{"id":"https://openalex.org/W4389918564","doi":"https://doi.org/10.1007/s10994-023-06420-y","title":"Smoclust: synthetic minority oversampling based on stream clustering for evolving data streams","display_name":"Smoclust: synthetic minority oversampling based on stream clustering for evolving data streams","publication_year":2023,"publication_date":"2023-12-18","ids":{"openalex":"https://openalex.org/W4389918564","doi":"https://doi.org/10.1007/s10994-023-06420-y"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-023-06420-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-023-06420-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-023-06420-y.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-023-06420-y.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073527276","display_name":"Chun Wai Chiu","orcid":"https://orcid.org/0000-0002-3157-8943"},"institutions":[{"id":"https://openalex.org/I56007636","display_name":"Keele University","ror":"https://ror.org/00340yn33","country_code":"GB","type":"education","lineage":["https://openalex.org/I56007636"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Chun Wai Chiu","raw_affiliation_strings":["School of Computer Science and Mathematics, Keele University, Keele, Staffordshire, ST5 5BG, UK"],"raw_orcid":"https://orcid.org/0000-0002-3157-8943","affiliations":[{"raw_affiliation_string":"School of Computer Science and Mathematics, Keele University, Keele, Staffordshire, ST5 5BG, UK","institution_ids":["https://openalex.org/I56007636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064089961","display_name":"Leandro L. Minku","orcid":"https://orcid.org/0000-0002-2639-0671"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Leandro L. Minku","raw_affiliation_strings":["School of Computer Science, University of Birmingham, Edgbaston, Birmingham, B15 2TT, UK"],"raw_orcid":"https://orcid.org/0000-0002-2639-0671","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Birmingham, Edgbaston, Birmingham, B15 2TT, UK","institution_ids":["https://openalex.org/I79619799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064089961","https://openalex.org/A5073527276"],"corresponding_institution_ids":["https://openalex.org/I56007636","https://openalex.org/I79619799"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.9518,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7990926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"113","issue":"7","first_page":"4671","last_page":"4721"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","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/T12761","display_name":"Data Stream Mining Techniques","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":0.98089998960495,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9785000085830688,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.8581907749176025},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7846626043319702},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7696092128753662},{"id":"https://openalex.org/keywords/concept-drift","display_name":"Concept drift","score":0.7413831949234009},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.7161616086959839},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.6957956552505493},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6648584604263306},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5367822051048279},{"id":"https://openalex.org/keywords/streams","display_name":"STREAMS","score":0.47282207012176514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44211989641189575},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40062204003334045},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.07481494545936584}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.8581907749176025},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7846626043319702},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7696092128753662},{"id":"https://openalex.org/C60777511","wikidata":"https://www.wikidata.org/wiki/Q3045002","display_name":"Concept drift","level":3,"score":0.7413831949234009},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.7161616086959839},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.6957956552505493},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6648584604263306},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5367822051048279},{"id":"https://openalex.org/C42090638","wikidata":"https://www.wikidata.org/wiki/Q4048907","display_name":"STREAMS","level":2,"score":0.47282207012176514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44211989641189575},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40062204003334045},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.07481494545936584},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10994-023-06420-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-023-06420-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-023-06420-y.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/fcf43272-2e77-4559-bb6d-3074f46341cb","is_oa":true,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/fcf43272-2e77-4559-bb6d-3074f46341cb","pdf_url":"https://pure-oai.bham.ac.uk/ws/files/215940727/ChiuC2023Smoclust.pdf","source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Chiu , C W & Minku , L 2023 , ' SMOClust : Synthetic Minority Oversampling based on Stream Clustering for Evolving Data Streams ' , Machine Learning . https://doi.org/10.1007/s10994-023-06420-y","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s10994-023-06420-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-023-06420-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-023-06420-y.