{"id":"https://openalex.org/W2954848721","doi":"https://doi.org/10.1145/3321707.3321761","title":"Evolving controllably difficult datasets for clustering","display_name":"Evolving controllably difficult datasets for clustering","publication_year":2019,"publication_date":"2019-07-03","ids":{"openalex":"https://openalex.org/W2954848721","doi":"https://doi.org/10.1145/3321707.3321761","mag":"2954848721"},"language":"en","primary_location":{"id":"doi:10.1145/3321707.3321761","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3321707.3321761","pdf_url":null,"source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.manchester.ac.uk/ws/files/102181089/ClusterGen_GECCO2019_Deposit_nonacm.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086174310","display_name":"Cameron Shand","orcid":"https://orcid.org/0000-0002-1299-890X"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cameron Shand","raw_affiliation_strings":["University of Manchester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Manchester","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053181919","display_name":"Richard Allmendinger","orcid":"https://orcid.org/0000-0003-1236-3143"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Richard Allmendinger","raw_affiliation_strings":["University of Manchester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Manchester","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020541197","display_name":"Julia Handl","orcid":"https://orcid.org/0000-0002-4338-1806"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Julia Handl","raw_affiliation_strings":["University of Manchester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Manchester","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080984611","display_name":"Andrew Webb","orcid":"https://orcid.org/0000-0001-7834-5250"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Webb","raw_affiliation_strings":["University of Manchester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Manchester","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105350782","display_name":"John Keane","orcid":"https://orcid.org/0000-0001-9022-4339"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"John Keane","raw_affiliation_strings":["University of Manchester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Manchester","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":null,"apc_paid":null,"fwci":1.317,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85929581,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"463","last_page":"471"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9993000030517578,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9993000030517578,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9988999962806702,"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/T12535","display_name":"Machine Learning and Data Classification","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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8426618576049805},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8333349227905273},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6970140933990479},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5865663290023804},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5531821250915527},{"id":"https://openalex.org/keywords/strengths-and-weaknesses","display_name":"Strengths and weaknesses","score":0.5485844612121582},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5400993824005127},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5028888583183289},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47825542092323303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4307795763015747},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.430172860622406},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4205473065376282}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8426618576049805},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8333349227905273},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6970140933990479},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5865663290023804},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5531821250915527},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.5485844612121582},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5400993824005127},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5028888583183289},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47825542092323303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4307795763015747},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.430172860622406},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4205473065376282},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3321707.3321761","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3321707.3321761","pdf_url":null,"source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/b1821b0b-05d0-4fb8-97c9-cf762cfb8768","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/b1821b0b-05d0-4fb8-97c9-cf762cfb8768","pdf_url":"https://pure.manchester.ac.uk/ws/files/102181089/ClusterGen_GECCO2019_Deposit_nonacm.pdf","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Shand, C, Allmendinger, R, Handl, J, Webb, A & Keane, J 2019, Evolving Controllably Difficult Datasets for Clustering. in Proceedings of the Annual Conference on Genetic and Evolutionary Computation (GECCO '19) . The Genetic and Evolutionary Computation Conference, Prague, Czech Republic, 13/07/19. https://doi.org/10.1145/3321707.3321761","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.atira.dk:publications/b1821b0b-05d0-4fb8-97c9-cf762cfb8768","is_oa":false,"landing_page_url":"https://www.research.manchester.ac.uk/portal/en/publications/evolving-controllably-difficult-datasets-for-clustering(b1821b0b-05d0-4fb8-97c9-cf762cfb8768).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/b1821b0b-05d0-4fb8-97c9-cf762cfb8768","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/b1821b0b-05d0-4fb8-97c9-cf762cfb8768","pdf_url":"https://pure.manchester.ac.uk/ws/files/102181089/ClusterGen_GECCO2019_Deposit_nonacm.pdf","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Shand, C, Allmendinger, R, Handl, J, Webb, A & Keane, J 2019, Evolving Controllably Difficult Datasets for Clustering. in Proceedings of the Annual Conference on Genetic and Evolutionary Computation (GECCO '19) . The Genetic and Evolutionary Computation Conference, Prague, Czech Republic, 13/07/19. https://doi.org/10.1145/3321707.3321761","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1115592165","display_name":null,"funder_award_id":"EP/M013766/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4082175093","display_name":"Manchester Centre for Doctoral Training in Computer Science","funder_award_id":"EP/I028099/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8635193776","display_name":null,"funder_award_id":"1704969","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2954848721.pdf","grobid_xml":"https://content.openalex.org/works/W2954848721.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W815914887","https://openalex.org/W1495775210","https://openalex.org/W1513608017","https://openalex.org/W1536492814","https://openalex.org/W1967715425","https://openalex.org/W1971650562","https://openalex.org/W1985059878","https://openalex.org/W1987971958","https://openalex.org/W2066473880","https://openalex.org/W2071948161","https://openalex.org/W2073459066","https://openalex.org/W2076089275","https://openalex.org/W2083265890","https://openalex.org/W2086351984","https://openalex.org/W2092993939","https://openalex.org/W2100012833","https://openalex.org/W2100483895","https://openalex.org/W2150484508","https://openalex.org/W2151339633","https://openalex.org/W2151554678","https://openalex.org/W2775947831","https://openalex.org/W2825570816","https://openalex.org/W2884586244","https://openalex.org/W2997591727","https://openalex.org/W3102018295","https://openalex.org/W4235169531","https://openalex.org/W4255717863","https://openalex.org/W4285719527","https://openalex.org/W4293874907","https://openalex.org/W6668990524"],"related_works":["https://openalex.org/W4295769391","https://openalex.org/W2972220648","https://openalex.org/W2332667808","https://openalex.org/W1997921863","https://openalex.org/W3112960490","https://openalex.org/W93605524","https://openalex.org/W2021145421","https://openalex.org/W821271700","https://openalex.org/W2183009720","https://openalex.org/W4250894911"],"abstract_inverted_index":{"Synthetic":[0],"datasets":[1,102],"play":[2],"an":[3,79,95],"important":[4],"role":[5],"in":[6,123],"evaluating":[7],"clustering":[8,39,125],"algorithms,":[9],"as":[10],"they":[11],"can":[12,97],"help":[13],"shed":[14],"light":[15],"on":[16,66],"consistent":[17],"biases,":[18],"strengths,":[19],"and":[20,42,115],"weaknesses":[21],"of":[22,37,44,86,103,112,127],"particular":[23],"techniques,":[24],"thereby":[25],"supporting":[26],"sound":[27],"conclusions.":[28],"Despite":[29],"this,":[30],"there":[31],"is":[32,53],"a":[33,73,87,104],"surprisingly":[34],"small":[35],"set":[36],"established":[38,128],"benchmark":[40],"data,":[41],"many":[43],"these":[45,67,117],"are":[46],"currently":[47],"handcrafted.":[48],"Even":[49],"then,":[50],"their":[51],"difficulty":[52],"typically":[54],"not":[55],"quantified":[56],"or":[57],"considered,":[58],"limiting":[59],"the":[60,124],"ability":[61],"to":[62,82,100,107],"interpret":[63],"algorithmic":[64],"performance":[65,126],"datasets.":[68],"Here,":[69],"we":[70],"introduce":[71],"HAWKS,":[72],"new":[74],"data":[75,89],"generator":[76],"that":[77],"uses":[78],"evolutionary":[80],"algorithm":[81],"evolve":[83],"cluster":[84],"structure":[85],"synthetic":[88],"set.":[90],"We":[91],"demonstrate":[92],"how":[93,116],"such":[94],"approach":[96],"be":[98],"used":[99],"produce":[101],"pre-specified":[105],"difficulty,":[106,114],"trade":[108],"off":[109],"different":[110],"aspects":[111],"problem":[113],"interventions":[118],"directly":[119],"translate":[120],"into":[121],"changes":[122],"algorithms.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}