{"id":"https://openalex.org/W7223445583","doi":"https://doi.org/10.1038/s41598-026-74767-y","title":"Variable ontology and target-leakage screening in industrial PLC-SCADA data using name-based and behavioral evidence","display_name":"Variable ontology and target-leakage screening in industrial PLC-SCADA data using name-based and behavioral evidence","publication_year":2026,"publication_date":"2026-10-24","ids":{"openalex":"https://openalex.org/W7223445583","doi":"https://doi.org/10.1038/s41598-026-74767-y"},"language":"en","primary_location":{"id":"doi:10.1038/s41598-026-74767-y","doi":"https://doi.org/10.1038/s41598-026-74767-y","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-74767-y","pdf_url":"https://www.nature.com/articles/s41598-026-74767-y_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41598-026-74767-y_reference.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060953724","display_name":"Mustafa \u015eahin","orcid":"https://orcid.org/0009-0006-1701-4566","observed_orcids":["https://orcid.org/0009-0006-1701-4566"]},"institutions":[{"id":"https://openalex.org/I4210154391","display_name":"Hasan Kalyoncu University","ror":"https://ror.org/054g2pw49","country_code":"TR","type":"education","lineage":["https://openalex.org/I4210154391"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Mustafa \u015eahin","raw_affiliation_strings":["Department of Computer Science, Hasan Kalyoncu University, Gaziantep, Turkey"],"raw_orcid":"https://orcid.org/0009-0006-1701-4566","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hasan Kalyoncu University, Gaziantep, Turkey","institution_ids":["https://openalex.org/I4210154391"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004677276","display_name":"Muhammed Fatih Talu","orcid":"https://orcid.org/0000-0003-1166-8404","observed_orcids":["https://orcid.org/0000-0003-1166-8404"]},"institutions":[{"id":"https://openalex.org/I20126385","display_name":"Inonu University","ror":"https://ror.org/04asck240","country_code":"TR","type":"education","lineage":["https://openalex.org/I20126385"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Muhammed Fatih Talu","raw_affiliation_strings":["Department of Computer Science, Inonu University, Malatya, Turkey"],"raw_orcid":"https://orcid.org/0000-0003-1166-8404","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inonu University, Malatya, Turkey","institution_ids":["https://openalex.org/I20126385"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061219896","display_name":"Faruk K\u00dcRKER","orcid":"https://orcid.org/0000-0003-1544-9743","observed_orcids":["https://orcid.org/0000-0003-1544-9743"]},"institutions":[{"id":"https://openalex.org/I198587356","display_name":"Ad\u0131yaman University","ror":"https://ror.org/02s4gkg68","country_code":"TR","type":"education","lineage":["https://openalex.org/I198587356"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Faruk K\u00fcrker","raw_affiliation_strings":["Department of Electrical and Electronics Engineering, Adiyaman University, Adiyaman, Turkey"],"raw_orcid":"https://orcid.org/0000-0003-1544-9743","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronics Engineering, Adiyaman University, Adiyaman, Turkey","institution_ids":["https://openalex.org/I198587356"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001721152","display_name":"Cem Onat","orcid":"https://orcid.org/0000-0002-4295-4860","observed_orcids":["https://orcid.org/0000-0002-4295-4860","https://orcid.org/0000-0002-2886-0470"]},"institutions":[{"id":"https://openalex.org/I198587356","display_name":"Ad\u0131yaman University","ror":"https://ror.org/02s4gkg68","country_code":"TR","type":"education","lineage":["https://openalex.org/I198587356"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Cem Onat","raw_affiliation_strings":["Department of Mechanical Engineering, Adiyaman University, Adiyaman, Turkey"],"raw_orcid":"https://orcid.org/0000-0002-4295-4860","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Adiyaman University, Adiyaman, Turkey","institution_ids":["https://openalex.org/I198587356"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159465465","display_name":"Mustafa \u00d6zt\u00fcrk","orcid":"https://orcid.org/0009-0004-4283-4561","observed_orcids":["https://orcid.org/0009-0004-4283-4561"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mustafa \u00d6zt\u00fcrk","raw_affiliation_strings":["Cimko Cement