{"id":"https://openalex.org/W4225073726","doi":"https://doi.org/10.5505/pajes.2021.62687","title":"A comprehensive review on data preprocessing techniques in data analysis","display_name":"A comprehensive review on data preprocessing techniques in data analysis","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4225073726","doi":"https://doi.org/10.5505/pajes.2021.62687"},"language":"en","primary_location":{"id":"doi:10.5505/pajes.2021.62687","doi":"https://doi.org/10.5505/pajes.2021.62687","is_oa":true,"landing_page_url":"https://doi.org/10.5505/pajes.2021.62687","pdf_url":"https://jag.journalagent.com/z4/download_fulltext.asp?pdir=pajes&plng=eng&un=PAJES-62687","source":{"id":"https://openalex.org/S2736584300","display_name":"Pamukkale University Journal of Engineering Sciences","issn_l":"1300-7009","issn":["1300-7009","2147-5881"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["dongbi-d","poland-20","russia-white-list-4","tr-dizin"],"host_organization":"https://openalex.org/P4310318385","host_organization_name":"Pamukkale University","host_organization_lineage":["https://openalex.org/P4310318385"],"host_organization_lineage_names":["Pamukkale University"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pamukkale University Journal of Engineering Sciences","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://jag.journalagent.com/z4/download_fulltext.asp?pdir=pajes&plng=eng&un=PAJES-62687","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055813528","display_name":"Volkan \u00c7ET\u0130N","orcid":"https://orcid.org/0000-0003-3131-5403","observed_orcids":["https://orcid.org/0000-0003-3131-5403"]},"institutions":[{"id":"https://openalex.org/I95634034","display_name":"Gazi University","ror":"https://ror.org/054xkpr46","country_code":"TR","type":"education","lineage":["https://openalex.org/I95634034"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Volkan \u00c7etin","raw_affiliation_strings":["Department of Computer Engineering , Faculty of Engineering , Gazi University , Ankara , Turkey","GAZ\u0130 \u00dcN\u0130VERS\u0130TES\u0130"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering , Faculty of Engineering , Gazi University , Ankara , Turkey","institution_ids":["https://openalex.org/I95634034"]},{"raw_affiliation_string":"GAZ\u0130 \u00dcN\u0130VERS\u0130TES\u0130","institution_ids":["https://openalex.org/I95634034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067359902","display_name":"Oktay Y\u0131ld\u0131z","orcid":"https://orcid.org/0000-0001-9155-7426","observed_orcids":["https://orcid.org/0000-0001-9155-7426"]},"institutions":[{"id":"https://openalex.org/I95634034","display_name":"Gazi University","ror":"https://ror.org/054xkpr46","country_code":"TR","type":"education","lineage":["https://openalex.org/I95634034"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Oktay Y\u0131ld\u0131z","raw_affiliation_strings":["GAZ\u0130 \u00dcN\u0130VERS\u0130TES\u0130"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GAZ\u0130 \u00dcN\u0130VERS\u0130TES\u0130","institution_ids":["https://openalex.org/I95634034"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5055813528"],"corresponding_institution_ids":["https://openalex.org/I95634034"],"apc_list":null,"apc_paid":null,"fwci":10.2636,"has_fulltext":true,"cited_by_count":99,"citation_normalized_percentile":{"value":0.98837565,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"28","issue":"2","first_page":"299","last_page":"312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.8925999999046326,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.8925999999046326,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.048500001430511475,"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/T13373","display_name":"Data Mining and Machine Learning Applications","score":0.026399999856948853,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/data-preprocessing","display_name":"data preprocessing","score":1.0},{"id":"https://openalex.org/keywords/data-cleaning","display_name":"data