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G4781280766","display_name":null,"funder_award_id":"EP/R006660/2","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6192470683","display_name":"Stable Prediction of Defect-Inducing Software Changes (SPDISC)","funder_award_id":"EP/R006660/2","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G781164028","display_name":null,"funder_award_id":"R006660/2","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":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4389918564.pdf"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W182707955","https://openalex.org/W752888290","https://openalex.org/W1529840045","https://openalex.org/W1585854823","https://openalex.org/W1642701485","https://openalex.org/W1904826605","https://openalex.org/W1975852288","https://openalex.org/W1978901130","https://openalex.org/W1996523702","https://openalex.org/W2015627422","https://openalex.org/W2018345399","https://openalex.org/W2037242621","https://openalex.org/W2048442462","https://openalex.org/W2068714596","https://openalex.org/W2072159774","https://openalex.org/W2088220893","https://openalex.org/W2088654600","https://openalex.org/W2096529583","https://openalex.org/W2099419573","https://openalex.org/W2104933073","https://openalex.org/W2107327607","https://openalex.org/W2110222014","https://openalex.org/W2115677675","https://openalex.org/W2123003172","https://openalex.org/W2132791018","https://openalex.org/W2134385409","https://openalex.org/W2136256517","https://openalex.org/W2143991132","https://openalex.org/W2148143831","https://openalex.org/W2160512933","https://openalex.org/W2163302275","https://openalex.org/W2165232124","https://openalex.org/W2166781513","https://openalex.org/W2170936641","https://openalex.org/W2188660960","https://openalex.org/W2240536489","https://openalex.org/W2520599539","https://openalex.org/W2585528949","https://openalex.org/W2590806298","https://openalex.org/W2604756720","https://openalex.org/W2626498001","https://openalex.org/W2740428142","https://openalex.org/W2752201871","https://openalex.org/W2783033425","https://openalex.org/W2897349693","https://openalex.org/W2899131347","https://openalex.org/W2909853646","https://openalex.org/W2979979633","https://openalex.org/W3014846019","https://openalex.org/W3021596612","https://openalex.org/W3089692094","https://openalex.org/W3104788453","https://openalex.org/W3115143688","https://openalex.org/W3137868789","https://openalex.org/W3146478267","https://openalex.org/W3200267594","https://openalex.org/W4206495069","https://openalex.org/W4224267307","https://openalex.org/W4382516701","https://openalex.org/W6680192438"],"related_works":["https://openalex.org/W4307392573","https://openalex.org/W2802243998","https://openalex.org/W2736127210","https://openalex.org/W2329342202","https://openalex.org/W2574092225","https://openalex.org/W4200217704","https://openalex.org/W2161835057","https://openalex.org/W1521014365","https://openalex.org/W3208495060","https://openalex.org/W2740428142"],"abstract_inverted_index":{"Abstract":[0],"Many":[1],"real-world":[2,138],"data":[3,39,53,94,109,139,162],"stream":[4,72,78,163],"applications":[5],"not":[6,42],"only":[7],"suffer":[8],"from":[9],"concept":[10,148],"drift":[11,61,149],"but":[12],"also":[13],"class":[14,37,51,68,132,153,166,177],"imbalance.":[15],"Yet,":[16],"very":[17],"few":[18],"existing":[19,47,157],"studies":[20],"investigated":[21],"this":[22,56],"joint":[23],"challenge.":[24],"Data":[25],"difficulty":[26,95],"factors,":[27],"which":[28],"have":[29],"been":[30],"shown":[31],"to":[32,65,84,103],"be":[33,101,122],"key":[34],"challenges":[35],"in":[36,110],"imbalanced":[38,52,167],"streams,":[40],"are":[41],"taken":[43],"into":[44],"account":[45],"by":[46],"approaches":[48],"when":[49,160],"learning":[50],"streams.":[54],"In":[55],"work,":[57],"we":[58],"propose":[59],"a":[60],"adaptable":[62],"oversampling":[63],"strategy":[64],"synthesise":[66],"minority":[67,131,152,176],"examples":[69,120],"based":[70],"on":[71,115],"clustering.":[73],"The":[74],"motivation":[75],"is":[76,164],"that":[77,127,142],"clustering":[79],"methods":[80],"continuously":[81],"update":[82],"themselves":[83],"reflect":[85],"the":[86,89,111,116,125,143,161],"characteristics":[87],"of":[88,172],"current":[90],"underlying":[91],"concept,":[92],"including":[93],"factors.":[96],"This":[97],"nature":[98],"can":[99,121,146],"potentially":[100],"used":[102],"compress":[104],"past":[105],"information":[106],"without":[107],"caching":[108],"memory":[112],"explicitly.":[113],"Based":[114],"compressed":[117],"information,":[118],"synthetic":[119],"created":[123],"within":[124],"region":[126],"recently":[128],"generated":[129],"new":[130],"examples.":[133,178],"Experiments":[134],"with":[135],"artificial":[136],"and":[137,168,174],"streams":[140],"show":[141],"proposed":[144],"approach":[145],"handle":[147],"involving":[150],"different":[151],"decomposition":[154],"better":[155],"than":[156],"approaches,":[158],"especially":[159],"severely":[165],"presenting":[169],"high":[170],"proportions":[171],"safe":[173],"borderline":[175]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}