W6760161469","https://openalex.org/W6780289322","https://openalex.org/W6781480655","https://openalex.org/W6904060930"],"related_works":["https://openalex.org/W2151768624","https://openalex.org/W2214078930","https://openalex.org/W3122052772","https://openalex.org/W561646759","https://openalex.org/W1983537108","https://openalex.org/W1974098980","https://openalex.org/W630632068","https://openalex.org/W587064707","https://openalex.org/W4205159025","https://openalex.org/W602275442"],"abstract_inverted_index":{"Severe":[0],"and":[1,11,24,63,79,118,143,152,159,227],"fatal":[2,25],"crashes":[3,27],"involving":[4,28],"large":[5,29],"trucks":[6,30],"result":[7],"in":[8,34,218,270],"significant":[9],"social":[10],"economic":[12],"losses":[13],"for":[14,59,260,264],"human":[15],"society.":[16],"Unfortunately,":[17],"the":[18,69,90,98,119,144,155,162,177,182,185,196,222,233,266],"notably":[19],"low":[20],"proportion":[21],"of":[22,72,184,235],"severe":[23],"injury":[26],"creates":[31],"an":[32],"imbalance":[33,268],"crash":[35,41,61,191,271],"data.":[36,272],"Models":[37],"trained":[38,151],"on":[39,190],"imbalanced":[40,60],"data":[42,102,192],"are":[43],"likely":[44,205,230,247],"to":[45,54,67,206,231,238,248],"produce":[46],"erroneous":[47],"results.":[48],"Therefore,":[49],"there":[50],"is":[51,65,204,229,246],"a":[52,73,84,239,252],"need":[53],"explore":[55],"novel":[56,85],"sampling":[57,77,110,115,179,219,223],"approaches":[58,111,180],"data,":[62],"it":[64],"crucial":[66],"determine":[68],"appropriate":[70],"combination":[71],"machine":[74,130,186],"learning":[75,131,187],"model,":[76],"approach,":[78],"ratio.":[80],"This":[81],"study":[82],"introduces":[83],"cluster-based":[86,96,100,173],"under-sampling":[87,174],"technique,":[88],"utilizing":[89],"k-prototypes":[91],"clustering":[92],"algorithm.":[93],"After":[94],"initial":[95],"under-sampling,":[97],"consolidated":[99],"under-sampled":[101],"set":[103],"was":[104],"further":[105],"resampled":[106],"using":[107,154],"three":[108],"different":[109],"(i.e.,":[112],"adaptive":[113],"synthetic":[114,120],"(ADASYN),":[116],"NearMiss-2,":[117,244],"minority":[121],"oversampling":[122],"technique":[123],"+":[124],"Tomek":[125],"links":[126],"(SMOTETomek)).":[127],"Later,":[128],"four":[129],"models":[132,188,236],"(logistic":[133],"regression":[134],"(LR),":[135],"random":[136],"forest":[137],"(RF),":[138],"gradient-boosted":[139],"decision":[140],"trees":[141],"(GBDT),":[142],"multi-layer":[145],"perceptron":[146],"(MLP)":[147],"neural":[148],"network)":[149],"were":[150],"evaluated":[153],"geometric":[156],"mean":[157],"(G-Mean)":[158],"area":[160],"under":[161],"receiver":[163],"operating":[164],"characteristic":[165],"curve":[166],"(AUC)":[167],"scores.":[168],"The":[169],"findings":[170,256],"suggest":[171],"that":[172],"coupled":[175],"with":[176,200,214,225,243],"investigated":[178],"improve":[181,232],"performance":[183,234,245],"developed":[189],"significantly.":[193],"In":[194],"addition,":[195],"GBDT":[197],"model":[198,212],"combined":[199,213],"ADASYN":[201,226],"or":[202],"SMOTETomek":[203,228],"yield":[207],"better":[208],"predictions":[209],"than":[210],"any":[211],"NearMiss-2.":[215],"Regarding":[216],"changes":[217],"ratios,":[220],"increasing":[221],"ratio":[224],"up":[237],"certain":[240],"level,":[241],"whereas":[242],"drop":[249],"significantly":[250],"beyond":[251],"specific":[253],"point.":[254],"These":[255],"provide":[257],"valuable":[258],"insights":[259],"selecting":[261],"optimal":[262],"strategies":[263],"treating":[265],"class":[267],"issue":[269]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-07T14:57:38.498316","created_date":"2025-10-10T00:00:00"}