{"id":"https://openalex.org/W4292387278","doi":"https://doi.org/10.1109/tnnls.2022.3197156","title":"A Synthetic Minority Oversampling Technique Based on Gaussian Mixture Model Filtering for Imbalanced Data Classification","display_name":"A Synthetic Minority Oversampling Technique Based on Gaussian Mixture Model Filtering for Imbalanced Data Classification","publication_year":2022,"publication_date":"2022-08-19","ids":{"openalex":"https://openalex.org/W4292387278","doi":"https://doi.org/10.1109/tnnls.2022.3197156","pmid":"https://pubmed.ncbi.nlm.nih.gov/35984792"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3197156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3197156","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5046193582","display_name":"Zhaozhao Xu","orcid":"https://orcid.org/0000-0002-7811-3799"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaozhao Xu","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-7811-3799","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015251362","display_name":"Derong Shen","orcid":"https://orcid.org/0000-0003-0310-6372"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Derong Shen","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026995541","display_name":"Yue Kou","orcid":"https://orcid.org/0000-0002-5307-4893"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Kou","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102979521","display_name":"Tiezheng Nie","orcid":"https://orcid.org/0000-0002-0166-1324"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiezheng Nie","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.1562,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":{"value":0.98237832,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"35","issue":"3","first_page":"3740","last_page":"3753"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9722999930381775,"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":0.9710000157356262,"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":0.9871348142623901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.558570384979248},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.516918420791626},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.514462947845459},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5086794495582581},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5072343349456787},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.48876428604125977},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.43024134635925293},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4250660836696625},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3669549822807312},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3344796895980835},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.09216871857643127},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08111324906349182}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.9871348142623901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.558570384979248},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.516918420791626},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.514462947845459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5086794495582581},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5072343349456787},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48876428604125977},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.43024134635925293},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4250660836696625},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3669549822807312},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3344796895980835},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.09216871857643127},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08111324906349182},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2022.3197156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3197156","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:35984792","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35984792","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1425812762","display_name":null,"funder_award_id":"62172082","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5505926156","display_name":"\u57fa\u4e8e\u7fa4\u7ec4\u751f\u6210\u673a\u7406\u7684\u53ef\u89e3\u91ca\u7fa4\u7ec4\u63a8\u8350\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62072084","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G674875540","display_name":null,"funder_award_id":"N2116008","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7932691611","display_name":"\u9762\u5411\u5927\u6570\u636e\u878d\u5408\u7684\u533a\u5757\u94fe\u6570\u636e\u7ba1\u7406\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