{"id":"https://openalex.org/W4281838772","doi":"https://doi.org/10.1145/3531232.3531262","title":"A Novel Under-sampling Method with Gaussian Mixture and Jensen-Shannon Divergence","display_name":"A Novel Under-sampling Method with Gaussian Mixture and Jensen-Shannon Divergence","publication_year":2022,"publication_date":"2022-03-18","ids":{"openalex":"https://openalex.org/W4281838772","doi":"https://doi.org/10.1145/3531232.3531262"},"language":"en","primary_location":{"id":"doi:10.1145/3531232.3531262","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3531232.3531262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 4th International Conference on Image, Video and Signal Processing","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/A5033300763","display_name":"Xueling Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xueling Pan","raw_affiliation_strings":["Beijing Key Lab of Data Mining for Petroleum Data, China University of Petroleum, China and College of Information Science and Engineering, China University of Petroleum, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Lab of Data Mining for Petroleum Data, China University of Petroleum, China and College of Information Science and Engineering, China University of Petroleum, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102844195","display_name":"Guohe Li","orcid":"https://orcid.org/0009-0008-9982-4478"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohe Li","raw_affiliation_strings":["Beijing Key Lab of Data Mining for Petroleum Data, China University of Petroleum, China and Department of Computer Science and Technology, China University of Petroleum-Beijing at Keramay, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Lab of Data Mining for Petroleum Data, China University of Petroleum, China and Department of Computer Science and Technology, China University of Petroleum-Beijing at Keramay, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053147206","display_name":"Shunxin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shunxin Liu","raw_affiliation_strings":["Beijing Key Lab of Data Mining for Petroleum Data, China University of Petroleum, China and College of Information Science and Engineering, China University of Petroleum, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Lab of Data Mining for Petroleum Data, China University of Petroleum, China and College of Information Science and Engineering, China University of Petroleum, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039834267","display_name":"Qiuyue Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuyue Yu","raw_affiliation_strings":["Beijing Key Lab of Data Mining for Petroleum Data, China University of Petroleum, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Lab of Data Mining for Petroleum Data, China University of Petroleum, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100414025","display_name":"Ying Li","orcid":"https://orcid.org/0000-0001-6440-3122"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Li","raw_affiliation_strings":["Beijing Key Lab of Data Mining for Petroleum Data, China University of Petroleum, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Lab of Data Mining for Petroleum Data, China University of Petroleum, China","institution_ids":["https://openalex.org/I204553293"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5033300763"],"corresponding_institution_ids":["https://openalex.org/I204553293"],"apc_list":null,"apc_paid":null,"fwci":0.1327,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50747537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"204","last_page":"210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9284999966621399,"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"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9182999730110168,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.6817567348480225},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6637749671936035},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6083704829216003},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5661965608596802},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5163106322288513},{"id":"https://openalex.org/keywords/cluster-sampling","display_name":"Cluster sampling","score":0.5072764754295349},{"id":"https://openalex.org/keywords/sampling-distribution","display_name":"Sampling distribution","score":0.4790557622909546},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4606243968009949},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.41895413398742676},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4102725684642792},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3965381979942322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39148658514022827},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.36464542150497437}],"concepts":[{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.6817567348480225},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6637749671936035},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6083704829216003},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5661965608596802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5163106322288513},{"id":"https://openalex.org/C183380357","wikidata":"https://www.wikidata.org/wiki/Q1776598","display_name":"Cluster sampling","level":3,"score":0.5072764754295349},{"id":"https://openalex.org/C167723999","wikidata":"https://www.wikidata.org/wiki/Q3773214","display_name":"Sampling distribution","level":2,"score":0.4790557622909546},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4606243968009949},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.41895413398742676},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4102725684642792},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3965381979942322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39148658514022827},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.36464542150497437},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3531232.3531262","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3531232.3531262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 4th International Conference on Image, Video and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1966129222","https://openalex.org/W2000206219","https://openalex.org/W2072398821","https://openalex.org/W2118978333","https://openalex.org/W2132791018","https://openalex.org/W2422369062","https://openalex.org/W2624913439","https://openalex.org/W2753605260","https://openalex.org/W2766296277","https://openalex.org/W2769758779","https://openalex.org/W2948219206","https://openalex.org/W2993620107","https://openalex.org/W3046387678","https://openalex.org/W4379510236","https://openalex.org/W6677954473","https://openalex.org/W6681236446","https://openalex.org/W6997115715"],"related_works":["https://openalex.org/W3208095355","https://openalex.org/W2177370417","https://openalex.org/W1975321310","https://openalex.org/W2052507016","https://openalex.org/W2180461068","https://openalex.org/W2051816080","https://openalex.org/W1952261593","https://openalex.org/W1981004928","https://openalex.org/W1578916557","https://openalex.org/W4256404793"],"abstract_inverted_index":{"Due":[0],"to":[1,95,113,127,140],"bias":[2],"towards":[3],"major":[4],"class":[5,99],"samples,":[6],"the":[7,23,32,38,46,53,61,66,79,97,105,120,129,135,142,151,156,161],"traditional":[8],"classifier":[9],"cannot":[10,56],"obtain":[11],"excellent":[12],"performance":[13],"in":[14,26,60,69,109],"imbalanced":[15],"data.":[16],"The":[17,146],"under-sampling":[18,33,76],"approach":[19,77],"is":[20,138],"one":[21],"of":[22,31,43,107,125,131,144],"effective":[24],"methods":[25,34],"imbalance":[27,48,157],"classification.":[28],"Nowadays,":[29],"most":[30],"do":[35],"not":[36],"consider":[37],"global":[39,121],"and":[40,45,83,122,159],"local":[41,123],"distribution":[42,124],"samples":[44,126],"intra-class":[47],"problem":[49,158],"simultaneously.":[50],"In":[51,116],"addition,":[52,117],"sampling":[54,108],"quantity":[55],"be":[57],"adjusted":[58],"adaptively":[59],"practical":[62],"application.":[63],"To":[64],"handle":[65],"above":[67],"problems,":[68],"this":[70],"paper,":[71],"we":[72],"propose":[73],"a":[74,91],"novel":[75],"with":[78],"Gaussian":[80,92],"mixture":[81,93],"model":[82,94],"Jensen-Shannon":[84,136],"divergence,":[85],"called":[86],"GD-US.":[87],"Firstly,":[88],"it":[89,103],"utilizes":[90],"cluster":[96,111],"majority":[98],"samples.":[100,133],"And":[101],"then,":[102],"calculates":[104],"number":[106,143],"each":[110],"according":[112],"its":[114],"sparsity.":[115],"GD-US":[118],"adopts":[119],"decide":[128],"probability":[130],"deleting":[132],"Eventually,":[134],"divergence":[137],"used":[139],"control":[141],"sampling.":[145],"experimental":[147],"results":[148],"show":[149],"that":[150],"proposal":[152],"can":[153],"help":[154],"solve":[155],"enhance":[160],"classification":[162],"accuracy.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}