cleaning","score":0.996999979019165},{"id":"https://openalex.org/keywords/data-transformation","display_name":"data transformation","score":0.9950000047683716},{"id":"https://openalex.org/keywords/data-reduction","display_name":"data reduction","score":0.9900000095367432},{"id":"https://openalex.org/keywords/missing-data-handling","display_name":"missing data handling","score":0.7979999780654907},{"id":"https://openalex.org/keywords/outlier-detection","display_name":"outlier detection","score":0.4269999861717224},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"noise reduction","score":0.5289999842643738},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.3919999897480011},{"id":"https://openalex.org/keywords/model-performance","display_name":"model performance","score":0.39899998903274536},{"id":"https://openalex.org/keywords/big-data","display_name":"big data","score":0.5389999747276306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5741732716560364},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5511214733123779},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.4387579560279846},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4383944571018219},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3875803053379059},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35002273321151733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20155173540115356}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5505/pajes.2021.62687","doi":"https://doi.org/10.5505/pajes.2021.62687","is_oa":true,"landing_page_url":"https://doi.org/10.5505/pajes.2021.62687","pdf_url":"https://jag.journalagent.com/z4/download_fulltext.asp?pdir=pajes&plng=eng&un=PAJES-62687","source":{"id":"https://openalex.org/S2736584300","display_name":"Pamukkale University Journal of Engineering Sciences","issn_l":"1300-7009","issn":["1300-7009","2147-5881"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["dongbi-d","poland-20","russia-white-list-4","tr-dizin"],"host_organization":"https://openalex.org/P4310318385","host_organization_name":"Pamukkale University","host_organization_lineage":["https://openalex.org/P4310318385"],"host_organization_lineage_names":["Pamukkale University"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pamukkale University Journal of Engineering Sciences","raw_type":"journal-article"},{"id":"pmh:oai:dergipark.org.tr:article/1110427","doi":null,"is_oa":true,"landing_page_url":"https://dergipark.org.tr/tr/pub/pajes/issue/69632/1110427","pdf_url":null,"source":{"id":"https://openalex.org/S4306401840","display_name":"DergiPark (Istanbul University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67581229","host_organization_name":"Istanbul University","host_organization_lineage":["https://openalex.org/I67581229"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Pamukkale \u00dcniversitesi M\u00fchendislik Bilimleri Dergisi","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.5505/pajes.2021.62687","doi":"https://doi.org/10.5505/pajes.2021.62687","is_oa":true,"landing_page_url":"https://doi.org/10.5505/pajes.2021.62687","pdf_url":"https://jag.journalagent.com/z4/download_fulltext.asp?pdir=pajes&plng=eng&un=PAJES-62687","source":{"id":"https://openalex.org/S2736584300","display_name":"Pamukkale University Journal of Engineering Sciences","issn_l":"1300-7009","issn":["1300-7009","2147-5881"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["dongbi-d","poland-20","russia-white-list-4","tr-dizin"],"host_organization":"https://openalex.org/P4310318385","host_organization_name":"Pamukkale University","host_organization_lineage":["https://openalex.org/P4310318385"],"host_organization_lineage_names":["Pamukkale University"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pamukkale University Journal of Engineering Sciences","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[{"display_name":"Systematic