{"id":"https://openalex.org/W2810047978","doi":"https://doi.org/10.3390/sym10070248","title":"From Theory to Practice: A Data Quality Framework for Classification Tasks","display_name":"From Theory to Practice: A Data Quality Framework for Classification Tasks","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2810047978","doi":"https://doi.org/10.3390/sym10070248","mag":"2810047978"},"language":"en","primary_location":{"id":"doi:10.3390/sym10070248","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym10070248","pdf_url":"https://www.mdpi.com/2073-8994/10/7/248/pdf?version=1530441596","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"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":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/10/7/248/pdf?version=1530441596","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058031153","display_name":"David Camilo Corrales","orcid":"https://orcid.org/0000-0003-4717-3040"},"institutions":[{"id":"https://openalex.org/I152650591","display_name":"University of Cauca","ror":"https://ror.org/04fybn584","country_code":"CO","type":"education","lineage":["https://openalex.org/I152650591"]},{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["CO","ES"],"is_corresponding":true,"raw_author_name":"David Camilo Corrales","raw_affiliation_strings":["Departamento de Inform\u00e1tica, Universidad Carlos III de Madrid, Avenida de la Universidad, 30, 28911 Legan\u00e9s, Spain","Grupo de Ingenier\u00eda Telem\u00e1tica, Universidad del Cauca, Campus Tulc\u00e1n, 190002 Popay\u00e1n, Colombia"],"affiliations":[{"raw_affiliation_string":"Departamento de Inform\u00e1tica, Universidad Carlos III de Madrid, Avenida de la Universidad, 30, 28911 Legan\u00e9s, Spain","institution_ids":["https://openalex.org/I50357001"]},{"raw_affiliation_string":"Grupo de Ingenier\u00eda Telem\u00e1tica, Universidad del Cauca, Campus Tulc\u00e1n, 190002 Popay\u00e1n, Colombia","institution_ids":["https://openalex.org/I152650591"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059348719","display_name":"Agapito Ledezma","orcid":"https://orcid.org/0000-0002-0041-6829"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Agapito Ledezma","raw_affiliation_strings":["Departamento de Inform\u00e1tica, Universidad Carlos III de Madrid, Avenida de la Universidad, 30, 28911 Legan\u00e9s, Spain"],"affiliations":[{"raw_affiliation_string":"Departamento de Inform\u00e1tica, Universidad Carlos III de Madrid, Avenida de la Universidad, 30, 28911 Legan\u00e9s, Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084306663","display_name":"Juan Carlos Corrales","orcid":"https://orcid.org/0000-0002-5608-9097"},"institutions":[{"id":"https://openalex.org/I152650591","display_name":"University of Cauca","ror":"https://ror.org/04fybn584","country_code":"CO","type":"education","lineage":["https://openalex.org/I152650591"]}],"countries":["CO"],"is_corresponding":false,"raw_author_name":"Juan Carlos Corrales","raw_affiliation_strings":["Grupo de Ingenier\u00eda Telem\u00e1tica, Universidad del Cauca, Campus Tulc\u00e1n, 190002 Popay\u00e1n, Colombia"],"affiliations":[{"raw_affiliation_string":"Grupo de Ingenier\u00eda Telem\u00e1tica, Universidad del Cauca, Campus Tulc\u00e1n, 190002 Popay\u00e1n, Colombia","institution_ids":["https://openalex.org/I152650591"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5058031153"],"corresponding_institution_ids":["https://openalex.org/I152650591","https://openalex.org/I50357001"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":2.8609,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.91101914,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"10","issue":"7","first_page":"248","last_page":"248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9724000096321106,"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":0.8257216811180115},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.7049946784973145},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6821781396865845},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5745705366134644},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5160341262817383},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.5152690410614014},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.4689561724662781},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4561033844947815},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