{"id":"https://openalex.org/W4387494240","doi":"https://doi.org/10.3233/scs-230008","title":"Data cleaning survey and challenges \u2013 improving outlier detection algorithm in machine learning","display_name":"Data cleaning survey and challenges \u2013 improving outlier detection algorithm in machine learning","publication_year":2023,"publication_date":"2023-10-09","ids":{"openalex":"https://openalex.org/W4387494240","doi":"https://doi.org/10.3233/scs-230008"},"language":"en","primary_location":{"id":"doi:10.3233/scs-230008","is_oa":true,"landing_page_url":"https://doi.org/10.3233/scs-230008","pdf_url":"https://content.iospress.com:443/download/journal-of-smart-cities-and-society/scs230008?id=journal-of-smart-cities-and-society%2Fscs230008","source":{"id":"https://openalex.org/S4220651211","display_name":"Journal of Smart Cities and Society","issn_l":"2772-3577","issn":["2772-3577","2772-3585"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Smart Cities and Society","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://content.iospress.com:443/download/journal-of-smart-cities-and-society/scs230008?id=journal-of-smart-cities-and-society%2Fscs230008","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092129175","display_name":"Sanae Borrohou","orcid":null},"institutions":[{"id":"https://openalex.org/I240042149","display_name":"Abdelmalek Essa\u00e2di University","ror":"https://ror.org/03c4shz64","country_code":"MA","type":"education","lineage":["https://openalex.org/I240042149"]}],"countries":["MA"],"is_corresponding":true,"raw_author_name":"Sanae Borrohou","raw_affiliation_strings":["IDS Team, Abdelmalek Essaadi University, Tangier, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDS Team, Abdelmalek Essaadi University, Tangier, Morocco","institution_ids":["https://openalex.org/I240042149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006207941","display_name":"Rachida Fissoune","orcid":null},"institutions":[{"id":"https://openalex.org/I240042149","display_name":"Abdelmalek Essa\u00e2di University","ror":"https://ror.org/03c4shz64","country_code":"MA","type":"education","lineage":["https://openalex.org/I240042149"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Rachida Fissoune","raw_affiliation_strings":["IDS Team, Abdelmalek Essaadi University, Tangier, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDS Team, Abdelmalek Essaadi University, Tangier, Morocco","institution_ids":["https://openalex.org/I240042149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014615360","display_name":"Hassan Badir","orcid":"https://orcid.org/0000-0002-6754-7807"},"institutions":[{"id":"https://openalex.org/I240042149","display_name":"Abdelmalek Essa\u00e2di University","ror":"https://ror.org/03c4shz64","country_code":"MA","type":"education","lineage":["https://openalex.org/I240042149"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Hassan Badir","raw_affiliation_strings":["IDS Team, Abdelmalek Essaadi University, Tangier, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDS Team, Abdelmalek Essaadi University, Tangier, Morocco","institution_ids":["https://openalex.org/I240042149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5092129175"],"corresponding_institution_ids":["https://openalex.org/I240042149"],"apc_list":null,"apc_paid":null,"fwci":6.9088,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.97643993,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"2","issue":"3","first_page":"125","last_page":"140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9997000098228455,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9997000098228455,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9684000015258789,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.96670001745224,"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/benchmarking","display_name":"Benchmarking","score":0.725609540939331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7215569615364075},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6310051679611206},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6105167269706726},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5779932141304016},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5640259981155396},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5558903813362122},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5450745224952698},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.47063538432121277},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46917277574539185},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3743630647659302},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13939377665519714}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.725609540939331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7215569615364075},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6310051679611206},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6105167269706726},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5779932141304016},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5640259981155396},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5558903813362122},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5450745224952698},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.47063538432121277},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46917277574539185},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3743630647659302},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13939377665519714},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/scs-230008","is_oa":true,"landing_page_url":"https://doi.org/10.3233/scs-230008","pdf_url":"https://content.iospress.com:443/download/journal-of-smart-cities-and-society/scs230008?id=journal-of-smart-cities-and-society%2Fscs230008","source":{"id":"https://openalex.org/S4220651211","display_name":"Journal