{"id":"https://openalex.org/W4409710348","doi":"https://doi.org/10.3389/fdata.2025.1542483","title":"An oversampling-undersampling strategy for large-scale data linkage","display_name":"An oversampling-undersampling strategy for large-scale data linkage","publication_year":2025,"publication_date":"2025-04-23","ids":{"openalex":"https://openalex.org/W4409710348","doi":"https://doi.org/10.3389/fdata.2025.1542483","pmid":"https://pubmed.ncbi.nlm.nih.gov/40336553"},"language":"en","primary_location":{"id":"doi:10.3389/fdata.2025.1542483","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2025.1542483","pdf_url":"https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2025.1542483/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2025.1542483/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037960046","display_name":"Hossein Hassani","orcid":"https://orcid.org/0000-0003-0897-8663"},"institutions":[{"id":"https://openalex.org/I1317774081","display_name":"International Institute for Applied Systems Analysis","ror":"https://ror.org/02wfhk785","country_code":"AT","type":"nonprofit","lineage":["https://openalex.org/I1317774081"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Hossein Hassani","raw_affiliation_strings":["International Institute for Applied Systems Analysis (IIASA), Laxenburg, Austria"],"affiliations":[{"raw_affiliation_string":"International Institute for Applied Systems Analysis (IIASA), Laxenburg, Austria","institution_ids":["https://openalex.org/I1317774081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051084626","display_name":"Mohammad Reza Entezarian","orcid":null},"institutions":[{"id":"https://openalex.org/I48379061","display_name":"Shahid Beheshti University","ror":"https://ror.org/0091vmj44","country_code":"IR","type":"education","lineage":["https://openalex.org/I48379061"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mohammad Reza Entezarian","raw_affiliation_strings":["Department of Statistics, Shahid Beheshti University, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Shahid Beheshti University, Tehran, Iran","institution_ids":["https://openalex.org/I48379061"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117268295","display_name":"Sara Zaeimzadeh","orcid":null},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Sara Zaeimzadeh","raw_affiliation_strings":["Department of Statistics, University of Tehran, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092188289","display_name":"Leila Marvian Mashhad","orcid":"https://orcid.org/0009-0009-1620-5346"},"institutions":[{"id":"https://openalex.org/I4210088705","display_name":"Imam Reza International University","ror":"https://ror.org/007jfm765","country_code":"IR","type":"education","lineage":["https://openalex.org/I4210088705"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Leila Marvian","raw_affiliation_strings":["Big Data Lab, Imam Reza International University, Mashhad, Iran"],"affiliations":[{"raw_affiliation_string":"Big Data Lab, Imam Reza International University, Mashhad, Iran","institution_ids":["https://openalex.org/I4210088705"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043358396","display_name":"Nadejda Komendantova","orcid":"https://orcid.org/0000-0003-2568-6179"},"institutions":[{"id":"https://openalex.org/I1317774081","display_name":"International Institute for Applied Systems Analysis","ror":"https://ror.org/02wfhk785","country_code":"AT","type":"nonprofit","lineage":["https://openalex.org/I1317774081"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Nadejda Komendantova","raw_affiliation_strings":["International Institute for Applied Systems Analysis (IIASA), Laxenburg, Austria"],"affiliations":[{"raw_affiliation_string":"International Institute for Applied Systems Analysis (IIASA), Laxenburg, Austria","institution_ids":["https://openalex.org/I1317774081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5043358396"],"corresponding_institution_ids":["https://openalex.org/I1317774081"],"apc_list":{"value":1150,"currency":"USD","value_usd":1150},"apc_paid":{"value":1150,"currency":"USD","value_usd":1150},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09197447,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":null,"first_page":"1542483","last_page":"1542483"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.902999997138977,"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/undersampling","display_name":"Undersampling","score":0.9838169813156128},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.9028717279434204},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.6870350241661072},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6305233836174011},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5205598473548889},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4981114864349365},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4790724217891693},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4609746038913727},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42625489830970764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3559926450252533},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12488338351249695},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