{"id":"https://openalex.org/W4406459650","doi":"https://doi.org/10.1109/bigdata62323.2024.10825889","title":"AGO-FT: An adaptive guided oversampling based on fast space division and trustworthy sampling space for imbalanced noisy datasets","display_name":"AGO-FT: An adaptive guided oversampling based on fast space division and trustworthy sampling space for imbalanced noisy datasets","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406459650","doi":"https://doi.org/10.1109/bigdata62323.2024.10825889"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5101413148","display_name":"Yi Deng","orcid":"https://orcid.org/0000-0001-5385-2408"},"institutions":[{"id":"https://openalex.org/I126924076","display_name":"Chongqing Normal University","ror":"https://ror.org/01dcw5w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I126924076"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Deng","raw_affiliation_strings":["Chongqing Normal University,School of Computer and Information Science,Chongqing,China"],"affiliations":[{"raw_affiliation_string":"Chongqing Normal University,School of Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I126924076"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340964","display_name":"Min Wu","orcid":"https://orcid.org/0000-0003-0977-3600"},"institutions":[{"id":"https://openalex.org/I126924076","display_name":"Chongqing Normal University","ror":"https://ror.org/01dcw5w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I126924076"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Wu","raw_affiliation_strings":["Chongqing Normal University,Wisdom Education Research Institute,Chongqing,China"],"affiliations":[{"raw_affiliation_string":"Chongqing Normal University,Wisdom Education Research Institute,Chongqing,China","institution_ids":["https://openalex.org/I126924076"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015521101","display_name":"Yan Ma","orcid":"https://orcid.org/0000-0002-7866-0354"},"institutions":[{"id":"https://openalex.org/I126924076","display_name":"Chongqing Normal University","ror":"https://ror.org/01dcw5w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I126924076"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Ma","raw_affiliation_strings":["Chongqing Normal University,Institute of Smart Education,Chongqing,China"],"affiliations":[{"raw_affiliation_string":"Chongqing Normal University,Institute of Smart Education,Chongqing,China","institution_ids":["https://openalex.org/I126924076"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101413148"],"corresponding_institution_ids":["https://openalex.org/I126924076"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23730019,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"529","last_page":"538"},"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":0.9883999824523926,"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":0.9853000044822693,"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":0.9571744203567505},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7164236307144165},{"id":"https://openalex.org/keywords/division","display_name":"Division (mathematics)","score":0.7050414681434631},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.6827693581581116},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.655963659286499},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5962726473808289},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49206990003585815},{"id":"https://openalex.org/keywords/adaptive-sampling","display_name":"Adaptive sampling","score":0.418089359998703},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.341874897480011},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3265842795372009},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20757654309272766},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12164387106895447},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10813218355178833},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07680192589759827},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.06334036588668823},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.06112542748451233}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.9571744203567505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7164236307144165},{"id":"https://openalex.org/C60798267","wikidata":"https://www.wikidata.org/wiki/Q1226939","display_name":"Division (mathematics)","level":2,"score":0.7050414681434631},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.6827693581581116},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.655963659286499},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5962726473808289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49206990003585815},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.418089359998703},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.341874897480011},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3265842795372009},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20757654309272766},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12164387106895447},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10813218355178833},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07680192589759827},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.06334036588668823},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.06112542748451233},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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":36,"referenced_works":["https://openalex.org/W1993220166","https://openalex.org/W1996523702","https://openalex.org/W2071785112","https://openalex.org/W2087240369","https://openalex.org/W2104933073","https://openalex.org/W2107138773","https://openalex.org/W2132791018","https://openalex.org/W2148143831","https://openalex.org/W2200953330","https://openalex.org/W2800788706","https://openalex.org/W2895410835","https://openalex.org/W2963613787","https://openalex.org/W2966679659","https://openalex.org/W3015967287","https://openalex.org/W3093212523","https://openalex.org/W3138064939","https://openalex.org/W3159359277","https://openalex.org/W3170931228","https://openalex.org/W3180223285","https://openalex.org/W3184234571","https://openalex.org/W3207618611","https://openalex.org/W4220925147","https://openalex.org/W4221077026","https://openalex.org/W4224217826","https://openalex.org/W4282593497","https://openalex.org/W4283269761","https://openalex.org/W4284693129","https://openalex.org/W4318147432","https://openalex.org/W4318147596","https://openalex.org/W4318147815","https://openalex.org/W4318147847","https://openalex.org/W4318185117","https://openalex.org/W4386955404","https://openalex.org/W4388923613","https://openalex.org/W4391094998","https://openalex.org/W4391096606"],"related_works":["https://openalex.org/W2152863486","https://openalex.org/W2038693912","https://openalex.org/W1991602789","https://openalex.org/W1582396021","https://openalex.org/W1988359706","https://openalex.org/W312558119","https://openalex.org/W4210985407","https://openalex.org/W2335441444","https://openalex.org/W138014004","https://openalex.org/W2075598034"],"abstract_inverted_index":{"The":[0],"prevalent":[1,33],"imbalance":[2],"can":[3,100],"cause":[4],"big":[5],"data":[6,44],"models":[7],"to":[8,14,41,151,171,177,217,239],"favor":[9],"the":[10,18,32,38,43,49,68,76,84,96,145,193,210,224,227],"common":[11],"class,":[12,21],"leading":[13],"difficulties":[15],"in":[16,175],"identifying":[17],"minority":[19,39],"value":[20],"deteriorating":[22],"their":[23],"overall":[24],"performance":[25,180],"and":[26,83,92,109,130,222,248],"decision-making.":[27],"Oversampling":[28],"methods":[29,71],"have":[30],"become":[31],"strategy":[34,142],"nowadays":[35],"by":[36,75,95],"synthesizing":[37,104],"instances":[40,60,105,220],"balance":[42],"distribution.":[45],"Nevertheless,":[46],"most":[47],"of":[48,78,89,195,212,226],"current":[50,69,97],"oversampling":[51,70,123,229,242],"mechanisms":[52,99],"are":[53,72],"based":[54,106,125,143,157,198,208],"on":[55,107,126,144,158,199,209,244],"SMOTE,":[56],"which":[57],"synthesizes":[58],"new":[59,205],"randomly":[61],"with":[62,187],"arbitrarily":[63],"chosen":[64],"k-nearest":[65,80,90],"neighbors.":[66],"Consequently,":[67],"readily":[73],"constrained":[74],"optimization":[77],"suitable":[79],"neighbor":[81],"hyperparameters,":[82],"unrestricted":[85],"blind":[86],"random":[87,114,147],"selection":[88],"neighbors":[91],"instance":[93],"synthesis":[94,221],"sampling":[98,132,185],"degrade":[101],"performance.":[102],"Specifically,":[103],"universal":[108],"unavoidable":[110],"noise":[111,166,174],"introduces":[112],"chaotic":[113],"generalization.":[115],"To":[116],"fill":[117],"these":[118],"gaps,":[119],"an":[120],"adaptive":[121],"guided":[122],"(AGO-FT)":[124],"fast":[127,138],"space":[128,133,140,154],"division":[129],"plausible":[131,200],"is":[134,149,169,190,215,237],"proposed.":[135],"Firstly,":[136],"a":[137,162,183,204],"sample":[139,153,196],"partitioning":[141],"complete":[146],"forest":[148],"proposed":[150,216],"derive":[152],"information":[155],"adaptively":[156],"dataset":[159],"specificity.":[160],"Secondly,":[161],"spatial":[163,213],"information-based":[164],"dataset-specific":[165],"detection":[167],"method":[168],"employed":[170],"detect":[172],"anomalous":[173],"order":[176],"prevent":[178],"further":[179],"degradation.":[181],"Then,":[182],"parameter-free":[184],"neighborhood":[186],"high":[188],"confidence":[189],"derived":[191],"from":[192],"set":[194],"spaces":[197],"frequency":[201],"filtering.":[202],"Finally,":[203],"probability":[206],"weight":[207],"degree":[211],"confusion":[214],"guide":[218],"rational":[219],"alleviate":[223],"blindness":[225],"SMOTE":[228],"mechanism.":[230],"Extensive":[231],"experimental":[232],"results":[233],"demonstrate":[234],"that":[235],"AGO-FT":[236],"superior":[238],"8":[240],"baseline":[241],"algorithms":[243],"13":[245],"real-world":[246],"datasets":[247],"four":[249],"classical":[250],"classifiers.":[251]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}