{"id":"https://openalex.org/W4414561714","doi":"https://doi.org/10.3390/info16100836","title":"An Automated Domain-Agnostic and Explainable Data Quality Assurance Framework for Energy Analytics and Beyond","display_name":"An Automated Domain-Agnostic and Explainable Data Quality Assurance Framework for Energy Analytics and Beyond","publication_year":2025,"publication_date":"2025-09-26","ids":{"openalex":"https://openalex.org/W4414561714","doi":"https://doi.org/10.3390/info16100836"},"language":"en","primary_location":{"id":"doi:10.3390/info16100836","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16100836","pdf_url":"https://www.mdpi.com/2078-2489/16/10/836/pdf?version=1758897987","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/16/10/836/pdf?version=1758897987","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093397980","display_name":"Bal\u00e1zs Andr\u00e1s Tolnai","orcid":"https://orcid.org/0009-0004-4183-4340"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]},{"id":"https://openalex.org/I184886455","display_name":"Maersk (Denmark)","ror":"https://ror.org/046gbzb64","country_code":"DK","type":"company","lineage":["https://openalex.org/I184886455"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Bal\u00e1zs Andr\u00e1s Tolnai","raw_affiliation_strings":["SDU Center for Energy Informatics, Maersk Mc-Kinney Moeller Institute, The Faculty of Engineering, University of Southern Denmark, 5230 Odense, Denmark"],"raw_orcid":"https://orcid.org/0009-0004-4183-4340","affiliations":[{"raw_affiliation_string":"SDU Center for Energy Informatics, Maersk Mc-Kinney Moeller Institute, The Faculty of Engineering, University of Southern Denmark, 5230 Odense, Denmark","institution_ids":["https://openalex.org/I184886455","https://openalex.org/I177969490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020907182","display_name":"Zhipeng Ma","orcid":"https://orcid.org/0000-0002-4049-539X"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]},{"id":"https://openalex.org/I184886455","display_name":"Maersk (Denmark)","ror":"https://ror.org/046gbzb64","country_code":"DK","type":"company","lineage":["https://openalex.org/I184886455"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zhipeng Ma","raw_affiliation_strings":["SDU Center for Energy Informatics, Maersk Mc-Kinney Moeller Institute, The Faculty of Engineering, University of Southern Denmark, 5230 Odense, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-4049-539X","affiliations":[{"raw_affiliation_string":"SDU Center for Energy Informatics, Maersk Mc-Kinney Moeller Institute, The Faculty of Engineering, University of Southern Denmark, 5230 Odense, Denmark","institution_ids":["https://openalex.org/I184886455","https://openalex.org/I177969490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020850598","display_name":"Bo N\u00f8rregaard J\u00f4rgensen","orcid":"https://orcid.org/0000-0001-5678-6602"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]},{"id":"https://openalex.org/I184886455","display_name":"Maersk (Denmark)","ror":"https://ror.org/046gbzb64","country_code":"DK","type":"company","lineage":["https://openalex.org/I184886455"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Bo N\u00f8rregaard J\u00f8rgensen","raw_affiliation_strings":["SDU Center for Energy Informatics, Maersk Mc-Kinney Moeller Institute, The Faculty of Engineering, University of Southern Denmark, 5230 Odense, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-5678-6602","affiliations":[{"raw_affiliation_string":"SDU Center for Energy Informatics, Maersk Mc-Kinney Moeller Institute, The Faculty of Engineering, University of Southern Denmark, 5230 Odense, Denmark","institution_ids":["https://openalex.org/I184886455","https://openalex.org/I177969490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076322755","display_name":"Zheng Ma","orcid":"https://orcid.org/0000-0002-9134-1032"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]},{"id":"https://openalex.org/I184886455","display_name":"Maersk (Denmark)","ror":"https://ror.org/046gbzb64","country_code":"DK","type":"company","lineage":["https://openalex.org/I184886455"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Zheng Grace Ma","raw_affiliation_strings":["SDU Center for Energy Informatics, Maersk Mc-Kinney Moeller Institute, The Faculty of Engineering, University of Southern Denmark, 5230 Odense, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-9134-1032","affiliations":[{"raw_affiliation_string":"SDU Center for Energy