{"id":"https://openalex.org/W2992345747","doi":"https://doi.org/10.1109/bracis.2019.00045","title":"The Influence of Sampling on Imbalanced Data Classification","display_name":"The Influence of Sampling on Imbalanced Data Classification","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2992345747","doi":"https://doi.org/10.1109/bracis.2019.00045","mag":"2992345747"},"language":"en","primary_location":{"id":"doi:10.1109/bracis.2019.00045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bracis.2019.00045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 8th Brazilian Conference on Intelligent Systems (BRACIS)","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/A5076518607","display_name":"Victor Barella","orcid":"https://orcid.org/0000-0002-7029-998X"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Victor Barella","raw_affiliation_strings":["University of Sao Paulo, Sao Carlos, Brazil"],"affiliations":[{"raw_affiliation_string":"University of Sao Paulo, Sao Carlos, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079832994","display_name":"Lu\u00eds P. F. Garcia","orcid":"https://orcid.org/0000-0003-0679-9143"},"institutions":[{"id":"https://openalex.org/I150729083","display_name":"Universidade de Bras\u00edlia","ror":"https://ror.org/02xfp8v59","country_code":"BR","type":"education","lineage":["https://openalex.org/I150729083"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Luis Garcia","raw_affiliation_strings":["University of Brasilia, Brasilia, Brazil"],"affiliations":[{"raw_affiliation_string":"University of Brasilia, Brasilia, Brazil","institution_ids":["https://openalex.org/I150729083"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079499583","display_name":"Andr\u00e9 C. P. L. F. de Carvalho","orcid":"https://orcid.org/0000-0002-4765-6459"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Andre de Carvalho","raw_affiliation_strings":["University of Sao Paulo, Sao Carlos, Brazil"],"affiliations":[{"raw_affiliation_string":"University of Sao Paulo, Sao Carlos, Brazil","institution_ids":["https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076518607"],"corresponding_institution_ids":["https://openalex.org/I17974374"],"apc_list":null,"apc_paid":null,"fwci":0.42,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7216362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"210","last_page":"215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9930999875068665,"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":0.9848999977111816,"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":0.7263539433479309},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6722848415374756},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6421412825584412},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6187106966972351},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5397821664810181},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5396357774734497},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.47496435046195984},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4453003406524658},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.42596012353897095},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.4185878336429596},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4158675968647003},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3695576786994934},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14876529574394226},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12915796041488647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7263539433479309},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6722848415374756},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6421412825584412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6187106966972351},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5397821664810181},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5396357774734497},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.47496435046195984},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4453003406524658},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.42596012353897095},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.4185878336429596},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4158675968647003},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3695576786994934},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14876529574394226},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12915796041488647},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/bracis.2019.00045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bracis.2019.00045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 8th Brazilian Conference on Intelligent Systems (BRACIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W85350352","https://openalex.org/W906603025","https://openalex.org/W1563088657","https://openalex.org/W1976035027","https://openalex.org/W1993220166","https://openalex.org/W2004710424","https://openalex.org/W2011376672","https://openalex.org/W2025886727","https://openalex.org/W2032867948","https://openalex.org/W2070762699","https://openalex.org/W2081697244","https://openalex.org/W2087240369","https://openalex.org/W2104933073","https://openalex.org/W2107542581","https://openalex.org/W2113608932","https://openalex.org/W2118978333","https://openalex.org/W2125877832","https://openalex.org/W2132791018","https://openalex.org/W2132862423","https://openalex.org/W2148143831","https://openalex.org/W2149706766","https://openalex.org/W2185967890","https://openalex.org/W2295282302","https://openalex.org/W2896309543","https://openalex.org/W2897069058","https://openalex.org/W4236137412","https://openalex.org/W4243367342","https://openalex.org/W6603460400","https://openalex.org/W6675634716","https://openalex.org/W6677954473"],"related_works":["https://openalex.org/W4388813866","https://openalex.org/W2999104021","https://openalex.org/W4293088233","https://openalex.org/W2850804095","https://openalex.org/W1481656249","https://openalex.org/W2162280767","https://openalex.org/W1570799877","https://openalex.org/W2800688113","https://openalex.org/W4236933217","https://openalex.org/W2057598446"],"abstract_inverted_index":{"Classification":[0],"tasks":[1],"using":[2,147],"imbalanced":[3,69],"data":[4,32,114,124,138,155,210],"are":[5,14,158],"not":[6,190],"challenging":[7],"on":[8],"their":[9],"own.":[10],"When":[11],"the":[12,28,36,40,58,75,111,119,133,137,154,171,175,182,186,209],"classes":[13,29,44],"linearly":[15],"separable,":[16],"a":[17,47,78,82,101,104,159,165,206],"regular":[18],"classification":[19,59,79],"algorithm":[20],"usually":[21],"induces":[22],"predictive":[23,134,172],"models":[24],"able":[25,72],"to":[26,56,63,73,93,99,117,152,161,169,199],"distinguish":[27],"properly.":[30],"Imbalanced":[31],"poses":[33],"difficulty":[34,61,183],"for":[35,68,81,123],"minority":[37,187],"class":[38,188],"when":[39,192],"training":[41],"sets":[42],"have":[43,85],"overlapping":[45],"or":[46],"complex":[48],"border":[49],"decision.":[50],"Assessing":[51],"these":[52],"characteristics":[53],"is":[54,98,189],"fundamental":[55],"understand":[57],"task":[60,80],"and":[62,136],"choose":[64],"adequate":[65],"pre-processing":[66,126,145],"techniques":[67,146],"data.":[70],"Measures":[71],"identify":[74,94],"complexity":[76,115,139,156,211],"of":[77,113,140,174,184,208,212],"given":[83],"dataset":[84],"been":[86],"proposed.":[87],"These":[88],"measures":[89,116,157],"use":[90,112],"different":[91,148],"criteria":[92],"how":[95],"difficult":[96],"it":[97],"induce":[100],"classifier":[102],"from":[103],"dataset.":[105],"In":[106],"this":[107,130,202],"paper,":[108],"we":[109,204],"investigate":[110],"estimate":[118],"best":[120],"sample":[121,149,167],"size":[122,168],"imbalance":[125],"techniques.":[127],"For":[128],"such,":[129],"paper":[131],"assesses":[132],"performance":[135,173],"real":[141],"datasets":[142],"after":[143],"applying":[144],"sizes.":[150],"According":[151],"experiments,":[153],"tool":[160],"help":[162],"in":[163],"choosing":[164],"proper":[166],"improve":[170],"classifiers.":[176],"We":[177],"also":[178],"observe":[179],"that":[180],"only":[181],"predicting":[185],"enough":[191],"dealing":[193],"with":[194,201],"sampling.":[195],"As":[196],"an":[197],"alternative":[198],"deal":[200],"deficiency,":[203],"suggest":[205],"combination":[207],"both":[213],"classes.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}