0872967541217804},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07127395272254944}],"concepts":[{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.9838169813156128},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.9028717279434204},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.6870350241661072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6305233836174011},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5205598473548889},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4981114864349365},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4790724217891693},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4609746038913727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42625489830970764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3559926450252533},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12488338351249695},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0872967541217804},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07127395272254944},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3389/fdata.2025.1542483","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2025.1542483","pdf_url":"https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2025.1542483/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},{"id":"pmid:40336553","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40336553","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":"Frontiers in big data","raw_type":null},{"id":"pmh:oai:pure.iiasa.ac.at:20573","is_oa":false,"landing_page_url":"https://pure.iiasa.ac.at/view/iiasa/3410.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4306401423","display_name":"IIASA PURE (International Institute of Applied Systems Analysis)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1317774081","host_organization_name":"International Institute for Applied Systems Analysis","host_organization_lineage":["https://openalex.org/I1317774081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:doaj.org/article:5ee10719d254465db4ab98ff97601575","is_oa":true,"landing_page_url":"https://doaj.org/article/5ee10719d254465db4ab98ff97601575","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Big Data, Vol 8 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:10868502","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12055850","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/fdata.2025.1542483","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2025.1542483","pdf_url":"https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2025.1542483/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320327324","display_name":"International Institute for Applied Systems Analysis","ror":"https://ror.org/02wfhk785"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409710348.pdf","grobid_xml":"https://content.openalex.org/works/W4409710348.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1984606274","https://openalex.org/W2106479238","https://openalex.org/W2540642777","https://openalex.org/W2886848602","https://openalex.org/W2899434936","https://openalex.org/W2936503027","https://openalex.org/W3040266635","https://openalex.org/W3086403350","https://openalex.org/W3131369853","https://openalex.org/W3135550350","https://openalex.org/W3199816041","https://openalex.org/W4311809066","https://openalex.org/W4312125474","https://openalex.org/W4366826709","https://openalex.org/W4380997613","https://openalex.org/W4390104180","https://openalex.org/W4399171839","https://openalex.org/W4399581195","https://openalex.org/W4399671350","https://openalex.org/W4401015350","https://openalex.org/W4403214058","https://openalex.org/W4403216860","https://openalex.org/W4404144498"],"related_works":["https://openalex.org/W32988189","https://openalex.org/W4389233021","https://openalex.org/W4308469503","https://openalex.org/W2904737874","https://openalex.org/W80466363","https://openalex.org/W2399571531","https://openalex.org/W2947132063","https://openalex.org/W4390415670","https://openalex.org/W4288337828","https://openalex.org/W4287816717"],"abstract_inverted_index":{"Effective":[0],"record":[1,38],"linkage":[2,31,39],"in":[3,7],"big":[4],"data,":[5],"particularly":[6],"imbalanced":[8],"datasets,":[9],"is":[10],"a":[11,65],"critical":[12],"yet":[13],"highly":[14],"challenging":[15],"task":[16],"due":[17],"to":[18,29,45,61,63],"the":[19,47,50,55,58,84],"inherent":[20],"complexity":[21],"involved.":[22],"This":[23],"article":[24],"utilizes":[25],"an":[26],"oversampling-undersampling":[27],"strategy":[28],"address":[30],"imbalances,":[32],"enabling":[33],"more":[34,66],"accurate":[35],"and":[36,53,75,87],"efficient":[37],"within":[40],"large-scale":[41],"datasets.":[42],"It":[43],"tries":[44],"increase":[46],"instances":[48],"of":[49,57,89],"minority":[51],"class":[52],"decrease":[54],"dominance":[56],"majority":[59],"classes":[60],"try":[62],"reach":[64],"balanced":[67],"dataset":[68],"that":[69],"can":[70],"be":[71],"used":[72],"for":[73],"training":[74],"testing.":[76],"Sensitivity":[77],"testing":[78],"was":[79],"carried":[80],"out":[81],"by":[82],"varying":[83],"training-test":[85],"ratio":[86],"degree":[88],"imbalance.":[90]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}