{"id":"https://openalex.org/W4283715676","doi":"https://doi.org/10.1177/15501329221106935","title":"Research and application of XGBoost in imbalanced data","display_name":"Research and application of XGBoost in imbalanced data","publication_year":2022,"publication_date":"2022-06-01","ids":{"openalex":"https://openalex.org/W4283715676","doi":"https://doi.org/10.1177/15501329221106935"},"language":"en","primary_location":{"id":"doi:10.1177/15501329221106935","is_oa":true,"landing_page_url":"https://doi.org/10.1177/15501329221106935","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/15501329221106935","source":{"id":"https://openalex.org/S64417657","display_name":"International Journal of Distributed Sensor Networks","issn_l":"1550-1329","issn":["1550-1329","1550-1477"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Distributed Sensor Networks","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.sagepub.com/doi/pdf/10.1177/15501329221106935","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ping Zhang","orcid":"https://orcid.org/0000-0002-8500-8727"},"institutions":[{"id":"https://openalex.org/I167383011","display_name":"Henan University of Science and Technology","ror":"https://ror.org/05d80kz58","country_code":"CN","type":"education","lineage":["https://openalex.org/I167383011"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ping Zhang","raw_affiliation_strings":["School of Mathematics and Statistics, Henan University of Science and Technology, Luoyang, China"],"raw_orcid":"https://orcid.org/0000-0002-8500-8727","affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Henan University of Science and Technology, Luoyang, China","institution_ids":["https://openalex.org/I167383011"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041855054","display_name":"Yiqiao Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I167383011","display_name":"Henan University of Science and Technology","ror":"https://ror.org/05d80kz58","country_code":"CN","type":"education","lineage":["https://openalex.org/I167383011"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqiao Jia","raw_affiliation_strings":["School of Mathematics and Statistics, Henan University of Science and Technology, Luoyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Henan University of Science and Technology, Luoyang, China","institution_ids":["https://openalex.org/I167383011"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120393203","display_name":"Youlin Shang","orcid":"https://orcid.org/0000-0002-9859-4040"},"institutions":[{"id":"https://openalex.org/I167383011","display_name":"Henan University of Science and Technology","ror":"https://ror.org/05d80kz58","country_code":"CN","type":"education","lineage":["https://openalex.org/I167383011"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youlin Shang","raw_affiliation_strings":["School of Mathematics and Statistics, Henan University of Science and Technology, Luoyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Henan University of Science and Technology, Luoyang, China","institution_ids":["https://openalex.org/I167383011"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I167383011"],"apc_list":{"value":2200,"currency":"USD","value_usd":2200},"apc_paid":{"value":2200,"currency":"USD","value_usd":2200},"fwci":28.5867,"has_fulltext":false,"cited_by_count":238,"citation_normalized_percentile":{"value":0.99734786,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"18","issue":"6","first_page":"155013292211069","last_page":"155013292211069"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9818999767303467,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8461679220199585},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5381532311439514},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5281414985656738},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5178685188293457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5130985975265503},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5082959532737732},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4396042823791504},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4335312843322754},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.41591113805770874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8461679220199585},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5381532311439514},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5281414985656738},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5178685188293457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5130985975265503},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5082959532737732},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4396042823791504},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4335312843322754},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.41591113805770874},{"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1177/15501329221106935","is_oa":true,"landing_page_url":"https://doi.org/10.1177/15501329221106935","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/15501329221106935","source":{"id":"https://openalex.org/S64417657","display_name":"International