{"id":"https://openalex.org/W2129312546","doi":"https://doi.org/10.1109/ijcnn.2008.4634266","title":"Fast parallel outlier detection for categorical datasets using MapReduce","display_name":"Fast parallel outlier detection for categorical datasets using MapReduce","publication_year":2008,"publication_date":"2008-06-01","ids":{"openalex":"https://openalex.org/W2129312546","doi":"https://doi.org/10.1109/ijcnn.2008.4634266","mag":"2129312546"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2008.4634266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2008.4634266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://stars.library.ucf.edu/scopus2000/9704","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035774745","display_name":"Anna Koufakou","orcid":"https://orcid.org/0000-0002-0295-3759"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anna Koufakou","raw_affiliation_strings":["School of EECS, University of Central Florida, Orlando, FL, USA","School of EECS, University of Central Florida, Orlando, FL"],"affiliations":[{"raw_affiliation_string":"School of EECS, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"School of EECS, University of Central Florida, Orlando, FL","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088123853","display_name":"Jimmy Secretan","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jimmy Secretan","raw_affiliation_strings":["School of EECS, University of Central Florida, Orlando, FL, USA","School of EECS, University of Central Florida, Orlando, FL"],"affiliations":[{"raw_affiliation_string":"School of EECS, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"School of EECS, University of Central Florida, Orlando, FL","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084134254","display_name":"John Reeder","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Reeder","raw_affiliation_strings":["School of EECS, University of Central Florida, Orlando, FL, USA","School of EECS, University of Central Florida, Orlando, FL"],"affiliations":[{"raw_affiliation_string":"School of EECS, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"School of EECS, University of Central Florida, Orlando, FL","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097510802","display_name":"Kelvin Cardona","orcid":null},"institutions":[{"id":"https://openalex.org/I200399037","display_name":"University of Puerto Rico System","ror":"https://ror.org/02yg0nm07","country_code":"PR","type":"education","lineage":["https://openalex.org/I200399037"]}],"countries":["PR"],"is_corresponding":false,"raw_author_name":"Kelvin Cardona","raw_affiliation_strings":["Department of Computer Engineering, University of Puerto Rico, Puerto Rico","Dept. of Comput. Eng., Univ. of Puerto Rico, Rico"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, University of Puerto Rico, Puerto Rico","institution_ids":["https://openalex.org/I200399037"]},{"raw_affiliation_string":"Dept. of Comput. Eng., Univ. of Puerto Rico, Rico","institution_ids":["https://openalex.org/I200399037"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036799400","display_name":"Michael Georgiopoulos","orcid":"https://orcid.org/0009-0002-8840-0123"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Georgiopoulos","raw_affiliation_strings":["School of EECS, University of Central Florida, Orlando, FL, USA","School of EECS, University of Central Florida, Orlando, FL"],"affiliations":[{"raw_affiliation_string":"School of EECS, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"School of EECS, University of Central Florida, Orlando, FL","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5035774745"],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":1.1708,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.85069415,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"17","issue":null,"first_page":"3298","last_page":"3304"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":1.0,"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":1.0,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.991599977016449,"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":0.9810000061988831,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.8449194431304932},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8377047777175903},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7680471539497375},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.7028470039367676},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6880884170532227},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5431316494941711},{"id":"https://openalex.org/keywords/credit-card-fraud","display_name":"Credit card fraud","score":0.5429112911224365},{"id":"https://openalex.org/keywords/parallelizable-manifold","display_name":"Parallelizable manifold","score":0.5314245223999023},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34697508811950684},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3376578688621521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33375659584999084},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2434729039669037},{"id":"https://openalex.org/keywords/credit-card","display_name":"Credit card","score":0.21436551213264465},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19211998581886292},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10754764080047607}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.8449194431304932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8377047777175903},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7680471539497375},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7028470039367676},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6880884170532227},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5431316494941711},{"id":"https://openalex.org/C2780747020","wikidata":"https://www.wikidata.org/wiki/Q83873","display_name":"Credit