Review","id":"https://openalex.org/study-designs/systematic-review"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4225073726.pdf","grobid_xml":"https://content.openalex.org/works/W4225073726.grobid-xml"},"referenced_works_count":76,"referenced_works":["https://openalex.org/W1992380169","https://openalex.org/W1994410331","https://openalex.org/W1996575035","https://openalex.org/W2078612822","https://openalex.org/W2107138773","https://openalex.org/W2107686700","https://openalex.org/W2169437694","https://openalex.org/W2182722412","https://openalex.org/W2206299551","https://openalex.org/W2238461883","https://openalex.org/W2332271625","https://openalex.org/W2343723090","https://openalex.org/W2344022952","https://openalex.org/W2345483369","https://openalex.org/W2409154825","https://openalex.org/W2429725500","https://openalex.org/W2494289807","https://openalex.org/W2512737680","https://openalex.org/W2521002152","https://openalex.org/W2524620548","https://openalex.org/W2545210392","https://openalex.org/W2552663603","https://openalex.org/W2553112030","https://openalex.org/W2562654122","https://openalex.org/W2564987603","https://openalex.org/W2573915595","https://openalex.org/W2574666645","https://openalex.org/W2582515246","https://openalex.org/W2588336250","https://openalex.org/W2589453516","https://openalex.org/W2592377938","https://openalex.org/W2594582036","https://openalex.org/W2596124285","https://openalex.org/W2600746833","https://openalex.org/W2601165891","https://openalex.org/W2602718451","https://openalex.org/W2604216405","https://openalex.org/W2607056758","https://openalex.org/W2607281691","https://openalex.org/W2623118547","https://openalex.org/W2625392185","https://openalex.org/W2736191004","https://openalex.org/W2747309270","https://openalex.org/W2758890981","https://openalex.org/W2765716772","https://openalex.org/W2766663781","https://openalex.org/W2768055745","https://openalex.org/W2769474643","https://openalex.org/W2777235285","https://openalex.org/W2779962409","https://openalex.org/W2780508324","https://openalex.org/W2782865993","https://openalex.org/W2783691054","https://openalex.org/W2792498089","https://openalex.org/W2793738599","https://openalex.org/W2798978457","https://openalex.org/W2802249969","https://openalex.org/W2808607069","https://openalex.org/W2810591130","https://openalex.org/W2886371990","https://openalex.org/W2898001300","https://openalex.org/W2900612779","https://openalex.org/W2906494211","https://openalex.org/W2912740422","https://openalex.org/W2915018599","https://openalex.org/W2925507233","https://openalex.org/W2945020349","https://openalex.org/W2951520411","https://openalex.org/W2961651406","https://openalex.org/W2979998718","https://openalex.org/W2991486385","https://openalex.org/W2996110062","https://openalex.org/W3007665943","https://openalex.org/W3014925248","https://openalex.org/W3048044163","https://openalex.org/W6696979589"],"related_works":["https://openalex.org/W2373691774","https://openalex.org/W7008846906","https://openalex.org/W3114412293","https://openalex.org/W2011972735","https://openalex.org/W4312438866","https://openalex.org/W7133203895","https://openalex.org/W2966617063","https://openalex.org/W4239963657","https://openalex.org/W4205337336","https://openalex.org/W2385178026"],"abstract_inverted_index":{"\u00d6zWith":[0],"the":[1,4,10,25,53,56,93,132,147,150],"technological":[2],"developments,":[3],"amount":[5],"of":[6,28,55,128,134,144,149],"data":[7,30,39,45,69,90,117,119,122,154,162,166,171],"stored":[8],"in":[9,44,92,142],"computer":[11],"environment":[12],"is":[13,49,61,136],"increasing":[14],"very":[15],"rapidly.Data":[16],"analysis":[17,70,172],"has":[18,103],"become":[19],"an":[20,41],"important":[21,42],"research":[22],"subject":[23],"for":[24],"correct":[26],"evaluation":[27],"these":[29],"and":[31,75,101,121,125,138],"to":[32,63],"transform":[33],"them":[34,65,129],"into":[35],"useful":[36,76],"information.Of":[37],"course,":[38],"play":[40],"role":[43],"analysis.However,":[46],"model":[47],"performance":[48],"highly":[50],"dependent":[51],"on":[52,89,160],"characteristics":[54],"data.For":[57],"this":[58,86],"reason