{"id":"https://openalex.org/W4406458732","doi":"https://doi.org/10.1109/bigdata62323.2024.10825416","title":"The Skyline Operator to Find the Needle in the Haystack for Automated Clustering","display_name":"The Skyline Operator to Find the Needle in the Haystack for Automated Clustering","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458732","doi":"https://doi.org/10.1109/bigdata62323.2024.10825416"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825416","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825416","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/A5078660657","display_name":"Georg Stefan Schlake","orcid":"https://orcid.org/0009-0008-5714-1804"},"institutions":[{"id":"https://openalex.org/I120691247","display_name":"University of Hagen","ror":"https://ror.org/04tkkr536","country_code":"DE","type":"education","lineage":["https://openalex.org/I120691247"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Georg Stefan Schlake","raw_affiliation_strings":["University of Hagen,Hagen,Germany"],"affiliations":[{"raw_affiliation_string":"University of Hagen,Hagen,Germany","institution_ids":["https://openalex.org/I120691247"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039809923","display_name":"Christian Beecks","orcid":"https://orcid.org/0009-0000-9028-629X"},"institutions":[{"id":"https://openalex.org/I120691247","display_name":"University of Hagen","ror":"https://ror.org/04tkkr536","country_code":"DE","type":"education","lineage":["https://openalex.org/I120691247"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Beecks","raw_affiliation_strings":["University of Hagen,Hagen,Germany"],"affiliations":[{"raw_affiliation_string":"University of Hagen,Hagen,Germany","institution_ids":["https://openalex.org/I120691247"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078660657"],"corresponding_institution_ids":["https://openalex.org/I120691247"],"apc_list":null,"apc_paid":null,"fwci":0.7471,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7306848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6117","last_page":"6122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9842000007629395,"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/haystack","display_name":"Haystack","score":0.9794819355010986},{"id":"https://openalex.org/keywords/skyline","display_name":"Skyline","score":0.8599375486373901},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7364396452903748},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6613914370536804},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4623512029647827},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.42141276597976685},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3587588369846344},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3011135458946228},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25105708837509155},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09067222476005554}],"concepts":[{"id":"https://openalex.org/C13424479","wikidata":"https://www.wikidata.org/wiki/Q5687237","display_name":"Haystack","level":2,"score":0.9794819355010986},{"id":"https://openalex.org/C2780757406","wikidata":"https://www.wikidata.org/wiki/Q465837","display_name":"Skyline","level":2,"score":0.8599375486373901},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7364396452903748},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6613914370536804},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4623512029647827},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.42141276597976685},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3587588369846344},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3011135458946228},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25105708837509155},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09067222476005554},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825416","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825416","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1987971958","https://openalex.org/W2016381774","https://openalex.org/W2067191022","https://openalex.org/W2085487226","https://openalex.org/W2102539288","https://openalex.org/W2152195021","https://openalex.org/W2160642098","https://openalex.org/W2180566385","https://openalex.org/W2299467264","https://openalex.org/W2408186052","https://openalex.org/W2601243251","https://openalex.org/W2870589900","https://openalex.org/W2997591727","https://openalex.org/W3049531359","https://openalex.org/W3082761365","https://openalex.org/W3118935356","https://openalex.org/W3128386428","https://openalex.org/W3163570135","https://openalex.org/W3171188308","https://openalex.org/W4285742542","https://openalex.org/W4309705183","https://openalex.org/W4312853738","https://openalex.org/W4321242758","https://openalex.org/W4367047496","https://openalex.org/W4391093358","https://openalex.org/W4403723851","https://openalex.org/W6601034125","https://openalex.org/W6637131181","https://openalex.org/W6678914141","https://openalex.org/W6792632234"],"related_works":["https://openalex.org/W4253878822","https://openalex.org/W1965563707","https://openalex.org/W1736550718","https://openalex.org/W4210692028","https://openalex.org/W2808729870","https://openalex.org/W2479343091","https://openalex.org/W2278064783","https://openalex.org/W3174858427","https://openalex.org/W1972480475","https://openalex.org/W275553111"],"abstract_inverted_index":{"The":[0],"analysis":[1],"of":[2,18,31,56,69,92,104,140,157,177,213,226,233],"big":[3],"datasets":[4],"is":[5,23,101,207],"a":[6,25,42,89,138,175,211,217,227],"challenging":[7],"task.":[8,72],"While":[9],"many":[10,189,198],"data":[11,20,33],"scientists":[12],"are":[13,169,180],"working":[14],"in":[15,28,88,122,161],"the":[16,29,62,66,70,144,148,155,158,224,234],"field":[17,30],"supervised":[19],"analysis,":[21,34],"there":[22],"also":[24],"growing":[26],"demand":[27],"unsupervised":[32],"such":[35],"as":[36,124],"clustering.":[37],"To":[38,110],"come":[39],"up":[40],"with":[41],"solution":[43],"for":[44,49,85,182,223],"this,":[45],"multiple":[46,130,231],"AutoML":[47,133],"approaches":[48,58],"clustering":[50,71,84,123],"have":[51,95],"been":[52,96],"proposed.":[53],"However,":[54],"most":[55,149],"these":[57,106],"try":[59],"to":[60,80,114,128,136,165,173],"find":[61,174],"\"best\"":[63],"clustering,":[64],"ignoring":[65],"subjective":[67],"nature":[68],"A":[73],"domain":[74,112,183,228],"expert,":[75],"however,":[76],"might":[77],"be":[78,192,237],"able":[79],"identify":[81,115],"an":[82,120],"appropriate":[83],"his/her":[86],"application":[87],"small":[90],"set":[91],"clusterings,":[93,141,167,178],"which":[94,143,168,179],"generated,":[97],"even":[98],"if":[99],"he/she":[100],"not":[102],"capable":[103],"creating":[105],"clusterings":[107,117,131,235],"by":[108],"themselves.":[109],"enable":[111],"experts":[113],"valuable":[116,199],"without":[118],"becoming":[119],"expert":[121,229],"well,":[125],"we":[126],"propose":[127],"generate":[129],"via":[132],"processes":[134],"and":[135,172,196,230],"return":[137],"selection":[139],"from":[142],"user":[145],"can":[146,191,221,236],"select":[147],"preferred":[150],"one.":[151],"We":[152,185],"will":[153,186],"investigate":[154],"use":[156,163],"Skyline":[159],"Operator":[160],"this":[162,194],"case,":[164],"prune":[166],"likely":[170],"useless,":[171],"number":[176,212],"usable":[181],"experts.":[184],"investigate,":[187],"how":[188,197],"clusters":[190,200],"pruned":[193],"way":[195],"get":[201],"falsely":[202],"pruned.":[203],"Our":[204],"empirical":[205],"investigation":[206],"carried":[208],"out":[209],"on":[210],"synthetic":[214],"datasets,":[215],"where":[216],"known":[218,238],"ground":[219],"truth":[220],"proxy":[222],"wishes":[225],"properties":[232],"beforehand.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}