{"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":"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/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":false,"raw_author_name":"Kushankur Ghosh","raw_affiliation_strings":["University of Alberta,Department of Computing Science,Edmonton,Canada"],"raw_orcid":null,"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 São Carlos,Department of Computing Science,São Paulo,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of São Carlos,Department of Computing Science,São 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"],"raw_orcid":null,"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"],"raw_orcid":null,"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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8448,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.92943786,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"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","display_name":"Climate action","score":0.4000000059604645}],"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":[0,159],"machine":[1],"learning":[2],"and":[3,16,28,155,213,234],"data":[4,8,73],"mining,":[5],"outliers":[6,37,146,191,215],"are":[7,33],"points":[9,210],"that":[10,21,99,226,236],"significantly":[11],"differ":[12],"from":[13,192],"the":[14,80,84,89,107,124,132,143,169,173,182,193,196,217,232,238],"dataset":[15,149],"often":[17,157],"introduce":[18],"irrelevant":[19],"information":[20,44],"can":[22,188,229],"induce":[23],"bias":[24],"in":[25,88,131],"its":[26,77],"statistics":[27],"models.":[29],"Therefore,":[30],"unsupervised":[31,56,165,202],"methods":[32],"crucial":[34],"to":[35,79,96,141,167,180,204,219],"detect":[36],"if":[38],"there":[39],"is":[40,54,114,156],"limited":[41,104],"or":[42,118,240],"no":[43],"about":[45,106],"them.":[46],"Global-Local":[47],"Outlier":[48],"Scores":[49],"based":[50],"on":[51],"Hierarchies":[52],"(GLOSH)":[53],"an":[55,110,164,201],"outlier":[57,69,243],"detection":[58,244],"method":[59],"within":[60],"HDBSCAN*,":[61],"a":[62,148,206],"state-of-the-art":[63],"hierarchical":[64],"clustering":[65],"method.":[66],"GLOSH":[67,92,176,186],"estimates":[68],"scores":[70,177,187],"for":[71,136,184,208],"each":[72],"point":[74],"by":[75],"comparing":[76],"density":[78,82,101],"highest":[81],"of":[83,134,145,175,195],"region":[85],"they":[86],"reside":[87],"HDBSCAN*":[90],"hierarchy.":[91],"may":[93,121,152],"be":[94,153],"sensitive":[95],"HDBSCAN*\u2019s":[97],"minptsparameter":[98],"influences":[100],"estimation.":[102],"With":[103],"knowledge":[105],"data,":[108],"choosing":[109],"appropriate":[111],"minptsvalue":[112,233],"beforehand":[113],"challenging":[115],"as":[116],"one":[117,139],"some":[119],"minptsvalues":[120,179],"better":[122],"represent":[123],"underlying":[125],"cluster":[126],"structure":[127],"than":[128],"others.":[129],"Additionally,":[130],"process":[133],"searching":[135],"\"potential":[137],"outliers\",":[138],"has":[140],"define":[142],"number":[144],"n":[147],"has,":[150],"which":[151,185],"impractical":[154],"unknown.":[158],"this":[160],"paper,":[161],"we":[162,199],"propose":[163,200],"strategy":[166,203],"find":[168,231],"\"best\"":[170],"minptsvalue,":[171],"leveraging":[172],"range":[174],"across":[178],"identify":[181,190],"value":[183],"best":[189,239,242],"rest":[194],"dataset.":[197],"Moreover,":[198],"estimate":[205],"threshold":[207,235],"classifying":[209],"into":[211],"inliers":[212],"(potential)":[214],"without":[216],"need":[218],"pre-define":[220],"any":[221],"value.":[222],"Our":[223],"experiments":[224],"show":[225],"our":[227],"strategies":[228],"automatically":[230],"yield":[237],"near":[241],"results":[245],"using":[246],"GLOSH.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}