{"id":"https://openalex.org/W4406461799","doi":"https://doi.org/10.1109/bigdata62323.2024.10825917","title":"Unsupervised Parameter-free Outlier Detection using HDBSCAN* Outlier Profiles","display_name":"Unsupervised Parameter-free Outlier Detection using HDBSCAN* Outlier Profiles","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406461799","doi":"https://doi.org/10.1109/bigdata62323.2024.10825917"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5066873115","display_name":"Kushankur Ghosh","orcid":"https://orcid.org/0000-0002-4761-120X"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Kushankur Ghosh","raw_affiliation_strings":["University of Alberta,Department of Computing Science,Edmonton,Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta,Department of Computing Science,Edmonton,Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081258813","display_name":"Murilo Coelho Naldi","orcid":"https://orcid.org/0000-0002-3107-8236"},"institutions":[{"id":"https://openalex.org/I177909021","display_name":"Universidade Federal de S\u00e3o Carlos","ror":"https://ror.org/00qdc6m37","country_code":"BR","type":"education","lineage":["https://openalex.org/I177909021"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Murilo Coelho Naldi","raw_affiliation_strings":["Federal University of S&#x00E3;o Carlos,Department of Computing Science,S&#x00E3;o Paulo,Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of S&#x00E3;o Carlos,Department of Computing Science,S&#x00E3;o Paulo,Brazil","institution_ids":["https://openalex.org/I177909021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021763337","display_name":"J\u00f6rg Sander","orcid":"https://orcid.org/0000-0003-4068-7268"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"J\u00f6rg Sander","raw_affiliation_strings":["University of Alberta,Department of Computing Science,Edmonton,Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta,Department of Computing Science,Edmonton,Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029121563","display_name":"Euijin Choo","orcid":"https://orcid.org/0000-0002-0055-050X"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Euijin Choo","raw_affiliation_strings":["University of Alberta,Department of Computing Science,Edmonton,Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta,Department of Computing Science,Edmonton,Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5066873115"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":2.9132,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.9239029,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7021","last_page":"7030"},"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/T10876","display_name":"Fault Detection and Control Systems","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9803000092506409,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/anomaly-detection","display_name":"Anomaly detection","score":0.7831218838691711},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.7547780275344849},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6509469747543335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5939372777938843},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5000405311584473}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7831218838691711},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.7547780275344849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6509469747543335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5939372777938843},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5000405311584473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.4000000059604645,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1585398001","https://openalex.org/W1673310716","https://openalex.org/W1967158716","https://openalex.org/W1986332411","https://openalex.org/W1992276041","https://openalex.org/W2049058890","https://openalex.org/W2079040080","https://openalex.org/W2160642098","https://openalex.org/W2180566385","https://openalex.org/W2249382963","https://openalex.org/W2804148081","https://openalex.org/W2910187721","https://openalex.org/W2923023146","https://openalex.org/W2947133089","https://openalex.org/W2998391271","https://openalex.org/W3007971687","https://openalex.org/W3017320328","https://openalex.org/W3039137796","https://openalex.org/W3128465814","https://openalex.org/W3153838899","https://openalex.org/W3190213853","https://openalex.org/W3212272194","https://openalex.org/W4206454995","https://openalex.org/W4247927186","https://openalex.org/W4253461361","https://openalex.org/W4254182148","https://openalex.org/W4285005306","https://openalex.org/W4289533744","https://openalex.org/W4312423502","https://openalex.org/W4312433903","https://openalex.org/W4353069336","https://openalex.org/W4376956106","https://openalex.org/W4386768901","https://openalex.org/W4393592775","https://openalex.org/W6637131181","https://openalex.org/W6678723600","https://openalex.org/W6766603212","https://openalex.org/W6803011850","https://openalex.org/W6803693056"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2499612753","https://openalex.org/W3111802945","https://openalex.org/W2946096271","https://openalex.org/W2295423552","https://openalex.org/W1598471830","https://openalex.org/W3107369729","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"In":[0,168],"machine":[1],"learning":[2],"and":[3,16,28,164,228,252],"data":[4,8,73],"mining,":[5],"outliers":[6,37,155,206,230],"are":[7,33],"points":[9,225],"that":[10,21,102,241,254],"significantly":[11],"differ":[12],"from":[13,207],"the":[14,80,84,89,110,133,141,152,178,185,197,208,211,232,247,256],"dataset":[15,158],"often":[17,166],"introduce":[18],"irrelevant":[19],"information":[20,44],"can":[22,203,244],"induce":[23],"bias":[24],"in":[25,88,140],"its":[26,77],"statistics":[27],"models.":[29],"Therefore,":[30],"unsupervised":[31,56,174,217],"methods":[32],"crucial":[34],"to":[35,79,96,150,176,195,219,234],"detect":[36],"if":[38],"there":[39],"is":[40,54,120,165],"limited":[41,107],"or":[42,124,258],"no":[43],"about":[45,109],"them.":[46],"Global-Local":[47],"Outlier":[48],"Scores":[49],"based":[50],"on":[51],"Hierarchies":[52],"(GLOSH)":[53],"an":[55,113,173,216],"outlier":[57,69,261],"detection":[58,262],"method":[59],"within":[60],"HDBSCAN*,":[61],"a":[62,157,221],"state-of-the-art":[63],"hierarchical":[64],"clustering":[65],"method.":[66],"GLOSH":[67,92,188,201],"estimates":[68],"scores":[70,189,202],"for":[71,145,199,223],"each":[72],"point":[74],"by":[75],"comparing":[76],"density":[78,82,104],"highest":[81],"of":[83,143,154,187,210],"region":[85],"they":[86],"reside":[87],"HDBSCAN*":[90],"hierarchy.":[91],"may":[93,130,161],"be":[94,162],"sensitive":[95],"HDBSCAN*\u2019s":[97],"min<inf":[98,115,126,180,191,248],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[99,116,127,181,192,249],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">pts</inf>":[100,117,128,182,193,250],"parameter":[101],"influences":[103],"estimation.":[105],"With":[106],"knowledge":[108],"data,":[111],"choosing":[112],"appropriate":[114],"value":[118,198,251],"beforehand":[119],"challenging":[121],"as":[122],"one":[123,148],"some":[125],"values":[129,194],"better":[131],"represent":[132],"underlying":[134],"cluster":[135],"structure":[136],"than":[137],"others.":[138],"Additionally,":[139],"process":[142],"searching":[144],"\"potential":[146],"outliers\",":[147],"has":[149],"define":[151],"number":[153],"n":[156],"has,":[159],"which":[160,200],"impractical":[163],"unknown.":[167],"this":[169],"paper,":[170],"we":[171,214],"propose":[172,215],"strategy":[175,218],"find":[177,246],"\"best\"":[179],"value,":[183],"leveraging":[184],"range":[186],"across":[190],"identify":[196,205],"best":[204,257,260],"rest":[209],"dataset.":[212],"Moreover,":[213],"estimate":[220],"threshold":[222,253],"classifying":[224],"into":[226],"inliers":[227],"(potential)":[229],"without":[231],"need":[233],"pre-define":[235],"any":[236],"value.":[237],"Our":[238],"experiments":[239],"show":[240],"our":[242],"strategies":[243],"automatically":[245],"yield":[255],"near":[259],"results":[263],"using":[264],"GLOSH.":[265]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}