{"id":"https://openalex.org/W4220731420","doi":"https://doi.org/10.1080/03610918.2022.2046087","title":"OCtS: an alternative of the t-Score method sensitive to outliers and correlation in feature selection","display_name":"OCtS: an alternative of the t-Score method sensitive to outliers and correlation in feature selection","publication_year":2022,"publication_date":"2022-03-12","ids":{"openalex":"https://openalex.org/W4220731420","doi":"https://doi.org/10.1080/03610918.2022.2046087"},"language":"en","primary_location":{"id":"doi:10.1080/03610918.2022.2046087","is_oa":false,"landing_page_url":"https://doi.org/10.1080/03610918.2022.2046087","pdf_url":null,"source":{"id":"https://openalex.org/S153329750","display_name":"Communications in Statistics - Simulation and Computation","issn_l":"0361-0918","issn":["0361-0918","1532-4141"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Statistics - Simulation and Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002963683","display_name":"Mert Demirarslan","orcid":"https://orcid.org/0000-0001-8848-7340"},"institutions":[{"id":"https://openalex.org/I41641357","display_name":"Ege University","ror":"https://ror.org/02eaafc18","country_code":"TR","type":"education","lineage":["https://openalex.org/I41641357"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Mert Demirarslan","raw_affiliation_strings":["Faculty of Medicine, Department of Biostatistics and Medical Informatics, Ege University, \u0130zmir, Turkey"],"raw_orcid":"https://orcid.org/0000-0001-8848-7340","affiliations":[{"raw_affiliation_string":"Faculty of Medicine, Department of Biostatistics and Medical Informatics, Ege University, \u0130zmir, Turkey","institution_ids":["https://openalex.org/I41641357"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080853718","display_name":"Asl\u0131 S\u00fcner","orcid":"https://orcid.org/0000-0002-6872-9901"},"institutions":[{"id":"https://openalex.org/I41641357","display_name":"Ege University","ror":"https://ror.org/02eaafc18","country_code":"TR","type":"education","lineage":["https://openalex.org/I41641357"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Asl\u0131 Suner","raw_affiliation_strings":["Faculty of Medicine, Department of Biostatistics and Medical Informatics, Ege University, \u0130zmir, Turkey"],"raw_orcid":"https://orcid.org/0000-0002-6872-9901","affiliations":[{"raw_affiliation_string":"Faculty of Medicine, Department of Biostatistics and Medical Informatics, Ege University, \u0130zmir, Turkey","institution_ids":["https://openalex.org/I41641357"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5080853718"],"corresponding_institution_ids":["https://openalex.org/I41641357"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01982743,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"53","issue":"3","first_page":"1409","last_page":"1422"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9995999932289124,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9955999851226807,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.770645022392273},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.7436134815216064},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7291129231452942},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6776663064956665},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6443378925323486},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.6203570365905762},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6184987425804138},{"id":"https://openalex.org/keywords/gradient-boosting","display_name":"Gradient boosting","score":0.598321795463562},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5893875360488892},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5784125924110413},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.505310595035553},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4915798604488373},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.4282691478729248},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.415089875459671},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.4126887321472168},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2370329201221466}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.770645022392273},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7436134815216064},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7291129231452942},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6776663064956665},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6443378925323486},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.6203570365905762},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6184987425804138},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.598321795463562},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5893875360488