4492557644844055},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44798097014427185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3836223781108856}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8257216811180115},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.7049946784973145},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6821781396865845},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5745705366134644},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5160341262817383},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.5152690410614014},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.4689561724662781},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4561033844947815},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4492557644844055},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44798097014427185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3836223781108856},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/sym10070248","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym10070248","pdf_url":"https://www.mdpi.com/2073-8994/10/7/248/pdf?version=1530441596","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"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":"Symmetry","raw_type":"journal-article"},{"id":"pmh:oai:dnet:earchivo____::369ba80ac22379fc9515c8552801f38b","is_oa":true,"landing_page_url":"http://hdl.handle.net/10016/28040","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:8f79e51c63d74010a6e57c93ddfeda16","is_oa":true,"landing_page_url":"https://doaj.org/article/8f79e51c63d74010a6e57c93ddfeda16","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry, Vol 10, Iss 7, p 248 (2018)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2073-8994/10/7/248/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/sym10070248","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Symmetry","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/sym10070248","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym10070248","pdf_url":"https://www.mdpi.com/2073-8994/10/7/248/pdf?version=1530441596","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"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":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2810047978.pdf","grobid_xml":"https://content.openalex.org/works/W2810047978.grobid-xml"},"referenced_works_count":109,"referenced_works":["https://openalex.org/W7960851","https://openalex.org/W91659207","https://openalex.org/W114024208","https://openalex.org/W403203070","https://openalex.org/W571200655","https://openalex.org/W935072310","https://openalex.org/W1491282455","https://openalex.org/W1494072001","https://openalex.org/W1497617446","https://openalex.org/W1563421732","https://openalex.org/W1567491469","https://openalex.org/W1673310716","https://openalex.org/W1736726159","https://openalex.org/W1741321747","https://openalex.org/W1831050183","https://openalex.org/W1949265207","https://openalex.org/W1969761972","https://openalex.org/W1978239142","https://openalex.org/W1978901130","https://openalex.org/W1979205968","https://openalex.org/W1979719735","https://openalex.org/W1979900513","https://openalex.org/W1986332411","https://openalex.org/W1986525510","https://openalex.org/W1988988036","https://openalex.org/W2022799139","https://openalex.org/W2029470356","https://openalex.org/W2037035119","https://openalex.org/W2039015671","https://openalex.org/W2040884411","https://openalex.org/W2049058890","https://openalex.org/W2053345242","https://openalex.org/W2055836025","https://openalex.org/W2056356749","https://openalex.org/W2063598276","https://openalex.org/W2066225277","https://openalex.org/W2070896531","https://openalex.org/W2071114814","https://openalex.org/W2074166357","https://openalex.org/W2080137107","https://openalex.org/W2085988980","https://openalex.org/W2087016914","https://openalex.org/W2105736812","https://openalex.org/W2118978333","https://openalex.org/W2122646361","https://openalex.org/W2122777273","https://openalex.org/W2124316743","https://openalex.org/W2124957697","https://openalex.org/W2127841934","https://openalex.org/W2130486630","https://openalex.org/W2133109597","https://openalex.org/W2133990480","https://openalex.org/W2135514714","https://openalex.org/W2136691316","https://openalex.org/W2139075905","https://openalex.org/W2140336868","https://