{"id":"https://openalex.org/W1506073843","doi":"https://doi.org/10.1109/icdm.2003.1250912","title":"Probabilistic noise identification and data cleaning","display_name":"Probabilistic noise identification and data cleaning","publication_year":2004,"publication_date":"2004-03-30","ids":{"openalex":"https://openalex.org/W1506073843","doi":"https://doi.org/10.1109/icdm.2003.1250912","mag":"1506073843"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2003.1250912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1250912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE International Conference on Data Mining","raw_type":"proceedings-article"},"type":"article","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/A5042115859","display_name":"Jeremy Kubica","orcid":"https://orcid.org/0009-0009-2281-7031"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Kubica","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Robotics Institute, Carnegie Mellon University,Pittsburgh,PA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101927521","display_name":"Andrew Moore","orcid":"https://orcid.org/0000-0002-3395-0841"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Moore","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.327,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.97326233,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"131","last_page":"138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9939000010490417,"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":0.9939000010490417,"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/T11443","display_name":"Advanced Statistical Process Monitoring","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"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/T11871","display_name":"Advanced Statistical Methods and Models","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6739262342453003},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6344296336174011},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6192370057106018},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5695464015007019},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4362291693687439},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3387529253959656},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1674031913280487}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6739262342453003},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6344296336174011},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6192370057106018},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5695464015007019},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4362291693687439},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3387529253959656},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1674031913280487},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icdm.2003.1250912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1250912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE International Conference on Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.10.6096","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.6096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.autonlab.org/autonweb/documents/papers/kubicaLENS.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.70.944","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.70.944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ri.cmu.edu/pub_files/pub4/kubica_jeremy_martin_2003_4/kubica_jeremy_martin_2003_4.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.71.4154","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.4154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ri.cmu.edu/pub_files/pub3/kubica_jeremy_martin_2002_1/kubica_jeremy_martin_2002_1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.8.5557","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.8.5557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://robotweb.ri.cmu.edu/pub_files/pub3/kubica_jeremy_martin_2002_1/kubica_jeremy_martin_2002_1.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.89.8609","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.89.8609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~jkubica/papers/LENS_ICDM.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W41502859","https://openalex.org/W123339444","https://openalex.org/W214562933","https://openalex.org/W1504360465","https://openalex.org/W1524704912","https://openalex.org/W1556344493","https://openalex.org/W1564764609","https://openalex.org/W1591052160","https://openalex.org/W1861600621","https://openalex.org/W2012712694","https://openalex.org/W2084812512","https://openalex.org/W2128221272","https://openalex.org/W2168793898","https://openalex.org/W2172162418"],"related_works":["https://openalex.org/W2327107878","https://openalex.org/W2171117985","https://openalex.org/W2012356576","https://openalex.org/W1526760723","https://openalex.org/W2126659863","https://openalex.org/W3112120395","https://openalex.org/W4385670989","https://openalex.org/W2102487628","https://openalex.org/W2436588531","https://openalex.org/W2009680848"],"abstract_inverted_index":{"Real":[0],"world":[1],"data":[2,67,95],"is":[3,44],"never":[4],"as":[5,7,148],"perfect":[6],"we":[8],"would":[9],"like":[10],"it":[11],"to":[12,41,45,96,157],"be":[13,69],"and":[14,32,47,80,89,118,137],"can":[15],"often":[16],"suffer":[17],"from":[18,29],"corruptions":[19],"that":[20,50],"may":[21],"impact":[22],"interpretations":[23],"of":[24,107,114,122,134],"the":[25,30,37,82,94,108,115,123,131,152],"data,":[26,31],"models":[27,136],"created":[28],"decisions":[33],"made":[34],"based":[35],"on":[36],"data.":[38],"One":[39],"approach":[40,75,92],"this":[42,155],"problem":[43],"identify":[46],"remove":[48],"records":[49],"contain":[51],"corruptions.":[52],"Unfortunately,":[53],"if":[54],"only":[55],"certain":[56],"fields":[57,79,85,146],"in":[58],"a":[59,98,104,111,119,158],"record":[60],"have":[61],"been":[62],"corrupted":[63,78,145],"then":[64],"usable,":[65],"uncorrupted":[66],"will":[68],"lost.":[70],"We":[71,126],"present":[72],"LENS,":[73],"an":[74,128],"for":[76,86,130],"identifying":[77],"using":[81],"remaining":[83],"noncorrupted":[84],"subsequent":[87],"modeling":[88],"analysis.":[90],"Our":[91],"uses":[93],"learn":[97],"probabilistic":[99,120],"model":[100,106,113,121],"containing":[101],"three":[102],"components:":[103],"generative":[105,112],"clean":[109],"records,":[110],"noise":[116],"values,":[117],"corruption":[124],"process.":[125],"provide":[127],"algorithm":[129],"unsupervised":[132],"discovery":[133],"such":[135],"empirically":[138],"evaluate":[139],"both":[140],"its":[141],"performance":[142],"at":[143],"detecting":[144],"and,":[147],"one":[149],"example":[150],"application,":[151],"resulting":[153],"improvement":[154],"gives":[156],"classifier.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}