892},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5784125924110413},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.505310595035553},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4915798604488373},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.4282691478729248},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.415089875459671},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.4126887321472168},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2370329201221466},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/03610918.2022.2046087","is_oa":false,"landing_page_url":"https://doi.org/10.1080/03610918.2022.2046087","pdf_url":null,"source":{"id":"https://openalex.org/S153329750","display_name":"Communications in Statistics - Simulation and Computation","issn_l":"0361-0918","issn":["0361-0918","1532-4141"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Statistics - Simulation and Computation","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W8145175","https://openalex.org/W575847903","https://openalex.org/W1619226191","https://openalex.org/W1666942233","https://openalex.org/W1678356000","https://openalex.org/W2005861721","https://openalex.org/W2017337590","https://openalex.org/W2027147487","https://openalex.org/W2034841618","https://openalex.org/W2094521154","https://openalex.org/W2148143831","https://openalex.org/W2162772535","https://openalex.org/W2177870565","https://openalex.org/W2293600471","https://openalex.org/W2295598076","https://openalex.org/W2579898249","https://openalex.org/W2581446344","https://openalex.org/W2695033683","https://openalex.org/W2738681903","https://openalex.org/W2767794418","https://openalex.org/W2780157115","https://openalex.org/W2786123035","https://openalex.org/W2787894218","https://openalex.org/W2800318991","https://openalex.org/W2805498989","https://openalex.org/W2899365137","https://openalex.org/W2900949315","https://openalex.org/W2911964244","https://openalex.org/W2934364120","https://openalex.org/W2963278959","https://openalex.org/W2990169631","https://openalex.org/W3011427405","https://openalex.org/W4212817109","https://openalex.org/W4212883601","https://openalex.org/W4255230573","https://openalex.org/W6732480269"],"related_works":["https://openalex.org/W2967733078","https://openalex.org/W3204430031","https://openalex.org/W3137904399","https://openalex.org/W4310492845","https://openalex.org/W2885778889","https://openalex.org/W2766514146","https://openalex.org/W2885516856","https://openalex.org/W4289703016","https://openalex.org/W4310224730","https://openalex.org/W4296079469"],"abstract_inverted_index":{"A":[0],"wide":[1],"range":[2],"of":[3,26,46,69,134],"issues":[4],"including":[5,99],"missing":[6],"values,":[7],"class":[8,10],"noise,":[9],"imbalance,":[11],"outliers,":[12],"correlation":[13],"and":[14,71,77,88,114,122,147],"irrelevant":[15,53],"variables":[16],"have":[17],"the":[18,23,39,44,131,142,158],"potential":[19],"to":[20,38,42,157],"negatively":[21],"affect":[22],"overall":[24],"performance":[25,45,123,133,155,180],"disease":[27,119,187],"diagnosis":[28,120,188],"classification":[29,49,132],"algorithms.":[30],"This":[31],"study":[32],"proposes":[33],"a":[34],"new":[35],"technique,":[36],"alternative":[37],"t-Score":[40,90],"method,":[41,151],"increase":[43],"ensemble":[47,96,136,183],"learning":[48,97,137,184],"algorithms":[50,98,138,185],"by":[51],"removing":[52],"variables.":[54],"Therefore,":[55],"three":[56],"publicly":[57],"available":[58],"datasets":[59,164],"from":[60],"medical":[61],"domain":[62],"varying":[63],"in":[64,186],"their":[65],"sample":[66],"sizes,":[67],"number":[68],"variables,":[70],"data":[72,172],"preprocessing":[73,173],"problems":[74],"were":[75,116,125],"selected":[76],"processed":[78],"with":[79,175],"our":[80,148],"newly":[81],"proposed":[82],"feature":[83,149],"selection":[84,150],"method":[85,144,161],"called":[86],"Outliers":[87],"Correlation":[89],"(OCtS).":[91],"Afterwards,":[92],"six":[93,135],"widely":[94],"used":[95],"Random":[100],"Forest,":[101],"Gradient":[102,106,110],"Boosting":[103,107,111],"Machine,":[104,108,112],"Extreme":[105],"Light":[109],"CatBoost,":[113],"Bagging":[115],"employed":[117],"for":[118],"classification,":[121],"metrics":[124],"measured.":[126],"Our":[127],"results":[128],"indicate":[129],"that":[130],"significantly":[139],"increased":[140],"when":[141,181],"OCtS":[143,176],"was":[145],"employed,":[146],"OCtS,":[152],"exhibited":[153],"higher":[154],"compared":[156],"standard":[159],"t-score":[160],"across":[162],"all":[163],"(p":[165],"=":[166],"0.0001).":[167],"We":[168],"conclude":[169],"that,":[170],"using":[171],"methods":[174],"offers":[177],"better":[178],"algorithm":[179],"employing":[182],"classification.":[189]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}