and Concrete Industry, Ankara, Turkey"],"raw_orcid":"https://orcid.org/0009-0004-4283-4561","affiliations":[{"raw_affiliation_string":"Cimko Cement and Concrete Industry, Ankara, Turkey","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037264235","display_name":"Ahmet Da\u011f","orcid":"https://orcid.org/0009-0000-3223-7166","observed_orcids":["https://orcid.org/0009-0000-3223-7166"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmet Da\u011f","raw_affiliation_strings":["Cimko Cement and Concrete Industry, Adiyaman, Turkey"],"raw_orcid":"https://orcid.org/0009-0000-3223-7166","affiliations":[{"raw_affiliation_string":"Cimko Cement and Concrete Industry, Adiyaman, Turkey","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061219896"],"corresponding_institution_ids":["https://openalex.org/I198587356"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73273639,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T13344","display_name":"Industrial Automation and Control Systems","score":0.0010000000474974513,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10791","display_name":"Advanced Control Systems Optimization","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/target-leakage","display_name":"target leakage","score":0.8289999961853027},{"id":"https://openalex.org/keywords/cement-clinker-production","display_name":"cement clinker production","score":0.6809999942779541},{"id":"https://openalex.org/keywords/expert-validation","display_name":"expert validation","score":0.5699999928474426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6707000136375427},{"id":"https://openalex.org/C12302492","wikidata":"https://www.wikidata.org/wiki/Q1752097","display_name":"Setpoint","level":2,"score":0.6301000118255615},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5213000178337097},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.5184000134468079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5059999823570251},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5008000135421753},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.45750001072883606},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38600000739097595},{"id":"https://openalex.org/C27574286","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Variables","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C153240184","wikidata":"https://www.wikidata.org/wiki/Q3243772","display_name":"Control variable","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27799999713897705},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26600000262260437},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C199163554","wikidata":"https://www.wikidata.org/wiki/Q1681619","display_name":"Univariate","level":3,"score":0.2563999891281128},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1038/s41598-026-74767-y","doi":"https://doi.org/10.1038/s41598-026-74767-y","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-74767-y","pdf_url":"https://www.nature.com/articles/s41598-026-74767-y_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},{"id":"pmh:oai:openaccess.hku.edu.tr:20.500.11782/13901","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11782/13901","pdf_url":null,"source":{"id":"https://openalex.org/S4306401159","display_name":"Hasan Kalyoncu University Institutional Repository (Hasan Kalyoncu University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210154391","host_organization_name":"Hasan Kalyoncu University","host_organization_lineage":["https://openalex.org/I4210154391"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1038/s41598-026-74767-y","doi":"https://doi.org/10.1038/s41598-026-74767-y","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-74767-y","pdf_url":"https://www.nature.com/articles/s41598-026-74767-y_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322626","display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu","ror":"https://ror.org/04w9kkr77"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223445583.pdf","grobid_xml":"https://content.openalex.org/works/W7223445583.