Informatics, Maersk Mc-Kinney Moeller Institute, The Faculty of Engineering, University of Southern Denmark, 5230 Odense, Denmark","institution_ids":["https://openalex.org/I184886455","https://openalex.org/I177969490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076322755"],"corresponding_institution_ids":["https://openalex.org/I177969490","https://openalex.org/I184886455"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29408946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"10","first_page":"836","last_page":"836"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9927999973297119,"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":0.9927999973297119,"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/T14280","display_name":"Big Data Technologies and Applications","score":0.9728000164031982,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11891","display_name":"Big Data and Business Intelligence","score":0.972599983215332,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.7448999881744385},{"id":"https://openalex.org/keywords/quality-assurance","display_name":"Quality assurance","score":0.6905999779701233},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6876000165939331},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.6575999855995178},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5644999742507935},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5633999705314636},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.49230000376701355},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4885999858379364},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.45899999141693115}],"concepts":[{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.7448999881744385},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.6905999779701233},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6876000165939331},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6678000092506409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6583999991416931},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.6575999855995178},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5644999742507935},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5633999705314636},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.49230000376701355},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4885999858379364},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C92446256","wikidata":"https://www.wikidata.org/wiki/Q3306762","display_name":"Data validation","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3093999922275543},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2775999903678894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2775000035762787},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.26089999079704285},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/info16100836","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16100836","pdf_url":"https://www.mdpi.com/2078-2489/16/10/836/pdf?version=1758897987","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:sdu.dk:openaire/1c328204-eb19-47d5-8246-246cda1c43a6","is_oa":true,"landing_page_url":"https://portal.findresearcher.sdu.dk/da/publications/1c328204-eb19-47d5-8246-246cda1c43a6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400423","display_name":"University of Southern Denmark Research Portal (University of Southern Denmark)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177969490","host_organization_name":"University of Southern Denmark","host_organization_lineage":["https://openalex.org/I177969490"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Tolnai, B A, Ma, Z M, J\u00f8rgensen, B N & Ma, Z G 2025, 'An Automated Domain-Agnostic and Explainable Data Quality Assurance Framework for Energy Analytics and Beyond', Information, vol. 16, no. 10, 836. https://doi.org/10.3390/info16100836","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:doaj.org/article:1d10a288a224458e8a323404a467280e","is_oa":true,"landing_page_url":"https://doaj.org/article/1d10a288a224458e8a323404a467280e","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 16, Iss 10, p 836 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info16100836","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16100836","pdf_url":"https://www.mdpi.com/2078-2489/16/10/836/pdf?version=1758897987","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331736","display_name":"Energiteknologisk udviklings- og demonstrationsprogram","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414561714.pdf","grobid_xml":"https://content.openalex.org/works/W4414561714.