{"id":"https://openalex.org/W2014082967","doi":"https://doi.org/10.1109/iri.2010.5558968","title":"Evaluating the impact of data quality on sampling","display_name":"Evaluating the impact of data quality on sampling","publication_year":2010,"publication_date":"2010-08-01","ids":{"openalex":"https://openalex.org/W2014082967","doi":"https://doi.org/10.1109/iri.2010.5558968","mag":"2014082967"},"language":"en","primary_location":{"id":"doi:10.1109/iri.2010.5558968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iri.2010.5558968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Information Reuse & Integration","raw_type":"proceedings-article"},"type":"conference-paper","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/A5111933705","display_name":"Jason Van Hulse","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Van Hulse","raw_affiliation_strings":["Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, USA","Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, 777 Glades Rd., Boca Raton, 33431, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, USA","institution_ids":["https://openalex.org/I63772739"]},{"raw_affiliation_string":"Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, 777 Glades Rd., Boca Raton, 33431, USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089170562","display_name":"Taghi M. Khoshgoftaar","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taghi M. Khoshgoftaar","raw_affiliation_strings":["Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, USA","Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, 777 Glades Rd., Boca Raton, 33431, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, USA","institution_ids":["https://openalex.org/I63772739"]},{"raw_affiliation_string":"Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, 777 Glades Rd., Boca Raton, 33431, USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090913753","display_name":"Amri Napolitano","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amri Napolitano","raw_affiliation_strings":["Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, USA","Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, 777 Glades Rd., Boca Raton, 33431, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, USA","institution_ids":["https://openalex.org/I63772739"]},{"raw_affiliation_string":"Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, 777 Glades Rd., Boca Raton, 33431, USA","institution_ids":["https://openalex.org/I63772739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63772739"],"apc_list":null,"apc_paid":null,"fwci":1.0899,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.76847726,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"11","issue":null,"first_page":"31","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9983000159263611,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9760000109672546,"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/computer-science","display_name":"Computer science","score":0.7901543378829956},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.7514775395393372},{"id":"https://openalex.org/keywords/data-sampling","display_name":"Data sampling","score":0.627720832824707},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6056949496269226},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5857976078987122},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5693520903587341},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5254004597663879},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4781450033187866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38666418194770813},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0748780369758606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7901543378829956},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.7514775395393372},{"id":"https://openalex.org/C2985946229","wikidata":"https://www.wikidata.org/wiki/Q49908","display_name":"Data sampling","level":2,"score":0.627720832824707},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6056949496269226},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5857976078987122},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5693520903587341},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5254004597663879},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4781450033187866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38666418194770813},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0748780369758606},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iri.2010.5558968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iri.2010.5558968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Information Reuse & Integration","raw_type":"proceedings-article"},{"id":"pmh:oai:RePEc:wsi:jikmxx:v:10:y:2011:i:03:p:225-245","is_oa":false,"landing_page_url":"http://www.worldscinet.com/cgi-bin/details.cgi?type=html&id=pii:S021964921100295X","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W18055459","https://openalex.org/W41502859","https://openalex.org/W1496447628","https://openalex.org/W1499593655","https://openalex.org/W1563601573","https://openalex.org/W1564764609","https://openalex.org/W1570448133","https://openalex.org/W1666942233","https://openalex.org/W1941659294","https://openalex.org/W1965895350","https://openalex.org/W1992795012","https://openalex.org/W2034841618","https://openalex.org/W2107686700","https://openalex.org/W2119168155","https://openalex.org/W2132656721","https://openalex.org/W2136903812","https://openalex.org/W2140187489","https://openalex.org/W2145384715","https://openalex.org/W2145899855","https://openalex.org/W2148143831","https://openalex.org/W3100570787","https://openalex.org/W3120740533","https://openalex.org/W4243610423","https://openalex.org/W6601696430","https://openalex.org/W6633851176","https://openalex.org/W6633899822","https://openalex.org/W6680202767","https://openalex.org/W6788247690"],"related_works":["https://openalex.org/W4231704780","https://openalex.org/W2368644753","https://openalex.org/W2367538773","https://openalex.org/W2075654366","https://openalex.org/W1999758163","https://openalex.org/W2059188306","https://openalex.org/W2092657059","https://openalex.org/W4387539107","https://openalex.org/W4283326678","https://openalex.org/W4376254451"],"abstract_inverted_index":{"Three":[0],"important":[1],"data":[2,9,16,37,52,56,73,100,130,160],"characteristics":[3,150],"that":[4,129],"can":[5,132],"substantially":[6],"impact":[7,155],"a":[8,28,67],"mining":[10],"project":[11],"are":[12,110,163],"class":[13,86],"imbalance,":[14],"poor":[15],"quality":[17],"and":[18,60,90,126,144],"the":[19,22,49,95,139,148,153,159],"size":[20],"of":[21,51,71,97,116,142,158],"training":[23,81],"dataset.":[24],"Data":[25],"sampling":[26,53,74,101,131,161],"is":[27,38,57],"commonly":[29],"used":[30],"method":[31],"for":[32,118],"improving":[33],"learner":[34],"performance":[35,50,96],"when":[36,55],"imbalanced.":[39,61],"However,":[40],"little":[41],"effort":[42],"has":[43],"been":[44],"put":[45],"forth":[46],"to":[47,77],"investigate":[48],"techniques":[54,75,102,162],"both":[58],"noisy":[59],"In":[62,146],"this":[63],"work,":[64],"we":[65],"present":[66,94],"comprehensive":[68],"empirical":[69],"investigation":[70],"how":[72],"react":[76],"changes":[78],"in":[79],"four":[80,98],"dataset":[82,84,149],"characteristics:":[83],"size,":[85],"distribution,":[87],"noise":[88,91,143],"level":[89],"distribution.":[92],"We":[93],"common":[99],"using":[103],"11":[104],"learning":[105],"algorithms.":[106],"The":[107],"results,":[108],"which":[109,119,151],"based":[111],"on":[112,156],"an":[113],"extensive":[114],"suite":[115],"experiments":[117],"over":[120],"15":[121],"million":[122],"models":[123],"were":[124],"trained":[125],"evaluated,":[127],"show":[128],"be":[133],"very":[134],"effective":[135],"at":[136],"dealing":[137],"with":[138],"combined":[140],"problems":[141],"imbalance.":[145],"addition,":[147],"have":[152],"greatest":[154],"each":[157],"identified.":[164]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}