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W623776627","https://openalex.org/W1990384678","https://openalex.org/W1996639869","https://openalex.org/W2000651380","https://openalex.org/W2004291985","https://openalex.org/W2014683958","https://openalex.org/W2729884040","https://openalex.org/W2736287575","https://openalex.org/W2759373267","https://openalex.org/W2788572835","https://openalex.org/W2905588001","https://openalex.org/W2909693411","https://openalex.org/W3111529655","https://openalex.org/W3118813946","https://openalex.org/W4226251359","https://openalex.org/W4323315612","https://openalex.org/W4385576721","https://openalex.org/W4396541948","https://openalex.org/W4406085118"],"related_works":["https://openalex.org/W7222635367","https://openalex.org/W7118908262","https://openalex.org/W2594495644","https://openalex.org/W7095779012","https://openalex.org/W7208786044","https://openalex.org/W3173093463","https://openalex.org/W7162662460","https://openalex.org/W7213451813","https://openalex.org/W2416829247","https://openalex.org/W7212039775"],"abstract_inverted_index":{"Abstract":[0],"Contemporary":[1],"cement":[2,126],"plants":[3],"measure":[4],"thousands":[5],"of":[6,12,41,50,124,203,208,227,267,284],"PLC-SCADA":[7,70],"variables,":[8,135,256],"and":[9,20,65,84,136,198,229,248,290],"the":[10,18,45,61,95,120,142,154,169,173,180,186,206,209,224,279,285],"semantics":[11],"those":[13],"variables":[14,43,52,270,286,295],"is":[15,98,117,177],"unclear,":[16],"since":[17],"tags":[19],"labels":[21],"are":[22,190],"usually":[23],"incomplete,":[24],"inconsistent,":[25],"and/or":[26],"deceptive.":[27],"The":[28,114],"problem":[29],"affects":[30],"not":[31],"only":[32],"control-advisory":[33],"systems":[34],"but":[35],"also":[36],"data-driven":[37],"models":[38],"via":[39],"inclusion":[40],"non-manipulated":[42],"into":[44],"decision":[46],"space":[47],"or":[48],"introduction":[49],"target-related":[51],"resulting":[53],"in":[54,192,241],"leakage.":[55,201],"In":[56],"this":[57,93,193],"paper,":[58],"we":[59],"propose":[60],"two-evidence":[62],"variable":[63],"ontology":[64,281],"leakage-auditing":[66],"approach":[67,116],"for":[68,81,105,185,253,282],"industrial":[69,122,187],"data.":[71],"We":[72],"combine":[73],"name-based":[74],"evidence,":[75,78],"behavior-based":[76],"signal":[77,176],"expert":[79,276],"validation":[80],"exceptional":[82],"cases,":[83],"target-leakage":[85],"auditing":[86],"within":[87],"a":[88,101,125,272],"unified":[89],"pre-modelling":[90],"workflow.":[91],"Within":[92],"workflow,":[94],"staircase":[96],"score":[97],"used":[99],"as":[100,179],"lightweight":[102],"behavioral":[103,225],"descriptor":[104],"distinguishing":[106],"piecewise-constant":[107],"setpoint-like":[108,228],"signals":[109,231],"from":[110,212],"continuously":[111,174],"varying":[112],"measurements.":[113],"proposed":[115],"applied":[118],"to":[119,216,296],"real":[121],"dataset":[123],"clinker":[127],"production":[128],"line":[129],"with":[130,244,257,261,278],"2.46":[131],"million":[132],"samples,":[133],"375":[134,255,269],"11":[137],"logged":[138],"operational":[139,161],"days.":[140],"Among":[141],"26":[143],"documented":[144],"control":[145,162,294],"parameters,":[146],"eight":[147],"exhibited":[148],"actively":[149],"changing":[150,175],"setpoint":[151],"behavior":[152],"during":[153],"analyzed":[155],"11-day":[156],"period,":[157],"while":[158],"one":[159],"additional":[160],"was":[163,232,239],"confirmed":[164],"through":[165],"process-engineering":[166],"validation.":[167],"Besides":[168],"label":[170],"anomaly":[171],"where":[172],"labeled":[178],"setpoint,":[181],"three":[182],"leakage":[183,204],"types":[184],"multivariate":[188],"regression":[189],"considered":[191],"paper:":[194],"definitional/mass":[195],"balance,":[196],"component,":[197],"computed":[199],"feature":[200],"Removal":[202],"drops":[205],"performance":[207],"firing-calorie":[210],"model":[211],"R\u00b2":[213,217],"=":[214,218,288],"0.9999":[215],"0.8109.":[219],"Supplementary":[220],"analyses":[221],"showed":[222],"that":[223],"separation":[226],"continuous":[230],"unchanged":[233],"under":[234],"unsupervised":[235],"(Otsu)":[236],"threshold":[237],"selection,":[238],"reproduced":[240],"two":[242],"sub-periods":[243],"different":[245],"logging":[246],"rates,":[247],"required":[249],"about":[250],"21":[251],"s":[252],"all":[254,268,292],"runtime":[258],"scaling":[259],"linearly":[260],"data":[262],"size.":[263],"A":[264],"blinded":[265],"annotation":[266],"by":[271],"second,":[273],"independent":[274],"process":[275],"agreed":[277],"final":[280],"89.3%":[283],"(\u03ba":[287],"0.755)":[289],"assigned":[291],"nine":[293],"CONTROL.":[297]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-25T00:00:00"}