of Smart Cities and Society","issn_l":"2772-3577","issn":["2772-3577","2772-3585"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Smart Cities and Society","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3233/scs-230008","is_oa":true,"landing_page_url":"https://doi.org/10.3233/scs-230008","pdf_url":"https://content.iospress.com:443/download/journal-of-smart-cities-and-society/scs230008?id=journal-of-smart-cities-and-society%2Fscs230008","source":{"id":"https://openalex.org/S4220651211","display_name":"Journal of Smart Cities and Society","issn_l":"2772-3577","issn":["2772-3577","2772-3585"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Smart Cities and Society","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4387494240.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W213987438","https://openalex.org/W1537066827","https://openalex.org/W1610496399","https://openalex.org/W1978239142","https://openalex.org/W2122646361","https://openalex.org/W2157564217","https://openalex.org/W2160197181","https://openalex.org/W2296719434","https://openalex.org/W2410531948","https://openalex.org/W2498771658","https://openalex.org/W2542372770","https://openalex.org/W2564294811","https://openalex.org/W2731977498","https://openalex.org/W2783436543","https://openalex.org/W2953557668","https://openalex.org/W2966559104","https://openalex.org/W2997590552","https://openalex.org/W3120441567","https://openalex.org/W3140288472","https://openalex.org/W3173842246","https://openalex.org/W4200619082","https://openalex.org/W4254182148","https://openalex.org/W4256141317","https://openalex.org/W6600474023","https://openalex.org/W6636177537","https://openalex.org/W7005509396"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2499612753","https://openalex.org/W3111802945","https://openalex.org/W2946096271","https://openalex.org/W2295423552","https://openalex.org/W3107369729","https://openalex.org/W2177870719","https://openalex.org/W4238158008","https://openalex.org/W2965606979"],"abstract_inverted_index":{"Data":[0],"cleaning,":[1,151],"also":[2],"referred":[3],"to":[4,16,23,56,60,64,96,136,144,193],"as":[5],"data":[6,13,17,40,54,61,73,150,174,197],"cleansing,":[7],"constitutes":[8],"a":[9],"pivotal":[10],"phase":[11],"in":[12,203],"processing":[14,175],"subsequent":[15],"collection.":[18],"Its":[19],"primary":[20],"objective":[21,171],"is":[22,50],"identify":[24,97],"and":[25,35,75,122,176,187,199],"eliminate":[26],"incomplete":[27],"data,":[28],"duplicates,":[29],"outdated":[30],"information,":[31],"anomalies,":[32],"missing":[33],"values,":[34],"errors.":[36],"The":[37],"influence":[38],"of":[39,45,72,78,88,107,119,129,149,163,172,182,196,206],"quality":[41],"on":[42,116],"the":[43,76,86,105,117,127,146,169,180,194,204],"effectiveness":[44],"machine":[46],"learning":[47],"(ML)":[48],"models":[49],"widely":[51],"acknowledged,":[52],"prompting":[53],"scientists":[55],"dedicate":[57],"substantial":[58],"effort":[59],"cleaning":[62,74,198],"prior":[63],"model":[65],"training.":[66],"This":[67,141],"study":[68,191],"accentuates":[69],"critical":[70],"facets":[71],"utilization":[77],"outlier":[79,90,138,164,200],"detection":[80,91,139,165,201],"algorithms.":[81],"Additionally,":[82],"our":[83,108,161],"investigation":[84],"encompasses":[85],"evaluation":[87],"prominent":[89],"algorithms":[92],"through":[93],"benchmarking,":[94],"seeking":[95],"an":[98,112],"efficient":[99],"algorithm":[100,114,134],"boasting":[101],"consistent":[102],"performance.":[103],"As":[104],"culmination":[106],"research,":[109],"we":[110],"introduce":[111],"innovative":[113,188],"centered":[115],"fusion":[118],"Isolation":[120],"Forest":[121],"clustering":[123],"techniques.":[124],"By":[125],"leveraging":[126],"strengths":[128],"both":[130],"methods,":[131],"this":[132,190],"proposed":[133],"aims":[135],"enhance":[137],"outcomes.":[140],"work":[142],"endeavors":[143],"elucidate":[145],"multifaceted":[147],"importance":[148],"underscored":[152],"by":[153],"its":[154],"symbiotic":[155],"relationship":[156],"with":[157,168],"ML":[158],"models.":[159],"Furthermore,":[160],"exploration":[162],"methodologies":[166],"aligns":[167],"broader":[170],"refining":[173],"analysis":[177],"paradigms.":[178],"Through":[179],"convergence":[181],"theoretical":[183],"insights,":[184],"algorithmic":[185],"exploration,":[186],"proposals,":[189],"contributes":[192],"advancement":[195],"techniques":[202],"realm":[205],"contemporary":[207],"data-driven":[208],"environments.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