,":[59],"it":[60,102],"essential":[62],"preprocess":[64],"before":[66],"starting":[67],"any":[68],"process.Data":[71],"preprocessing":[72,91,109,155,167],"creates":[73],"accurate":[74],"datasets":[77],"by":[78],"overcoming":[79],"erroneous,":[80],"incomplete,":[81],"or":[82,163],"other":[83],"unwanted":[84],"problems.In":[85],"study,":[87],"papers":[88],"last":[94],"5":[95,260],"years":[96],"have":[97],"been":[98,104],"researched":[99],"systematically":[100],"observed":[105],"that":[106],"widely":[107],"used":[108,159],"methods":[110,124,156,168,173],"are":[111,130,140,157,169],"classified":[112],"under":[113],"three":[114],"main":[115],"branches:":[116],"cleaning,":[118],"transformation":[120],"reduction.These":[123],"various":[126],"algorithms":[127],"examined,":[131],"frequency":[133],"use":[135],"presented,":[137],"comparisons":[139],"made":[141],"terms":[143],"accuracy":[145],"performance.As":[146],"result":[148],"study":[151],"shows,":[152],"when":[153,164],"not":[158],"raw":[161],"wrong":[165],"applied,":[170],"alone":[174],"cannot":[175],"achieve":[176],"sufficient":[177],"performance.Ya\u015fanan":[178],"teknolojik":[179],"geli\u015fmeler":[180],"ile":[181],"beraber":[182],"bilgisayar":[183],"ortam\u0131nda":[184],"saklanan":[185],"veri":[186,204,227,251,255,280,282,285,311,319,326],"miktar\u0131":[187],"\u00e7ok":[188],"h\u0131zl\u0131":[189],"bir":[190,195,207,215,226,232],"\u015fekilde":[191,196],"artmaktad\u0131r.Bu":[192],"verilerin":[193],"do\u011fru":[194,248],"de\u011ferlendirilmesi":[197],"ve":[198,249,264,269,284,291,298],"faydal\u0131":[199],"bilgiye":[200],"d\u00f6n\u00fc\u015ft\u00fcr\u00fclmesi":[201],"i\u00e7in":[202],"de":[203],"analizi":[205,228,327],"\u00f6nemli":[206,214],"ara\u015ft\u0131rma":[208],"konusu":[209],"olmu\u015ftur.Veri":[210],"analizinde":[211],"elbette":[212],"veriler":[213,309],"rol":[216],"oynar.Ancak":[217],"ba\u015far\u0131m,":[218],"verinin":[219],"\u00f6zelliklerine":[220],"b\u00fcy\u00fck":[221],"\u00f6l\u00e7\u00fcde":[222],"ba\u011f\u0131ml\u0131d\u0131r.Bu":[223],"sebeple":[224],"herhangi":[225],"s\u00fcreci":[229],"ba\u015flamadan":[230],"\u00f6nce":[231],"\u00f6n":[233,237,256,273,312,320],"i\u015flemden":[234],"ge\u00e7irmek":[235],"elzemdir.Veri":[236],"i\u015fleme":[238,257,274,313,321],"hatal\u0131,":[239],"eksik":[240],"ya":[241,316],"da":[242,305,317],"istenmeyen":[243],"di\u011fer":[244],"sorunlar\u0131n":[245],"\u00fcstesinden":[246],"gelerek":[247],"kullan\u0131\u015fl\u0131":[250],"k\u00fcmelerini":[252],"olu\u015fturur.Bu":[253],"makalede":[254],"konusunda":[258],"son":[259],"y\u0131lda":[261],"haz\u0131rlanm\u0131\u015f":[262],"makale":[263],"bildiriler":[265],"sistematik":[266],"olarak":[267,271,287],"ara\u015ft\u0131r\u0131lm\u0131\u015f":[268],"yayg\u0131n":[270],"kullan\u0131lan":[272],"y\u00f6ntemlerinin":[275],"\u00fc\u00e7":[276],"ana":[277],"dal":[278],"alt\u0131nda;":[279],"temizleme,":[281],"d\u00f6n\u00fc\u015ft\u00fcrme":[283],"azaltma":[286],"s\u0131n\u0131fland\u0131\u011f\u0131":[288],"g\u00f6r\u00fclm\u00fc\u015ft\u00fcr.Bu":[289],"y\u00f6ntemler":[290],"\u00e7e\u015fitli":[292],"algoritmalar\u0131":[293],"incelenmi\u015f,":[294],"kullan\u0131m":[295],"s\u0131kl\u0131klar\u0131":[296],"sunulmu\u015f":[297],"ba\u015far\u0131m":[299],"performanslar\u0131":[300],"a\u00e7\u0131s\u0131ndan":[301],"kar\u015f\u0131la\u015ft\u0131rmalar\u0131":[302],"yap\u0131lm\u0131\u015ft\u0131r.\u00c7al\u0131\u015fman\u0131n":[303],"sonucunun":[304],"g\u00f6sterdi\u011fi":[306],"\u00fczere":[307],"ham":[308],"\u00fczerine":[310],"y\u00f6ntemleri":[314,328],"kullan\u0131lmad\u0131\u011f\u0131nda":[315],"yanl\u0131\u015f":[318],"y\u00f6ntemi":[322],"kullan\u0131ld\u0131\u011f\u0131nda":[323],"tek":[324],"ba\u015f\u0131na":[325],"yeterli":[329],"ba\u015far\u0131mlara":[330],"ula\u015famamaktad\u0131r.":[331]},"counts_by_year":[{"year":2026,"cited_by_count":32},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":8}],"updated_date":"2026-10-21T09:56:26.102985","created_date":"2022-04-29T00:00:00"}