openalex.org/W2144792090","https://openalex.org/W2144798162","https://openalex.org/W2150088099","https://openalex.org/W2151580670","https://openalex.org/W2151818224","https://openalex.org/W2154846261","https://openalex.org/W2157954477","https://openalex.org/W2167025863","https://openalex.org/W2167101736","https://openalex.org/W2167460663","https://openalex.org/W2182886880","https://openalex.org/W2219995598","https://openalex.org/W2245479382","https://openalex.org/W2275507448","https://openalex.org/W2285144687","https://openalex.org/W2304359685","https://openalex.org/W2319270064","https://openalex.org/W2341871588","https://openalex.org/W2346663430","https://openalex.org/W2402277527","https://openalex.org/W2472882072","https://openalex.org/W2477380177","https://openalex.org/W2500453565","https://openalex.org/W2503949733","https://openalex.org/W2509943353","https://openalex.org/W2529882916","https://openalex.org/W2547942448","https://openalex.org/W2574408556","https://openalex.org/W2574666645","https://openalex.org/W2612965162","https://openalex.org/W2736661778","https://openalex.org/W2767789061","https://openalex.org/W2795539379","https://openalex.org/W2802209325","https://openalex.org/W3104738424","https://openalex.org/W3204351626","https://openalex.org/W4237625490","https://openalex.org/W4244908355","https://openalex.org/W4247793074","https://openalex.org/W4248482966","https://openalex.org/W4254182148","https://openalex.org/W4292328707","https://openalex.org/W4321613415","https://openalex.org/W6637639269","https://openalex.org/W6638324127","https://openalex.org/W6639468679","https://openalex.org/W6679199430","https://openalex.org/W6704567128","https://openalex.org/W6728732768","https://openalex.org/W6758972637","https://openalex.org/W6785963798","https://openalex.org/W6940498297","https://openalex.org/W7053032915"],"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/W3010890513","https://openalex.org/W120741642","https://openalex.org/W2390914021","https://openalex.org/W2389417819","https://openalex.org/W138569904"],"abstract_inverted_index":{"The":[0,11],"data":[1,38,53,66,79,105,119,125],"preprocessing":[2,15,57],"is":[3,88],"an":[4,112,144],"essential":[5],"step":[6],"in":[7,55,82,107,118,168],"knowledge":[8,28,117],"discovery":[9,29],"projects.":[10],"experts":[12],"affirm":[13],"that":[14,114],"tasks":[16,84,170],"take":[17],"between":[18],"50%":[19],"to":[20,50,76,95,102,162],"70%":[21],"of":[22,26,42,64,143,151,174,184,187,191,194,201,208,219],"the":[23,27,37,43,56,62,78,97,116,123,149,155,164,172,185,192,202,206,209,217,220],"total":[24],"time":[25],"process.":[30],"In":[31,69,198],"this":[32,70],"sense,":[33],"several":[34],"authors":[35,173],"consider":[36],"cleaning":[39,120,126],"as":[40],"one":[41],"most":[44],"cumbersome":[45],"and":[46,110,121,140,176],"critical":[47],"tasks.":[48],"Failure":[49],"provide":[51,96],"high":[52],"quality":[54,80],"stage":[58],"will":[59],"significantly":[60],"reduce":[61],"accuracy":[63],"any":[65],"analytic":[67],"project.":[68],"paper,":[71],"we":[72,179],"propose":[73],"a":[74,92],"framework":[75,94],"address":[77],"issues":[81],"classification":[83,108,169],"DQF4CT.":[85],"Our":[86],"approach":[87],"composed":[89],"of:":[90],"(i)":[91],"conceptual":[93],"user":[98],"guidance":[99],"on":[100],"how":[101],"deal":[103],"with":[104],"problems":[106],"tasks;":[109],"(ii)":[111],"ontology":[113],"represents":[115],"suggests":[122],"proper":[124],"approaches.":[127],"We":[128],"presented":[129],"two":[130],"case":[131],"studies":[132],"through":[133,182],"real":[134],"datasets:":[135],"physical":[136],"activity":[137],"monitoring":[138],"(PAM)":[139],"occupancy":[141],"detection":[142],"office":[145],"room":[146],"(OD).":[147],"With":[148],"aim":[150],"evaluating":[152],"our":[153],"proposal,":[154],"cleaned":[156,211],"datasets":[157,183,210,221],"by":[158,171,205,212],"DQF4CT":[159,181,213],"were":[160],"used":[161,167],"train":[163],"same":[165],"algorithms":[166],"PAM":[175],"OD.":[177],"Additionally,":[178],"evaluated":[180],"Repository":[186],"Machine":[188],"Learning":[189],"Databases":[190],"University":[193],"California,":[195],"Irvine":[196],"(UCI).":[197],"addition,":[199],"84%":[200],"results":[203],"achieved":[204],"models":[207,218],"are":[214],"better":[215],"than":[216],"authors.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2018-07-10T00:00:00"}
