{"id":"https://openalex.org/W4388280086","doi":"https://doi.org/10.1109/icbase59196.2023.10303096","title":"An unbalanced data classification method based on improved SMOTE","display_name":"An unbalanced data classification method based on improved SMOTE","publication_year":2023,"publication_date":"2023-08-25","ids":{"openalex":"https://openalex.org/W4388280086","doi":"https://doi.org/10.1109/icbase59196.2023.10303096"},"language":"en","primary_location":{"id":"doi:10.1109/icbase59196.2023.10303096","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icbase59196.2023.10303096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 4th International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE)","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/A5111068220","display_name":"Fangrui Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139765","display_name":"Beijing Computing Center","ror":"https://ror.org/047r47y76","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210139765"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fangrui Shi","raw_affiliation_strings":["Beijing Institute of Computing and Communication,Beijing,China","Beijing Institute of Computing and Communication, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Computing and Communication,Beijing,China","institution_ids":["https://openalex.org/I4210139765"]},{"raw_affiliation_string":"Beijing Institute of Computing and Communication, Beijing, China","institution_ids":["https://openalex.org/I4210139765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057196653","display_name":"Guochao Fan","orcid":"https://orcid.org/0000-0003-3265-5602"},"institutions":[{"id":"https://openalex.org/I4210139765","display_name":"Beijing Computing Center","ror":"https://ror.org/047r47y76","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210139765"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guochao Fan","raw_affiliation_strings":["Beijing Institute of Computing and Communication,Beijing,China","Beijing Institute of Computing and Communication, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Computing and Communication,Beijing,China","institution_ids":["https://openalex.org/I4210139765"]},{"raw_affiliation_string":"Beijing Institute of Computing and Communication, Beijing, China","institution_ids":["https://openalex.org/I4210139765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5111068220"],"corresponding_institution_ids":["https://openalex.org/I4210139765"],"apc_list":null,"apc_paid":null,"fwci":0.1751,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57315396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"29","issue":null,"first_page":"55","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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/T11443","display_name":"Advanced Statistical Process Monitoring","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9702000021934509,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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":0.7510908842086792},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6445242762565613},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.5765396356582642},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.559440016746521},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5104426145553589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5074324011802673},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.485443651676178},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4599015712738037},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4269748032093048},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.41900402307510376},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41484585404396057},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34180325269699097},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.1312510371208191},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08492136001586914},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.07118621468544006}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7510908842086792},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6445242762565613},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.5765396356582642},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.559440016746521},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5104426145553589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5074324011802673},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.485443651676178},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4599015712738037},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4269748032093048},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.41900402307510376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41484585404396057},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34180325269699097},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.1312510371208191},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08492136001586914},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.07118621468544006},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icbase59196.2023.10303096","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icbase59196.2023.10303096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 4th International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1967320885","https://openalex.org/W2098254218","https://openalex.org/W2148143831","https://openalex.org/W2763619424","https://openalex.org/W2769758779","https://openalex.org/W2899446476","https://openalex.org/W3003185269","https://openalex.org/W3044574934","https://openalex.org/W4292170267","https://openalex.org/W4366992038","https://openalex.org/W6745674421"],"related_works":["https://openalex.org/W3196098778","https://openalex.org/W3211250490","https://openalex.org/W4360584310","https://openalex.org/W2981515171","https://openalex.org/W80466363","https://openalex.org/W2924282518","https://openalex.org/W3080872054","https://openalex.org/W4386210978","https://openalex.org/W4237698281","https://openalex.org/W4283808318"],"abstract_inverted_index":{"With":[0],"the":[1,42,48,99,123,129,136,151,162,211],"continuous":[2],"development":[3],"of":[4,17,22,44,50,65,101,135,184,213],"modern":[5],"industry,":[6],"product":[7,18,26,51,102,214],"quality":[8,19,27,52,103,215],"control":[9],"standards":[10],"have":[11],"become":[12],"increasingly":[13],"stringent.":[14],"The":[15,54],"classification":[16,34,49,76,100,112,169],"characteristics":[20],"is":[21,30,60,71],"paramount":[23],"importance":[24],"to":[25,32,40,74,121,132,147,160,210],"control.":[28],"It":[29],"necessary":[31],"improve":[33],"methods":[35,120,170],"specifically":[36],"for":[37,90,158],"imbalanced":[38,68,167],"data":[39,45,69,110,139,168],"solve":[41],"issue":[43],"imbalance":[46],"in":[47,81,98,140],"characteristics.":[53,104],"Synthetic":[55],"Minority":[56],"Over-Sampling":[57],"Technique":[58],"(SMOTE)":[59],"a":[61,177,200],"mature":[62],"algorithm":[63,113,131,175],"capable":[64],"effectively":[66],"classifying":[67],"and":[70,85,92,118,171,196],"widely":[72],"applied":[73],"various":[75],"problems.":[77],"However,":[78],"its":[79],"performance":[80],"handling":[82],"class":[83,138,141],"overlap":[84,142],"noise":[86,149],"issues":[87,94],"leaves":[88],"room":[89],"improvement,":[91],"these":[93],"are":[95],"often":[96],"prevalent":[97],"This":[105,206],"paper":[106],"proposes":[107],"an":[108],"improved":[109,173],"sampling":[111],"based":[114],"on":[115,181],"KNN":[116,130],"under-sampling":[117],"DBSCAN":[119,146],"enhance":[122],"SMOTE":[124,157],"algorithm.":[125],"We":[126,164],"first":[127],"employ":[128],"remove":[133],"part":[134],"majority":[137],"regions,":[143],"then":[144],"introduce":[145],"eliminate":[148],"within":[150],"sample":[152],"data.":[153,163],"Lastly,":[154],"we":[155],"apply":[156],"over-sampling":[159],"balance":[161],"compare":[165],"common":[166],"our":[172,192],"KD-SMOTE":[174],"using":[176],"decision":[178],"tree":[179],"classifier":[180],"five":[182],"groups":[183],"public":[185],"UCI":[186],"datasets.":[187],"Experimental":[188],"results":[189],"indicate":[190],"that":[191],"method":[193,207],"improves":[194],"AUC":[195],"other":[197],"metrics,":[198],"providing":[199],"significant":[201],"enhancement":[202],"over":[203],"existing":[204],"algorithms.":[205],"better":[208],"caters":[209],"needs":[212],"characteristic":[216],"classification.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}