{"id":"https://openalex.org/W4406495621","doi":"https://doi.org/10.1109/bigdata62323.2024.10825430","title":"Data Imbalance Solutions Using Pseudo-Cluster and Two-Step Classification Methods","display_name":"Data Imbalance Solutions Using Pseudo-Cluster and Two-Step Classification Methods","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406495621","doi":"https://doi.org/10.1109/bigdata62323.2024.10825430"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825430","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":null,"display_name":"Gawon Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gawon Lim","raw_affiliation_strings":["University of Illinois,School of Information Sciences,Urbana-Champaign,IL,USA,61820"],"affiliations":[{"raw_affiliation_string":"University of Illinois,School of Information Sciences,Urbana-Champaign,IL,USA,61820","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23201736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8751","last_page":"8753"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9896000027656555,"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":0.9758999943733215,"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/computer-science","display_name":"Computer science","score":0.6496882438659668},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.6356114745140076},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4058936834335327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3711482286453247},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3484753966331482},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.06837278604507446}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6496882438659668},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.6356114745140076},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4058936834335327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3711482286453247},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3484753966331482},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06837278604507446}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825430","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":5,"referenced_works":["https://openalex.org/W2612634114","https://openalex.org/W2800788706","https://openalex.org/W2989219518","https://openalex.org/W3090132388","https://openalex.org/W3120740533"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Data":[0],"imbalance":[1],"poses":[2],"a":[3,15],"significant":[4],"challenge":[5],"in":[6,10,27,67,84],"machine":[7],"learning,":[8],"especially":[9],"binary":[11],"classification":[12,81],"t":[13],"asks,":[14],"s":[16],"traditional":[17],"algorithms":[18],"tend":[19],"to":[20,44],"favor":[21],"the":[22,51,56,68],"majority":[23,57],"class,":[24],"often":[25],"resulting":[26],"biased":[28],"models.":[29],"This":[30],"paper":[31],"proposes":[32],"two":[33],"novel":[34],"clustering-based":[35],"techniques:":[36],"Pseudo-Cluster":[37,40],"Classification":[38],"and":[39,47,89],"Two-Step":[41],"Classification,":[42],"designed":[43],"improve":[45],"balance":[46],"model":[48],"generalization":[49],"for":[50],"minority":[52],"class.":[53],"By":[54],"partitioning":[55],"class":[58,65],"into":[59],"distinct":[60],"sub-clusters,":[61],"these":[62,77],"methods":[63,78],"enhance":[64],"representation":[66],"dataset,":[69],"facilitating":[70],"improved":[71],"accuracy.":[72],"Experimental":[73],"results":[74],"indicate":[75],"that":[76],"outperform":[79],"default":[80],"approaches,":[82],"particularly":[83],"terms":[85],"of":[86],"Macro":[87],"F1-Score":[88],"MCC.":[90]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}