card fraud","level":4,"score":0.5429112911224365},{"id":"https://openalex.org/C148047603","wikidata":"https://www.wikidata.org/wiki/Q1014612","display_name":"Parallelizable manifold","level":2,"score":0.5314245223999023},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34697508811950684},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3376578688621521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33375659584999084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2434729039669037},{"id":"https://openalex.org/C2983355114","wikidata":"https://www.wikidata.org/wiki/Q161380","display_name":"Credit card","level":3,"score":0.21436551213264465},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19211998581886292},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10754764080047607},{"id":"https://openalex.org/C145097563","wikidata":"https://www.wikidata.org/wiki/Q1148747","display_name":"Payment","level":2,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn.2008.4634266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2008.4634266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)","raw_type":"proceedings-article"},{"id":"pmh:oai:stars.library.ucf.edu:scopus2000-10703","is_oa":true,"landing_page_url":"https://stars.library.ucf.edu/scopus2000/9704","pdf_url":null,"source":{"id":"https://openalex.org/S4210172555","display_name":"Journal of International Crisis and Risk Communication Research","issn_l":"2576-0017","issn":["2576-0017","2576-0025"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus Export 2000s","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:stars.library.ucf.edu:scopus2000-10703","is_oa":true,"landing_page_url":"https://stars.library.ucf.edu/scopus2000/9704","pdf_url":null,"source":{"id":"https://openalex.org/S4210172555","display_name":"Journal of International Crisis and Risk Communication Research","issn_l":"2576-0017","issn":["2576-0017","2576-0025"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus Export 2000s","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1481707143","https://openalex.org/W1484413656","https://openalex.org/W1602011302","https://openalex.org/W1876967670","https://openalex.org/W1944649467","https://openalex.org/W1966147156","https://openalex.org/W1970088130","https://openalex.org/W2061240327","https://openalex.org/W2079557269","https://openalex.org/W2101277490","https://openalex.org/W2105045879","https://openalex.org/W2109722477","https://openalex.org/W2110784166","https://openalex.org/W2117891917","https://openalex.org/W2119565742","https://openalex.org/W2124536999","https://openalex.org/W2137130182","https://openalex.org/W2144182447","https://openalex.org/W2169217090","https://openalex.org/W2173213060","https://openalex.org/W3120740533","https://openalex.org/W4238722012","https://openalex.org/W4239670432","https://openalex.org/W4240428965","https://openalex.org/W4254182148","https://openalex.org/W4285719527","https://openalex.org/W4300363951","https://openalex.org/W6628750762","https://openalex.org/W6640853137","https://openalex.org/W6676367512"],"related_works":["https://openalex.org/W4285069850","https://openalex.org/W1974634278","https://openalex.org/W4240963716","https://openalex.org/W2499612753","https://openalex.org/W3111802945","https://openalex.org/W2122407924","https://openalex.org/W2564294811","https://openalex.org/W2946096271","https://openalex.org/W2295423552","https://openalex.org/W3107369729"],"abstract_inverted_index":{"Outlier":[0],"detection":[1,30,40,45,91,105],"has":[2],"received":[3],"considerable":[4],"attention":[5],"in":[6,25,71],"many":[7],"applications,":[8],"such":[9],"as":[10],"detecting":[11],"network":[12],"attacks":[13],"or":[14],"credit":[15],"card":[16],"fraud":[17],"The":[18],"massive":[19],"datasets":[20],"currently":[21],"available":[22],"for":[23,107,126],"mining":[24],"some":[26],"of":[27,50,53,69,155],"these":[28],"outlier":[29,39,44,90,104],"applications":[31],"require":[32,78],"large":[33],"parallel":[34,89,127],"systems,":[35],"and":[36,74,133,142],"consequently":[37],"parallelizable":[38],"methods.":[41],"Most":[42],"existing":[43],"methods":[46],"assume":[47],"that":[48,110],"all":[49],"the":[51,67,72,95,123,153],"attributes":[52],"a":[54,60,87,101],"dataset":[55,80],"are":[56],"numerical,":[57],"usually":[58],"have":[59],"quadratic":[61],"time":[62],"complexity":[63],"with":[64,150],"respect":[65,151],"to":[66,114,140,146,152],"number":[68,154],"points":[70],"dataset,":[73],"quite":[75],"often":[76],"they":[77],"multiple":[79],"scans.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85],"propose":[86],"fast":[88],"strategy":[92],"based":[93,121],"on":[94,122],"Attribute":[96],"Value":[97],"Frequency":[98],"(AVF)":[99],"approach,":[100],"high-speed,":[102],"scalable":[103,149],"method":[106],"categorical":[108],"data":[109],"is":[111,120,137,144],"inherently":[112],"easy":[113],"parallelize.":[115],"Our":[116],"proposed":[117],"solution,":[118],"MR-AVF,":[119],"MapReduce":[124],"paradigm":[125],"programming,":[128],"which":[129],"offers":[130],"load":[131],"balancing":[132],"fault":[134],"tolerance.":[135],"MR-AVF":[136],"particularly":[138],"simple":[139],"develop":[141],"it":[143],"shown":[145],"be":[147],"highly":[148],"cluster":[156],"nodes.":[157]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}