"62072086","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1496056137","https://openalex.org/W1997254720","https://openalex.org/W2005330159","https://openalex.org/W2020858209","https://openalex.org/W2087240369","https://openalex.org/W2091007025","https://openalex.org/W2099192586","https://openalex.org/W2104933073","https://openalex.org/W2126996952","https://openalex.org/W2130745297","https://openalex.org/W2132791018","https://openalex.org/W2137446621","https://openalex.org/W2148143831","https://openalex.org/W2150755264","https://openalex.org/W2157305948","https://openalex.org/W2163947777","https://openalex.org/W2168572310","https://openalex.org/W2471991522","https://openalex.org/W2518774129","https://openalex.org/W2531607313","https://openalex.org/W2562319768","https://openalex.org/W2601726217","https://openalex.org/W2763110968","https://openalex.org/W2766296277","https://openalex.org/W2766742395","https://openalex.org/W2798869704","https://openalex.org/W2829536470","https://openalex.org/W2884975621","https://openalex.org/W2896805537","https://openalex.org/W2925326750","https://openalex.org/W2928048063","https://openalex.org/W2948219206","https://openalex.org/W2952448206","https://openalex.org/W2969260977","https://openalex.org/W2973351188","https://openalex.org/W2978341006","https://openalex.org/W2981905647","https://openalex.org/W3000057629","https://openalex.org/W3015967287","https://openalex.org/W3025519219","https://openalex.org/W3033266910","https://openalex.org/W3039655752","https://openalex.org/W3043110585","https://openalex.org/W3091985450","https://openalex.org/W3120093105","https://openalex.org/W3135420375","https://openalex.org/W3136451693","https://openalex.org/W3140120701","https://openalex.org/W4224213643","https://openalex.org/W4225141704","https://openalex.org/W4282972746","https://openalex.org/W4393301322","https://openalex.org/W6863082409"],"related_works":["https://openalex.org/W2766503024","https://openalex.org/W2781247653","https://openalex.org/W4206637278","https://openalex.org/W4386005305","https://openalex.org/W4386214543","https://openalex.org/W3082051559","https://openalex.org/W1969988626","https://openalex.org/W1682621979","https://openalex.org/W2141301039","https://openalex.org/W3173198409"],"abstract_inverted_index":{"Data":[0],"imbalance":[1],"is":[2,117,222],"a":[3,82],"common":[4],"phenomenon":[5],"in":[6,60,128],"machine":[7],"learning.":[8],"In":[9,187],"the":[10,41,54,61,77,96,102,108,112,122,129,150,155,176,192,198,209,215,226],"imbalanced":[11,109],"data":[12],"classification,":[13],"minority":[14,27,36,46,49,84,138],"samples":[15,50,59],"are":[16,182,201],"far":[17],"less":[18],"than":[19,154,208,225],"majority":[20,136],"samples,":[21,139],"which":[22,200],"makes":[23],"it":[24],"difficult":[25],"for":[26],"to":[28,45,66,106,119,134],"be":[29],"effectively":[30],"learned":[31],"by":[32,47,180],"classifiers.":[33],"A":[34],"synthetic":[35,83],"oversampling":[37,85,144,157,211,228],"technique":[38,86],"(SMOTE)":[39],"improves":[40],"sensitivity":[42,167],"of":[43,56,166,171,197],"classifiers":[44],"synthesizing":[48,57],"without":[51],"repetition.":[52],"However,":[53],"process":[55],"new":[58],"SMOTE":[62],"algorithm":[63,99,116],"may":[64],"lead":[65],"problems":[67],"such":[68],"as":[69],"\"noisy":[70,123],"samples\"":[71,124,127],"and":[72,125,137,168,184,194,203],"\"boundary":[73,126],"samples.\"":[74],"Based":[75],"on":[76,88,101,159,175],"above":[78],"description,":[79],"we":[80,140,189],"propose":[81],"based":[87,100],"Gaussian":[89,103],"mixture":[90,104],"model":[91,105],"filtering":[92,115],"(GMF-SMOTE).":[93],"GMF-SMOTE":[94,151,181,221],"uses":[95],"expected":[97,113],"maximum":[98,114],"group":[107],"data.":[110],"Then,":[111],"used":[118],"filter":[120],"out":[121],"subclasses":[130],"after":[131],"grouping.":[132],"Finally,":[133],"synthesize":[135],"design":[141],"two":[142,216],"dynamic":[143],"ratios.":[145],"Experimental":[146],"results":[147],"show":[148,219],"that":[149,220],"performs":[152],"better":[153,207,224],"traditional":[156,210,227],"algorithms":[158],"20":[160],"UCI":[161,177],"datasets.":[162],"The":[163],"population":[164],"averages":[165],"specificity":[169],"indexes":[170,196],"random":[172],"forest":[173],"(RF)":[174],"datasets":[178],"synthesized":[179],"97.49%":[183],"97.02%,":[185],"respectively.":[186],"addition,":[188],"also":[190],"record":[191],"G-mean":[193],"MCC":[195],"RF,":[199],"97.32%":[202],"94.80%,":[204],"respectively,":[205],"significantly":[206,223],"algorithms.":[212,229],"More":[213],"importantly,":[214],"statistical":[217],"tests":[218]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":29},{"year":2023,"cited_by_count":13}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}