{"id":"https://openalex.org/W2997966807","doi":"https://doi.org/10.1145/3366650.3366665","title":"Handling Imbalanced Data through Affinity Propagation and SMOTE","display_name":"Handling Imbalanced Data through Affinity Propagation and SMOTE","publication_year":2019,"publication_date":"2019-10-18","ids":{"openalex":"https://openalex.org/W2997966807","doi":"https://doi.org/10.1145/3366650.3366665","mag":"2997966807"},"language":"en","primary_location":{"id":"doi:10.1145/3366650.3366665","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3366650.3366665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Computing and Big Data","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/A5002016340","display_name":"Lanie Laureano","orcid":"https://orcid.org/0000-0001-9762-6293"},"institutions":[{"id":"https://openalex.org/I95350115","display_name":"Technological Institute of the Philippines","ror":"https://ror.org/02p79p790","country_code":"PH","type":"education","lineage":["https://openalex.org/I95350115"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Lanie B. Laureano","raw_affiliation_strings":["Technological Institute of the Philippines, Quezon City, Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technological Institute of the Philippines, Quezon City, Philippines","institution_ids":["https://openalex.org/I95350115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052741392","display_name":"Ariel M. Sison","orcid":"https://orcid.org/0000-0002-8204-8002"},"institutions":[{"id":"https://openalex.org/I220050277","display_name":"Emilio Aguinaldo College","ror":"https://ror.org/03sygwm20","country_code":"PH","type":"education","lineage":["https://openalex.org/I220050277"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Ariel M. Sison","raw_affiliation_strings":["School of Computer Studies, Emilio Aguinaldo College, Manila, Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Studies, Emilio Aguinaldo College, Manila, Philippines","institution_ids":["https://openalex.org/I220050277"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032332379","display_name":"Ruji P. Medina","orcid":"https://orcid.org/0000-0003-1649-4634"},"institutions":[{"id":"https://openalex.org/I95350115","display_name":"Technological Institute of the Philippines","ror":"https://ror.org/02p79p790","country_code":"PH","type":"education","lineage":["https://openalex.org/I95350115"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Ruji P. Medina","raw_affiliation_strings":["Dean, Graduate Programs, Technological Institute of the Philippines Quezon City, Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dean, Graduate Programs, Technological Institute of the Philippines Quezon City, Philippines","institution_ids":["https://openalex.org/I95350115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8747,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.80822747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"22","last_page":"26"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9911999702453613,"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":0.9815000295639038,"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/oversampling","display_name":"Oversampling","score":0.8785960078239441},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7428761124610901},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7019038796424866},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6986668705940247},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5916301608085632},{"id":"https://openalex.org/keywords/affinity-propagation","display_name":"Affinity propagation","score":0.5822140574455261},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5680239200592041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5228336453437805},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5205608010292053},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.512817919254303},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4121537208557129},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3769122362136841},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.18029996752738953},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.11196064949035645}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.8785960078239441},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7428761124610901},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7019038796424866},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6986668705940247},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5916301608085632},{"id":"https://openalex.org/C109659709","wikidata":"https://www.wikidata.org/wiki/Q3407504","display_name":"Affinity propagation","level":5,"score":0.5822140574455261},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5680239200592041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5228336453437805},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5205608010292053},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.512817919254303},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4121537208557129},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3769122362136841},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.18029996752738953},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.11196064949035645},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3366650.3366665","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3366650.3366665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Computing and Big Data","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":21,"referenced_works":["https://openalex.org/W123443654","https://openalex.org/W1496056137","https://openalex.org/W1990262636","https://openalex.org/W2096574974","https://openalex.org/W2115969689","https://openalex.org/W2148143831","https://openalex.org/W2165232124","https://openalex.org/W2172165257","https://openalex.org/W2287979797","https://openalex.org/W2338318698","https://openalex.org/W2562319768","https://openalex.org/W2601726217","https://openalex.org/W2625777111","https://openalex.org/W2725860187","https://openalex.org/W2726366273","https://openalex.org/W2744139632","https://openalex.org/W2766296277","https://openalex.org/W2772832743","https://openalex.org/W2784249848","https://openalex.org/W2891857749","https://openalex.org/W2901624508"],"related_works":["https://openalex.org/W2766503024","https://openalex.org/W2781247653","https://openalex.org/W4206637278","https://openalex.org/W4386005305","https://openalex.org/W3082051559","https://openalex.org/W4386214543","https://openalex.org/W1969988626","https://openalex.org/W2141301039","https://openalex.org/W2012117566","https://openalex.org/W1981856929"],"abstract_inverted_index":{"Imbalanced":[0],"datasets":[1,149,169],"occur":[2],"in":[3,13,45,54,140,157],"real-world":[4],"scenarios":[5],"and":[6,22,39,57,112,162,173],"affect":[7],"the":[8,11,18,34,63,71,76,80,84,118,121,131,151,154],"performance":[9],"of":[10,60,79,86,97,120,123,133,153,159,170],"classifiers":[12],"supervised":[14],"learning.":[15],"To":[16],"combat":[17],"imbalance":[19],"between":[20,36],"majority":[21],"minority":[23,37,64],"instances,":[24],"several":[25],"techniques":[26,68],"including":[27],"SMOTE":[28,48],"which":[29,134],"generates":[30],"artificial":[31],"data":[32,53],"along":[33],"line":[35],"samples":[38,61,88,135],"its":[40,113],"selected":[41],"neighbors":[42],"are":[43,136],"used":[44],"preprocessing.":[46],"However,":[47],"suffers":[49],"from":[50],"generating":[51],"synthetic":[52,87],"noise":[55],"regions":[56],"imbalanced":[58],"distribution":[59],"within":[62],"class.":[65],"Using":[66],"clustering":[67,107],"prior":[69],"to":[70,74,93,109,137],"oversampling":[72],"step":[73],"determine":[75],"target":[77],"areas":[78],"input":[81],"space":[82],"where":[83],"generation":[85],"is":[89,91],"effective,":[90],"known":[92],"be":[94,138],"an":[95],"extension":[96],"SMOTE.":[98],"The":[99,127],"proposed":[100,155],"method":[101,156],"uses":[102],"affinity":[103],"propagation":[104],"as":[105],"a":[106,125,165],"technique":[108],"generate":[110],"clusters":[111,124],"cluster":[114,128],"exemplar":[115,129],"without":[116],"requiring":[117],"specification":[119],"number":[122],"priori.":[126],"becomes":[130],"basis":[132],"oversampled":[139],"each":[141],"cluster.":[142],"Simulation":[143],"results":[144],"on":[145],"some":[146],"publicly":[147],"available":[148],"show":[150],"effectiveness":[152],"terms":[158],"F-measure,":[160],"G-mean":[161],"AUC":[163],"with":[164],"mean":[166],"value":[167],"across":[168],".685,":[171],".756":[172],".765":[174],"respectively.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}