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W2097481773","https://openalex.org/W2754029504","https://openalex.org/W2786918196","https://openalex.org/W2889249015","https://openalex.org/W2994947794","https://openalex.org/W3013886221","https://openalex.org/W3033693292","https://openalex.org/W3094252156","https://openalex.org/W3095976090","https://openalex.org/W3102477513","https://openalex.org/W3118434263","https://openalex.org/W3188373407","https://openalex.org/W3215641607","https://openalex.org/W4221143046","https://openalex.org/W4285082635","https://openalex.org/W4304960649","https://openalex.org/W4310497722","https://openalex.org/W4318049614","https://openalex.org/W4383175740","https://openalex.org/W4386295954","https://openalex.org/W4386753409","https://openalex.org/W4388900149","https://openalex.org/W4390583408","https://openalex.org/W4392858461","https://openalex.org/W4396661265","https://openalex.org/W4399576774","https://openalex.org/W4400307252","https://openalex.org/W4400439311","https://openalex.org/W4401042875","https://openalex.org/W4402036333","https://openalex.org/W4404047123","https://openalex.org/W4404250052","https://openalex.org/W4405577577","https://openalex.org/W4407870456","https://openalex.org/W4408444355","https://openalex.org/W4408567713","https://openalex.org/W4408994876","https://openalex.org/W4411300543","https://openalex.org/W4411442649"],"related_works":[],"abstract_inverted_index":{"Nonintrusive":[0],"load":[1,16],"monitoring":[2],"(NILM)":[3],"relies":[4],"on":[5],"high-resolution":[6],"sensor":[7,91],"data":[8],"to":[9,42,50,57,81,122,181],"disaggregate":[10],"total":[11],"building":[12],"energy":[13,110],"into":[14,130,162],"end-use":[15],"components,":[17],"for":[18,44,52,59,108,216],"example":[19],"HVAC,":[20],"ventilation,":[21],"and":[22,34,54,68,90,119,141,145,152,191,206,213,219],"appliances.":[23],"On":[24],"the":[25,45,60,204],"ADRENALIN":[26],"corpus,":[27],"simple":[28],"NaN":[29],"handling":[30,174],"with":[31],"forward":[32],"fill":[33],"mean":[35],"substitution":[36],"reduced":[37],"average":[38],"NMAE":[39],"from":[40,48,55],"0.82":[41],"0.76":[43],"Bayesian":[46],"baseline,":[47],"0.71":[49],"0.64":[51],"BI-LSTM,":[53],"0.59":[56],"0.53":[58],"Time\u2013Frequency":[61],"Mask":[62],"(TFM)":[63],"model,":[64,157],"across":[65,199],"nine":[66],"buildings":[67],"four":[69],"temporal":[70],"resolutions.":[71],"However,":[72],"many":[73],"NILM":[74,139,228],"models":[75],"still":[76],"show":[77],"degraded":[78],"accuracy":[79],"due":[80],"unresolved":[82],"data-quality":[83,105],"issues,":[84],"especially":[85],"missing":[86,176],"values,":[87,177],"timestamp":[88,192],"irregularities,":[89],"inconsistencies,":[92],"a":[93,102,153],"limitation":[94],"underexplored":[95],"in":[96],"current":[97],"benchmarks.":[98],"This":[99],"paper":[100],"presents":[101],"fully":[103],"automated":[104],"assurance":[106],"pipeline":[107,113],"time-series":[109,217],"datasets.":[111],"The":[112,166],"performs":[114],"multivariate":[115],"profiling,":[116],"statistical":[117],"analysis,":[118],"threshold-based":[120],"diagnostics":[121,161,226],"compute":[123],"standardized":[124],"quality":[125,170,225],"metrics,":[126],"which":[127,158],"are":[128],"aggregated":[129],"an":[131,210,220],"interpretable":[132,211],"Building":[133],"Quality":[134],"Score":[135],"(BQS)":[136],"that":[137],"predicts":[138],"performance":[140,229],"supports":[142],"dataset":[143],"ranking":[144],"selection.":[146],"Explainability":[147],"is":[148],"provided":[149],"by":[150],"SHAP":[151,188],"lightweight":[154],"large":[155],"language":[156],"turns":[159],"visual":[160],"concise,":[163],"actionable":[164],"narratives.":[165],"study":[167],"evaluates":[168],"practical":[169],"improvement":[171],"through":[172],"systematic":[173],"of":[175,197,208,223],"linking":[178],"metric":[179],"changes":[180],"downstream":[182],"error":[183,198],"reduction.":[184],"Using":[185],"random-forest":[186],"surrogates,":[187],"identifies":[189],"missingness":[190],"irregularity":[193],"as":[194],"dominant":[195],"drivers":[196],"models.":[200],"Core":[201],"contributions":[202],"include":[203],"definition":[205],"validation":[207],"BQS,":[209],"scoring":[212],"explanation":[214],"framework":[215],"quality,":[218],"end-to-end":[221],"evaluation":[222],"how":[224],"affect":[227],"at":[230],"scale.":[231]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}