{"id":"https://openalex.org/W3160953847","doi":"https://doi.org/10.1007/s10994-021-06012-8","title":"RB-CCR: Radial-Based Combined Cleaning and Resampling algorithm for imbalanced data classification","display_name":"RB-CCR: Radial-Based Combined Cleaning and Resampling algorithm for imbalanced data classification","publication_year":2021,"publication_date":"2021-10-06","ids":{"openalex":"https://openalex.org/W3160953847","doi":"https://doi.org/10.1007/s10994-021-06012-8","mag":"3160953847"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-021-06012-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-06012-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06012-8.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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06012-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027393953","display_name":"Micha\u0142 Koziarski","orcid":"https://orcid.org/0000-0001-7707-9640"},"institutions":[{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Micha\u0142 Koziarski","raw_affiliation_strings":["Department of Electronics, AGH University of Science and Technology, Al. Mickiewicza 30, 30-059, Krak\u00f3w, Poland","AGH UNIVERSITY OF SCIENCE AND TECHNOLOGY"],"affiliations":[{"raw_affiliation_string":"Department of Electronics, AGH University of Science and Technology, Al. Mickiewicza 30, 30-059, Krak\u00f3w, Poland","institution_ids":["https://openalex.org/I686019"]},{"raw_affiliation_string":"AGH UNIVERSITY OF SCIENCE AND TECHNOLOGY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033365772","display_name":"Colin Bellinger","orcid":"https://orcid.org/0000-0002-3567-7834"},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Colin Bellinger","raw_affiliation_strings":["Digital Technologies, National Research Council of Canada, Ottawa, Canada"],"affiliations":[{"raw_affiliation_string":"Digital Technologies, National Research Council of Canada, Ottawa, Canada","institution_ids":["https://openalex.org/I4210159778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060936121","display_name":"Micha\u0142 Wo\u017aniak","orcid":"https://orcid.org/0000-0003-0146-4205"},"institutions":[{"id":"https://openalex.org/I11923345","display_name":"Wroc\u0142aw University of Science and Technology","ror":"https://ror.org/008fyn775","country_code":"PL","type":"education","lineage":["https://openalex.org/I11923345"]},{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Micha\u0142 Wo\u017aniak","raw_affiliation_strings":["Department of Systems and Computer Networks, Wroc\u0142aw University of Science and Technology, Wybrze\u017ce Wyspia\u0144skiego 27, 50-370, Wroc\u0142aw, Poland","Wroclaw University of Science and Techno"],"affiliations":[{"raw_affiliation_string":"Department of Systems and Computer Networks, Wroc\u0142aw University of Science and Technology, Wybrze\u017ce Wyspia\u0144skiego 27, 50-370, Wroc\u0142aw, Poland","institution_ids":["https://openalex.org/I11923345","https://openalex.org/I686019"]},{"raw_affiliation_string":"Wroclaw University of Science and Techno","institution_ids":["https://openalex.org/I11923345"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027393953"],"corresponding_institution_ids":["https://openalex.org/I686019"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.2799,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62484002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"110","issue":"11-12","first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13429","display_name":"Electricity Theft Detection Techniques","score":0.9957000017166138,"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/resampling","display_name":"Resampling","score":0.8768860101699829},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.8068006038665771},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6821677684783936},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5982610583305359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5355987548828125},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5281360745429993},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.525933563709259},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.493566632270813},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46098148822784424},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.431352823972702},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43046554923057556},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4102901220321655},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33203983306884766},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2449437379837036},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.2133847177028656},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.10186457633972168}],"concepts":[{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.8768860101699829},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.8068006038665771},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6821677684783936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5982610583305359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5355987548828125},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5281360745429993},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.525933563709259},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.493566632270813},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46098148822784424},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.431352823972702},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43046554923057556},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4102901220321655},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33203983306884766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2449437379837036},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2133847177028656},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.10186457633972168},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"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/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1007/s10994-021-06012-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-06012-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06012-8.