{"id":"https://openalex.org/W4291910525","doi":"https://doi.org/10.1109/access.2022.3198662","title":"Auto-Prep: Efficient and Automated Data Preprocessing Pipeline","display_name":"Auto-Prep: Efficient and Automated Data Preprocessing Pipeline","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4291910525","doi":"https://doi.org/10.1109/access.2022.3198662"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3198662","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3198662","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2022.3198662","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069195965","display_name":"Mehwish Bilal","orcid":"https://orcid.org/0000-0002-6766-6240"},"institutions":[{"id":"https://openalex.org/I3130814776","display_name":"University of Okara","ror":"https://ror.org/02fmg6q11","country_code":"PK","type":"education","lineage":["https://openalex.org/I3130814776"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Mehwish Bilal","raw_affiliation_strings":["Department of Computer Science, University of Okara, Okara, Pakistan"],"raw_orcid":"https://orcid.org/0000-0002-6766-6240","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Okara, Okara, Pakistan","institution_ids":["https://openalex.org/I3130814776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047955118","display_name":"Ghulam Ali","orcid":"https://orcid.org/0000-0002-0726-2738"},"institutions":[{"id":"https://openalex.org/I3130814776","display_name":"University of Okara","ror":"https://ror.org/02fmg6q11","country_code":"PK","type":"education","lineage":["https://openalex.org/I3130814776"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Ghulam Ali","raw_affiliation_strings":["Department of Computer Science, University of Okara, Okara, Pakistan"],"raw_orcid":"https://orcid.org/0000-0002-0726-2738","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Okara, Okara, Pakistan","institution_ids":["https://openalex.org/I3130814776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101874727","display_name":"Muhammad Waseem Iqbal","orcid":"https://orcid.org/0000-0001-6284-5904"},"institutions":[{"id":"https://openalex.org/I4210100043","display_name":"Superior University","ror":"https://ror.org/00yh88643","country_code":"PK","type":"education","lineage":["https://openalex.org/I4210100043"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Waseem Iqbal","raw_affiliation_strings":["Department of Software Engineering, Superior University, Lahore, Pakistan"],"raw_orcid":"https://orcid.org/0000-0001-6284-5904","affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Superior University, Lahore, Pakistan","institution_ids":["https://openalex.org/I4210100043"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010653042","display_name":"Muhammad Anwar","orcid":"https://orcid.org/0000-0002-0615-3038"},"institutions":[{"id":"https://openalex.org/I3130814776","display_name":"University of Okara","ror":"https://ror.org/02fmg6q11","country_code":"PK","type":"education","lineage":["https://openalex.org/I3130814776"]},{"id":"https://openalex.org/I5100685","display_name":"University of Education","ror":"https://ror.org/052z7nw84","country_code":"PK","type":"education","lineage":["https://openalex.org/I5100685"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Anwar","raw_affiliation_strings":["Department of Information Sciences, Division of Science and Technology, University of Education, Lahore, Pakistan"],"raw_orcid":"https://orcid.org/0000-0002-0615-3038","affiliations":[{"raw_affiliation_string":"Department of Information Sciences, Division of Science and Technology, University of Education, Lahore, Pakistan","institution_ids":["https://openalex.org/I5100685","https://openalex.org/I3130814776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038265911","display_name":"Muhammad Sheraz Arshad Malik","orcid":"https://orcid.org/0000-0002-0944-6362"},"institutions":[{"id":"https://openalex.org/I194348271","display_name":"Government College University, Faisalabad","ror":"https://ror.org/051zgra59","country_code":"PK","type":"education","lineage":["https://openalex.org/I194348271"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Sheraz Arshad Malik","raw_affiliation_strings":["Department of Information Technology, Government College University Faisalabad, Faisalabad, Pakistan"],"raw_orcid":"https://orcid.org/0000-0002-0944-6362","affiliations":[{"raw_affiliation_string":"Department of Information Technology, Government College University Faisalabad, Faisalabad, Pakistan","institution_ids":["https://openalex.org/I194348271"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029682293","display_name":"Rabiah Abdul Kadir","orcid":"https://orcid.org/0000-0003-3897-0873"},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Rabiah Abdul Kadir","raw_affiliation_strings":["Institute of IR4.0, Universiti Kebangsaan Malaysia (UKM), Bangi, Selangor, Malaysia"],"raw_orcid":"https://orcid.org/0000-0003-3897-0873","affiliations":[{"raw_affiliation_string":"Institute of IR4.0, Universiti Kebangsaan Malaysia (UKM), Bangi, Selangor, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5069195965"],"corresponding_institution_ids":["https://openalex.org/I3130814776"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":11.4851,"has_fulltext":false,"cited_by_count":78,"citation_normalized_percentile":{"value":0.99021495,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"10","issue":null,"first_page":"107764","last_page":"107784"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9970999956130981,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.8092789053916931},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6944878101348877},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5558823943138123},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.4491337835788727},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4362643361091614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29724857211112976},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10839179158210754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8092789053916931},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6944878101348877},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5558823943138123},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.4491337835788727},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4362643361091614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29724857211112976},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10839179158210754}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3198662","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3198662","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:404b97a0d36942e387a03976cd16710d","is_oa":true,"landing_page_url":"https://doaj.org/article/404b97a0d36942e387a03976cd16710d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 107764-107784 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3198662","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3198662","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G3304534413","display_name":null,"funder_award_id":"GPK-4IR-2020-020","funder_id":"https://openalex.org/F4320322699","funder_display_name":"Universiti Kebangsaan Malaysia"}],"funders":[{"id":"https://openalex.org/F4320322699","display_name":"Universiti Kebangsaan Malaysia","ror":"https://ror.org/00bw8d226"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1484864026","https://openalex.org/W1508363294","https://openalex.org/W1536826708","https://openalex.org/W1537049716","https://openalex.org/W1612155886","https://openalex.org/W1634075355","https://openalex.org/W1680622244","https://openalex.org/W1966168183","https://openalex.org/W2074184525","https://openalex.org/W2127841934","https://openalex.org/W2139075905","https://openalex.org/W2140898374","https://openalex.org/W2480680997","https://openalex.org/W2517773182","https://openalex.org/W2605939563","https://openalex.org/W2607255160","https://openalex.org/W2608595939","https://openalex.org/W2626095066","https://openalex.org/W2749057300","https://openalex.org/W2785051855","https://openalex.org/W2886765421","https://openalex.org/W2895242880","https://openalex.org/W2899372475","https://openalex.org/W2910027896","https://openalex.org/W2919115771","https://openalex.org/W2921161724","https://openalex.org/W2941345940","https://openalex.org/W2947123069","https://openalex.org/W2948917653","https://openalex.org/W2975605169","https://openalex.org/W2976174503","https://openalex.org/W2977104352","https://openalex.org/W2996589733","https://openalex.org/W2999569333","https://openalex.org/W3005880794","https://openalex.org/W3006395747","https://openalex.org/W3007031763","https://openalex.org/W3020873385","https://openalex.org/W3024333932","https://openalex.org/W3040879595","https://openalex.org/W3074779148","https://openalex.org/W3110894330","https://openalex.org/W3167986842","https://openalex.org/W3185256938","https://openalex.org/W4213308398","https://openalex.org/W4288086169","https://openalex.org/W4385885462","https://openalex.org/W4392271976","https://openalex.org/W6755141915","https://openalex.org/W6755509158","https://openalex.org/W6761471028","https://openalex.org/W6780874407"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W2977327189","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2952736244"],"abstract_inverted_index":{"Data":[0],"preprocessing":[1,68,85,139],"is":[2,53,128],"crucial":[3],"in":[4],"the":[5,10,16,21,64,91,98,106,115,119,125,153,157,178,191,194],"Machine":[6,51],"Learning":[7,52],"pipeline":[8],"because":[9],"models\u2019":[11],"learning":[12],"ability":[13],"directly":[14],"affects":[15],"quality":[17],"of":[18,193],"data":[19,67,84,92,109,138],"and":[20,59,80,94,111,133,182],"underlying":[22],"information":[23],"acquired":[24],"from":[25],"this":[26,175],"stage.":[27],"Nevertheless,":[28],"surprisingly,":[29],"there":[30],"are":[31,149],"many":[32],"alternatives":[33],"for":[34,49,136],"each":[35],"transformation":[36],"task,":[37],"which":[38],"makes":[39],"an":[40,144],"inexperienced":[41],"user":[42,116],"overwhelmed.":[43],"A":[44],"simple":[45],"Python-based":[46],"Auto-preprocessing":[47],"architecture":[48,127],"Automated":[50],"developed":[54],"to":[55,62,97,114,143,189],"offer":[56],"automated,":[57],"interactive,":[58],"data-driven":[60],"support":[61],"help":[63],"users":[65],"perform":[66],"tasks":[69,86],"efficiently.":[70],"The":[71,147,167],"suggested":[72],"method":[73,113],"provides":[74],"valuable":[75],"insights":[76],"into":[77],"a":[78],"dataset":[79],"can":[81],"handle":[82],"standard":[83],"adeptly.":[87],"Initially,":[88],"it":[89,96,104,142,185],"detects":[90],"problem":[93],"presents":[95],"end-user":[99],"using":[100],"compelling":[101],"visualizations.":[102],"Then,":[103],"recommends":[105],"most":[107],"effective":[108],"cleaning":[110],"preparation":[112],"after":[117],"evaluating":[118],"state-of-the-art":[120],"candidate":[121],"techniques.":[122],"For":[123],"evaluation,":[124],"proposed":[126],"employed":[129],"on":[130,163],"ten":[131],"different":[132],"diverse":[134],"datasets":[135],"automatic":[137],"before":[140],"passing":[141],"ML":[145,159],"algorithm.":[146],"results":[148,154,168],"then":[150],"compared":[151],"with":[152],"generated":[155],"by":[156],"same":[158],"algorithm":[160],"but":[161,184],"implemented":[162],"manually":[164],"preprocessed":[165],"data.":[166],"have":[169],"shown":[170],"that":[171],"not":[172],"only":[173],"did":[174],"approach":[176],"make":[177],"whole":[179],"process":[180],"uncomplicated":[181],"facile,":[183],"was":[186],"also":[187],"able":[188],"improve":[190],"performance":[192],"model":[195],"significantly.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":11}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}