{"id":"https://openalex.org/W4206495069","doi":"https://doi.org/10.1109/bigdata52589.2021.9671609","title":"SMOTE-OB: Combining SMOTE and Online Bagging for Continuous Rebalancing of Evolving Data Streams","display_name":"SMOTE-OB: Combining SMOTE and Online Bagging for Continuous Rebalancing of Evolving Data Streams","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4206495069","doi":"https://doi.org/10.1109/bigdata52589.2021.9671609"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9671609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671609","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"2021 IEEE International Conference on Big Data (Big Data)","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/A5087779654","display_name":"Alessio Bernardo","orcid":"https://orcid.org/0000-0002-3492-0345"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Alessio Bernardo","raw_affiliation_strings":["DEIB - Politecnico di Milano, Milano, Italy"],"affiliations":[{"raw_affiliation_string":"DEIB - Politecnico di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015694017","display_name":"Emanuele Della Valle","orcid":"https://orcid.org/0000-0002-5176-5885"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Emanuele Della Valle","raw_affiliation_strings":["DEIB - Politecnico di Milano, Milano, Italy"],"affiliations":[{"raw_affiliation_string":"DEIB - Politecnico di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5087779654"],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":0.8796,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.78108058,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5033","last_page":"5042"},"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":0.9861000180244446,"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":0.9650999903678894,"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/oversampling","display_name":"Oversampling","score":0.8336029052734375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7917860150337219},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.648820161819458},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.6390843391418457},{"id":"https://openalex.org/keywords/concept-drift","display_name":"Concept drift","score":0.5111339688301086},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5054230690002441},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.497405081987381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4871980547904968},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11672103404998779}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.8336029052734375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7917860150337219},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.648820161819458},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.6390843391418457},{"id":"https://openalex.org/C60777511","wikidata":"https://www.wikidata.org/wiki/Q3045002","display_name":"Concept drift","level":3,"score":0.5111339688301086},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5054230690002441},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.497405081987381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4871980547904968},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11672103404998779},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9671609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671609","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1202060","is_oa":false,"landing_page_url":"http://hdl.handle.net/11311/1202060","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W93565154","https://openalex.org/W139044672","https://openalex.org/W164124199","https://openalex.org/W1506627523","https://openalex.org/W1525647652","https://openalex.org/W1529840045","https://openalex.org/W1565746575","https://openalex.org/W1601795611","https://openalex.org/W1975852288","https://openalex.org/W1986515506","https://openalex.org/W2012663856","https://openalex.org/W2067205732","https://openalex.org/W2073256825","https://openalex.org/W2088059023","https://openalex.org/W2088654600","https://openalex.org/W2107327607","https://openalex.org/W2110222014","https://openalex.org/W2118978333","https://openalex.org/W2136256517","https://openalex.org/W2143991132","https://openalex.org/W2160409620","https://openalex.org/W2163302275","https://openalex.org/W2520599539","https://openalex.org/W2621345043","https://openalex.org/W2626498001","https://openalex.org/W2752201871","https://openalex.org/W2773675312","https://openalex.org/W2800788706","https://openalex.org/W2945271821","https://openalex.org/W2977431930","https://openalex.org/W2978488090","https://openalex.org/W3003253354","https://openalex.org/W3120740533","https://openalex.org/W3133463776","https://openalex.org/W3146478267","https://openalex.org/W4212883601","https://openalex.org/W6603818862","https://openalex.org/W6605683200","https://openalex.org/W6630111507","https://openalex.org/W6633774736","https://openalex.org/W6680192438","https://openalex.org/W6684149856","https://openalex.org/W6768413947","https://openalex.org/W6790518815"],"related_works":["https://openalex.org/W2802243998","https://openalex.org/W2469699777","https://openalex.org/W4200217704","https://openalex.org/W3201554469","https://openalex.org/W2368264659","https://openalex.org/W4307392573","https://openalex.org/W2060628068","https://openalex.org/W2953675148","https://openalex.org/W3112950814","https://openalex.org/W3208495060"],"abstract_inverted_index":{"The":[0],"world":[1],"is":[2,51],"constantly":[3],"changing,":[4],"and":[5,33,61,72,80,90],"so":[6],"are":[7,106],"the":[8,27,41,70,98,109],"massive":[9],"amount":[10],"of":[11,29,66],"data":[12,31,82],"produced.":[13],"However,":[14],"only":[15],"a":[16,52,62,115],"few":[17],"studies":[18],"deal":[19],"with":[20,46],"online":[21],"class":[22,91,103],"imbalance":[23,88],"learning":[24],"that":[25,57,97,105],"combines":[26],"challenges":[28],"class-imbalanced":[30],"streams":[32,83],"concept":[34,86],"drift.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39,113],"propose":[40],"Synthetic":[42],"Minority":[43],"Oversampling":[44],"TEchnique":[45],"Online":[47,59],"Bagging":[48,60],"(SMOTE-OB).":[49],"It":[50],"novel":[53],"cost-sensitive":[54],"ensemble":[55,100],"strategy":[56],"uses":[58],"new":[63],"sketched":[64],"version":[65],"SMOTE":[67],"to":[68],"over/undersample":[69],"minority":[71,102],"majority":[73],"classes.":[74],"We":[75,93],"benchmarked":[76],"SMOTE-OB":[77,99],"on":[78],"synthetic":[79],"real":[81],"containing":[84],"different":[85],"drifts,":[87],"levels,":[89],"distributions.":[92],"bring":[94],"statistical":[95],"evidence":[96],"achieves":[101],"performance":[104],"better":[107],"than":[108],"state-of-the-art":[110],"ones.":[111],"Moreover,":[112],"perform":[114],"time/memory":[116],"consumption":[117],"analysis.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}