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":"doi:10.1109/dsaa53316.2021.9564135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa53316.2021.9564135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:c4cb8938-38ff-47ae-ae68-45f0bf675014","is_oa":false,"landing_page_url":"https://nrc-publications.canada.ca/eng/view/object/?id=c4cb8938-38ff-47ae-ae68-45f0bf675014","pdf_url":null,"source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","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":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:arXiv.org:2105.04009","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.04009","pdf_url":"https://arxiv.org/pdf/2105.04009","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2105.04009","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2105.04009","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3160953847","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1007/s10994-021-06012-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-06012-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06012-8.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":[{"display_name":"Industry, innovation and infrastructure","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G7217512731","display_name":null,"funder_award_id":"2017/27/B/ST6/01325","funder_id":"https://openalex.org/F4320322511","funder_display_name":"Narodowe Centrum Nauki"},{"id":"https://openalex.org/G828268973","display_name":null,"funder_award_id":"2017/27/N/ST6/01705","funder_id":"https://openalex.org/F4320322511","funder_display_name":"Narodowe Centrum Nauki"}],"funders":[{"id":"https://openalex.org/F4320322511","display_name":"Narodowe Centrum Nauki","ror":"https://ror.org/03ha2q922"},{"id":"https://openalex.org/F4320326815","display_name":"Infrastruktura PL-Grid","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3160953847.pdf","grobid_xml":"https://content.openalex.org/works/W3160953847.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W85350352","https://openalex.org/W88102734","https://openalex.org/W1496056137","https://openalex.org/W1503432700","https://openalex.org/W1563938718","https://openalex.org/W1591261915","https://openalex.org/W1605695115","https://openalex.org/W1976526581","https://openalex.org/W1984323748","https://openalex.org/W2038705219","https://openalex.org/W2043779491","https://openalex.org/W2055271333","https://openalex.org/W2061237952","https://openalex.org/W2068258779","https://openalex.org/W2078885513","https://openalex.org/W2087240369","https://openalex.org/W2088059023","https://openalex.org/W2090135786","https://openalex.org/W2099454382","https://openalex.org/W2101234009","https://openalex.org/W2104933073","https://openalex.org/W2107686700","https://openalex.org/W2118978333","https://openalex.org/W2119191234","https://openalex.org/W2132791018","https://openalex.org/W2137029138","https://openalex.org/W2148143831","https://openalex.org/W2150706391","https://openalex.org/W2158896888","https://openalex.org/W2167464971","https://openalex.org/W2182722412","https://openalex.org/W2226725405","https://openalex.org/W2338318698","https://openalex.org/W2409438660","https://openalex.org/W2490420619","https://openalex.org/W2507698194","https://openalex.org/W2521200999","https://openalex.org/W2606460416","https://openalex.org/W2751084232","https://openalex.org/W2763619424","https://openalex.org/W2765177294","https://openalex.org/W2783151797","https://openalex.org/W2907754184","https://openalex.org/W2914361121","https://openalex.org/W2922186538","https://openalex.org/W2952448206","https://openalex.org/W2964050365","https://openalex.org/W2964349084","https://openalex.org/W2979979633","https://openalex.org/W3005484410","https://openalex.org/W3041664846","https://openalex.org/W3199294801","https://openalex.org/W6630210095","https://openalex.org/W6635474240","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W3210983949","https://openalex.org/W2141340736","https://openalex.org/W2968770746","https://openalex.org/W3178813823","https://openalex.org/W2899303751","https://openalex.org/W2618516756","https://openalex.org/W2943284727","https://openalex.org/W3036099941","https://openalex.org/W3203204473","https://openalex.org/W2979389376","https://openalex.org/W3137818553","https://openalex.org/W3111007659","https://openalex.org/W2592842236","https://openalex.org/W3116450406","https://openalex.org/W3162194311","https://openalex.org/W3003647027","https://openalex.org/W2883035064","https://openalex.org/W3138850049","https://openalex.org/W2948706569","https://openalex.org/W3182194881"],"abstract_inverted_index":{"Abstract":[0],"Real-world":[1],"classification":[2,26,47],"domains,":[3],"such":[4,23],"as":[5,68,140],"medicine,":[6],"health":[7],"and":[8,10,17,97,185,196],"safety,":[9],"finance,":[11],"often":[12],"exhibit":[13],"imbalanced":[14,50],"class":[15,105,120],"priors":[16],"have":[18],"asynchronous":[19],"misclassification":[20],"costs.":[21],"In":[22,89,115],"cases,":[24],"the":[25,38,42,54,58,63,78,83,102,109,119,127,188],"model":[27],"must":[28],"achieve":[29],"a":[30,69,179],"high":[31],"recall":[32],"without":[33],"significantly":[34],"impacting":[35],"precision.":[36],"Resampling":[37,98],"training":[39,79],"data":[40,64,85],"is":[41,87],"standard":[43],"approach":[44,112],"to":[45,107,122,144],"improving":[46],"performance":[48],"on":[49,167],"binary":[51,170],"data.":[52],"However,":[53],"state-of-the-art":[55,189],"methods":[56,191],"ignore":[57],"local":[59],"joint":[60],"distribution":[61,86],"of":[62,104,113,126,194],"or":[65,148],"correct":[66],"it":[67],"post-processing":[70],"step.":[71],"This":[72],"can":[73,137],"causes":[74],"sub-optimal":[75],"shifts":[76],"in":[77,192],"distribution,":[80],"particularly":[81],"when":[82],"target":[84],"complex.":[88],"this":[90],"paper,":[91],"we":[92],"propose":[93],"Radial-Based":[94],"Combined":[95],"Cleaning":[96],"(RB-CCR).":[99],"RB-CCR":[100,117,177],"utilizes":[101],"concept":[103],"potential":[106,121],"refine":[108],"energy-based":[110],"resampling":[111,190],"CCR.":[114],"particular,":[116],"exploits":[118],"accurately":[123],"locate":[124],"sub-regions":[125],"data-space":[128],"for":[129,135],"synthetic":[130],"oversampling.":[131],"The":[132],"category":[133],"sub-region":[134],"oversampling":[136],"be":[138,149],"specified":[139],"an":[141],"input":[142],"parameter":[143],"meet":[145],"domain-specific":[146],"needs":[147],"automatically":[150],"selected":[151],"via":[152],"cross-validation.":[153],"Our":[154],"$$5\\times":[155],"2$$":[156],"<mml:math":[157],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[158],"<mml:mrow>":[159],"<mml:mn>5</mml:mn>":[160],"<mml:mo>\u00d7</mml:mo>":[161],"<mml:mn>2</mml:mn>":[162],"</mml:mrow>":[163],"</mml:math>":[164],"cross-validated":[165],"results":[166],"57":[168],"benchmark":[169],"datasets":[171],"with":[172],"9":[173],"classifiers":[174],"show":[175],"that":[176],"achieves":[178],"better":[180],"precision-recall":[181],"trade-off":[182],"than":[183],"CCR":[184],"generally":[186],"out-performs":[187],"terms":[193],"AUC":[195],"G-mean.":[197]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2022-07-25T00:00:00"}