{"id":"https://openalex.org/W4400277625","doi":"https://doi.org/10.1109/icoin59985.2024.10572133","title":"A K-means Clustering Based Under-Sampling Method for Imbalanced Dataset Classification","display_name":"A K-means Clustering Based Under-Sampling Method for Imbalanced Dataset Classification","publication_year":2024,"publication_date":"2024-01-17","ids":{"openalex":"https://openalex.org/W4400277625","doi":"https://doi.org/10.1109/icoin59985.2024.10572133"},"language":"en","primary_location":{"id":"doi:10.1109/icoin59985.2024.10572133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icoin59985.2024.10572133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Information Networking (ICOIN)","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/A5049420241","display_name":"Chih-Ming Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chih-Ming Huang","raw_affiliation_strings":["National Sun Yat-sen University,Dept. of Computer Science and Engineering,Kaohsiung,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Sun Yat-sen University,Dept. of Computer Science and Engineering,Kaohsiung,Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039559097","display_name":"Chuan-Sheng Hung","orcid":"https://orcid.org/0009-0008-6290-0967"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chuan-Sheng Hung","raw_affiliation_strings":["National Sun Yat-sen University,Dept. of Computer Science and Engineering,Kaohsiung,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Sun Yat-sen University,Dept. of Computer Science and Engineering,Kaohsiung,Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102700195","display_name":"Yao-Yuan Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yao-Yuan Hsu","raw_affiliation_strings":["National Sun Yat-sen University,Dept. of Computer Science and Engineering,Kaohsiung,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Sun Yat-sen University,Dept. of Computer Science and Engineering,Kaohsiung,Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003423115","display_name":"You-Cheng Zheng","orcid":"https://orcid.org/0000-0002-6961-1323"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"You-Cheng Zheng","raw_affiliation_strings":["National Sun Yat-sen University,Dept. of Computer Science and Engineering,Kaohsiung,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Sun Yat-sen University,Dept. of Computer Science and Engineering,Kaohsiung,Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062479970","display_name":"Cheng-Han Yu","orcid":"https://orcid.org/0000-0002-6977-6400"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Han Yu","raw_affiliation_strings":["National Sun Yat-sen University,Dept. of Computer Science and Engineering,Kaohsiung,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Sun Yat-sen University,Dept. of Computer Science and Engineering,Kaohsiung,Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015921213","display_name":"Chun\u2010Hung Richard Lin","orcid":"https://orcid.org/0000-0003-0840-394X"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-Hung Richard Lin","raw_affiliation_strings":["National Sun Yat-sen University,Dept. of Computer Science and Engineering,Kaohsiung,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Sun Yat-sen University,Dept. of Computer Science and Engineering,Kaohsiung,Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090457063","display_name":"Shi-Huang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134750","display_name":"Shu-Te University","ror":"https://ror.org/03pcb1m79","country_code":"TW","type":"education","lineage":["https://openalex.org/I4210134750"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shi-Huang Chen","raw_affiliation_strings":["Shu-Te University,Dept. of Computer Science and Information Engineering,Kaohsiung,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shu-Te University,Dept. of Computer Science and Information Engineering,Kaohsiung,Taiwan","institution_ids":["https://openalex.org/I4210134750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"708","last_page":"713"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9871000051498413,"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":0.9871000051498413,"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":0.7434332966804504},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7064962387084961},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5251554846763611},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.503858745098114},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4408209025859833},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40136444568634033},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3212299942970276}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7434332966804504},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7064962387084961},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5251554846763611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.503858745098114},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4408209025859833},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40136444568634033},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3212299942970276},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icoin59985.2024.10572133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icoin59985.2024.10572133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Information Networking (ICOIN)","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":16,"referenced_works":["https://openalex.org/W1036088323","https://openalex.org/W1673310716","https://openalex.org/W1993220166","https://openalex.org/W2104933073","https://openalex.org/W2118978333","https://openalex.org/W2127218421","https://openalex.org/W2132791018","https://openalex.org/W2146369703","https://openalex.org/W2148143831","https://openalex.org/W2490420619","https://openalex.org/W2511002675","https://openalex.org/W2562319768","https://openalex.org/W2767106145","https://openalex.org/W3155649056","https://openalex.org/W6637131181","https://openalex.org/W6678914141"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W2393816671","https://openalex.org/W2158836806","https://openalex.org/W2083665254","https://openalex.org/W1926736923","https://openalex.org/W2942177010"],"abstract_inverted_index":{"This":[0,48,63,178,197],"paper":[1,64],"explores":[2],"the":[3,19,28,36,72,93,104,109,113,123,128,136,145,159,170,181,214],"challenges":[4],"of":[5,21,56,74,155,184],"applying":[6],"imbalanced":[7,76,146,189,195],"datasets":[8],"to":[9,25,39,60,96,169],"machine":[10],"learning":[11,29,186],"models.":[12],"There":[13],"is":[14,80,175],"a":[15,66],"significant":[16],"disparity":[17],"in":[18,27,51,127,202,213],"quantities":[20],"different":[22,139],"classes,":[23],"leading":[24,59],"biases":[26],"process.":[30],"Consequently,":[31],"many":[32],"models":[33],"favor":[34],"predicting":[35],"majority":[37,98],"class":[38,46,99],"enhance":[40],"accuracy,":[41],"neglecting":[42],"potentially":[43],"crucial":[44],"minority":[45],"data.":[47,77,100],"bias":[49,183],"results":[50,143],"an":[52,152],"overly":[53],"optimistic":[54],"perception":[55],"predictive":[57,192],"outcomes,":[58],"erroneous":[61],"decision-making.":[62],"proposes":[65],"classification":[67,182],"sampling":[68],"method":[69,162,172],"that":[70,158],"solves":[71],"issue":[73],"original":[75],"The":[78,86,119],"process":[79],"divided":[81],"into":[82],"two":[83],"main":[84],"parts.":[85],"first":[87],"part":[88,121],"involves":[89],"data":[90,117,125],"preprocessing,":[91],"utilizing":[92],"K-Means":[94],"algorithm":[95],"cluster":[97],"Additionally,":[101],"it":[102],"replaces":[103],"traditional":[105,185],"Euclidean":[106],"distance":[107,111],"with":[108,151],"Hellinger":[110,161],"as":[112,131],"similarity":[114],"metric":[115],"for":[116,194],"clustering.":[118],"second":[120],"utilizes":[122],"representative":[124],"obtained":[126],"previous":[129],"step":[130],"training":[132],"input,":[133],"thereby":[134],"reducing":[135],"imbalance":[137,153],"between":[138],"classifications.":[140],"Finally,":[141],"experimental":[142],"using":[144],"Kawasaki":[147],"Disease":[148],"(KD)":[149],"dataset,":[150],"rate":[154],"64.35%,":[156],"demonstrate":[157],"proposed":[160],"improves":[163],"Precision":[164],"(PPV)":[165],"by":[166],"20.2%":[167],"compared":[168],"XGBoost":[171],"when":[173],"Recall":[174],"above":[176],"90%.":[177],"effectively":[179],"addresses":[180],"methods":[187],"towards":[188],"data,":[190],"enhancing":[191],"outcomes":[193],"datasets.":[196],"approach":[198],"holds":[199],"potential":[200],"applications":[201],"medical":[203],"disease":[204],"prediction,":[205],"financial":[206],"fraud":[207],"detection,":[208],"and":[209],"other":[210],"related":[211],"domains":[212],"future.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}