Journal of Distributed Sensor Networks","issn_l":"1550-1329","issn":["1550-1329","1550-1477"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Distributed Sensor Networks","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:sae:intdis:v:18:y:2022:i:6:p:15501329221106935","is_oa":false,"landing_page_url":"https://journals.sagepub.com/doi/10.1177/15501329221106935","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:d237e5f4e2dc4342b637598e53bbfe7a","is_oa":false,"landing_page_url":"https://doaj.org/article/d237e5f4e2dc4342b637598e53bbfe7a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Distributed Sensor Networks, Vol 18 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1177/15501329221106935","is_oa":true,"landing_page_url":"https://doi.org/10.1177/15501329221106935","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/15501329221106935","source":{"id":"https://openalex.org/S64417657","display_name":"International Journal of Distributed Sensor Networks","issn_l":"1550-1329","issn":["1550-1329","1550-1477"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Distributed Sensor Networks","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2416943596","display_name":"\u57fa\u4e8e\u6ee4\u5b50\u548c\u8f85\u52a9\u51fd\u6570\u7684\u5168\u5c40\u4f18\u5316\u7b97\u6cd5\u53ca\u5e94\u7528\u7814\u7a76","funder_award_id":"12071112","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5222901678","display_name":"\u975e\u7ebf\u6027\u7ea6\u675f\u5168\u5c40\u4f18\u5316\u7684\u65b0\u65b9\u6cd5\u7814\u7a76","funder_award_id":"11471102","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"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4283715676.pdf"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2096945460","https://openalex.org/W2104167780","https://openalex.org/W2122825543","https://openalex.org/W2148143831","https://openalex.org/W2384341180","https://openalex.org/W2914874661","https://openalex.org/W3088316021","https://openalex.org/W3136335490","https://openalex.org/W3183778643","https://openalex.org/W3186655196"],"related_works":["https://openalex.org/W2090763504","https://openalex.org/W148178222","https://openalex.org/W2104657898","https://openalex.org/W1948992892","https://openalex.org/W1886884218","https://openalex.org/W1910826599","https://openalex.org/W2012353789","https://openalex.org/W2530420969","https://openalex.org/W2051187167","https://openalex.org/W4404691825"],"abstract_inverted_index":{"As":[0],"a":[1,47],"new":[2],"and":[3,46,54,67,74,85,97,114,128,137,152],"efficient":[4],"ensemble":[5,55],"learning":[6,56],"algorithm,":[7],"XGBoost":[8,82],"has":[9],"been":[10],"widely":[11],"applied":[12],"for":[13,71],"its":[14,18],"multitudinous":[15],"advantages,":[16],"but":[17],"classification":[19,48,106,131],"effect":[20],"in":[21],"the":[22,41,77,88,91,100,109,112,117,130,144,150,155],"case":[23],"of":[24,44,133,154],"data":[25,72,146],"imbalance":[26],"is":[27,57,62],"often":[28],"not":[29],"ideal.":[30],"Aiming":[31],"at":[32],"this":[33],"problem,":[34],"an":[35],"attempt":[36],"was":[37],"made":[38],"to":[39,63,104,126],"optimize":[40],"regularization":[42],"term":[43],"XGBoost,":[45],"algorithm":[49,103,138],"based":[50,80],"on":[51,81,143],"mixed":[52],"sampling":[53,135],"proposed.":[58],"The":[59,140],"main":[60],"idea":[61],"combine":[64],"SVM-SMOTE":[65],"over-sampling":[66],"EasyEnsemble":[68],"under-sampling":[69],"technologies":[70],"processing,":[73],"then":[75],"obtain":[76],"final":[78],"model":[79],"by":[83],"training":[84],"ensemble.":[86],"At":[87],"same":[89],"time,":[90],"optimal":[92],"parameters":[93],"are":[94,121],"automatically":[95],"searched":[96],"adjusted":[98],"through":[99],"Bayesian":[101],"optimization":[102],"realize":[105],"prediction.":[107],"In":[108],"experimental":[110,141],"stage,":[111],"G-mean":[113],"area":[115],"under":[116],"curve":[118],"(AUC)":[119],"values":[120],"used":[122],"as":[123],"evaluation":[124],"indicators":[125],"compare":[127],"analyze":[129],"performance":[132],"different":[134],"methods":[136],"models.":[139],"results":[142],"public":[145],"set":[147],"also":[148],"verify":[149],"feasibility":[151],"effectiveness":[153],"proposed":[156],"algorithm.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":32},{"year":2025,"cited_by_count":129},{"year":2024,"cited_by_count":55},{"year":2023,"cited_by_count":22}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}