{"id":"https://openalex.org/W4391093031","doi":"https://doi.org/10.1109/bigdata59044.2023.10386749","title":"Dividing and Merging for Imbalanced Long-Tail Datasets","display_name":"Dividing and Merging for Imbalanced Long-Tail Datasets","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391093031","doi":"https://doi.org/10.1109/bigdata59044.2023.10386749"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386749","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5114859362","display_name":"Minseo Park","orcid":"https://orcid.org/0000-0003-1205-6178"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minseo Park","raw_affiliation_strings":["Korea Institute of Energy Technology (KENTECH) 21 Kentech-gil,Department of Energy Engineering,Naju,Jeonnam,Republic of Korea,58217"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Institute of Energy Technology (KENTECH) 21 Kentech-gil,Department of Energy Engineering,Naju,Jeonnam,Republic of Korea,58217","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067672248","display_name":"Hyuk Lim","orcid":"https://orcid.org/0000-0002-9926-3913"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyuk Lim","raw_affiliation_strings":["Korea Institute of Energy Technology (KENTECH) 21 Kentech-gil,Department of Energy Engineering,Naju,Jeonnam,Republic of Korea,58217"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Institute of Energy Technology (KENTECH) 21 Kentech-gil,Department of Energy Engineering,Naju,Jeonnam,Republic of Korea,58217","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101424021","display_name":"Seunghyun Yoon","orcid":"https://orcid.org/0000-0002-7262-3579"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seunghyun Yoon","raw_affiliation_strings":["Korea Institute of Energy Technology (KENTECH) 21 Kentech-gil,Department of Energy Engineering,Naju,Jeonnam,Republic of Korea,58217"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Institute of Energy Technology (KENTECH) 21 Kentech-gil,Department of Energy Engineering,Naju,Jeonnam,Republic of Korea,58217","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"6254","last_page":"6256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9997000098228455,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9997000098228455,"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/T13429","display_name":"Electricity Theft Detection Techniques","score":0.9984999895095825,"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"}},{"id":"https://openalex.org/T12707","display_name":"Vehicle License Plate Recognition","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/computer-science","display_name":"Computer science","score":0.770755410194397},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6717854142189026},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6565901041030884},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5993474721908569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5180606842041016},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5052147507667542},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5043038129806519},{"id":"https://openalex.org/keywords/long-tail","display_name":"Long tail","score":0.49811315536499023},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3229464590549469},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12208980321884155},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07372176647186279}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770755410194397},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6717854142189026},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6565901041030884},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5993474721908569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5180606842041016},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5052147507667542},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5043038129806519},{"id":"https://openalex.org/C15189868","wikidata":"https://www.wikidata.org/wiki/Q534685","display_name":"Long tail","level":2,"score":0.49811315536499023},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3229464590549469},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12208980321884155},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07372176647186279},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata59044.2023.10386749","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2023060295","https://openalex.org/W2970941190","https://openalex.org/W3034933032","https://openalex.org/W6764733053","https://openalex.org/W6780793664","https://openalex.org/W6784097300"],"related_works":["https://openalex.org/W4381191248","https://openalex.org/W2961085424","https://openalex.org/W4224009465","https://openalex.org/W3124876361","https://openalex.org/W2107962325","https://openalex.org/W2374385360","https://openalex.org/W4306674287","https://openalex.org/W4286629047","https://openalex.org/W2075391946","https://openalex.org/W2248928492"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,53],"introduce":[4],"a":[5,34,55],"novel":[6],"approach":[7],"for":[8,45],"addressing":[9],"class":[10,39,62],"imbalance":[11],"in":[12],"long-tail":[13],"datasets,":[14],"focusing":[15],"on":[16],"the":[17,27,38],"strategy":[18],"of":[19,37],"dividing":[20,26],"and":[21,48],"merging.":[22],"Our":[23],"methodology":[24],"involves":[25],"dataset":[28],"into":[29],"separate":[30],"clusters,":[31],"each":[32,46],"representing":[33],"different":[35],"segment":[36],"distribution.":[40],"By":[41],"training":[42],"dedicated":[43],"models":[44],"cluster":[47],"subsequently":[49],"merging":[50],"their":[51],"parameters,":[52],"achieve":[54],"more":[56],"balanced":[57],"learning":[58],"process":[59],"across":[60],"diverse":[61],"sizes.":[63]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}