{"authors":[{"id":"orcid_______::e1b1718fb5598c9c95fb98b529603d86","fullName":"Batic, Djordje","name":"Djordje","surname":"Batic","rank":1,"pid":{"id":{"scheme":"orcid","value":"0000-0002-7647-6641"},"provenance":null}},{"id":"orcid_______::72c91db2225705e9be0068de2b9e2e18","fullName":"Stankovic, Vladimir","name":"Vladimir","surname":"Stankovic","rank":2,"pid":{"id":{"scheme":"orcid","value":"0000-0002-1075-2420"},"provenance":null}},{"id":"orcid_______::71125be661b1711695d1077996b65a61","fullName":"Stankovic, Lina","name":"Lina","surname":"Stankovic","rank":3,"pid":{"id":{"scheme":"orcid","value":"0000-0002-8112-1976"},"provenance":null}}],"openAccessColor":"hybrid","publiclyFunded":false,"eoscIfGuidelines":null,"type":"publication","language":{"code":"eng","label":"English"},"countries":null,"subjects":[{"subject":{"scheme":"keyword","value":"330"},"provenance":null},{"subject":{"scheme":"keyword","value":"000"},"provenance":null},{"subject":{"scheme":"keyword","value":"Electronic computers. Computer science"},"provenance":null},{"subject":{"scheme":"FOS","value":"0202 electrical engineering, electronic engineering, information engineering"},"provenance":null},{"subject":{"scheme":"FOS","value":"02 engineering and technology"},"provenance":null}],"mainTitle":"XNILMBoost: Explainability-informed load disaggregation training enhancement using attribution priors","subTitle":null,"descriptions":["In the ongoing energy transition, characterised by increased reliance on distributed renewable sources and smart grid technologies, the need for advanced and trustworthy artificial intelligence (AI) in energy management systems is crucial. Non-intrusive load monitoring (NILM), a method for inferring individual appliance energy consumption from aggregate smart meter data, has gained prominence for enhancing energy efficiency. However, advanced deep neural network models used in NILM, while effective, raise transparency and trust concerns due to their complexity. This paper introduces a novel explainability-informed NILM training framework, specifically designed for low-frequency NILM. Our approach aligns with principles for trustworthy AI, focusing on human agency and oversight, technical robustness, and transparency, incorporating explainability directly into the training phase of a NILM model. We propose a novel iterative, explainability-informed NILM training algorithm that uses attribution priors to guide model optimization, including implementation and evaluation of the framework across multiple state-of-the-art NILM architectures, namely, convolutional, recurrent, and dilated causal layers. We introduce a novel Robustness-Trust metric to measure joint improvement in predictive and explainability performance, utilizing explainability metrics of faithfulness, robustness and effective complexity while analyzing model predictive performance against NILM-specific regression and classification metrics. Results broadly show that robust models achieve better explainability, while explainability-enhanced models can lead to improved model robustness. Together, our results demonstrate significant improvements in robustness and transparency of NILM systems across various appliances, model architectures, measurement scales, types of buildings, and energy usage patterns. This work paves the way for more transparent and trustworthy deployments in AI-driven energy systems."],"publicationDate":"2025-02-01","publisher":"Elsevier BV","embargoEndDate":null,"sources":["Crossref","Engineering Applications of Artificial Intelligence"],"formats":["text"],"contributors":null,"coverages":null,"bestAccessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/"},"container":{"name":"Engineering Applications of Artificial Intelligence","issnPrinted":"0952-1976","issnOnline":null,"issnLinking":null,"ep":null,"iss":null,"sp":"109766","vol":"141","edition":null,"conferencePlace":null,"conferenceDate":null},"documentationUrls":null,"codeRepositoryUrl":null,"programmingLanguage":null,"contactPeople":null,"contactGroups":null,"tools":null,"size":null,"version":null,"geoLocations":null,"id":"doi_dedup___::3cae59c9396ede20c545e185aaa6d1aa","originalIds":["S0952197624019250","10.1016/j.engappai.2024.109766","50|doiboost____|3cae59c9396ede20c545e185aaa6d1aa","50|dblp________::4c6b7d0062efb4818db906b21b6cdf52","50|od______1181::4a87221ff14c021483181053b943b5a1","oai:strathprints.strath.ac.uk:91519","50|r3c4b2081b22::3cae59c9396ede20c545e185aaa6d1aa","50|sygma_______::3cae59c9396ede20c545e185aaa6d1aa","ftustrathclyde:oai:strathprints.strath.ac.uk:91519","50|base_oa_____::649b4e15814f103afc7e8ca85906a0af"],"pids":[{"scheme":"doi","value":"10.1016/j.engappai.2024.109766"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":8.0,"influence":2.5117899E-9,"popularity":7.473681E-9,"impulse":8.0,"citationClass":"C5","influenceClass":"C5","impulseClass":"C4","popularityClass":"C4"}},"projects":[{"id":"corda__h2020::a6b279dae779065e947c11fe5da5749e","code":"955422","acronym":"GECKO","title":"building GrEener and more sustainable soCieties by filling the Knowledge gap in social science and engineering to enable responsible artificial intelligence co-creatiOn","funder":"European Commission","pids":[{"scheme":"doi","value":"10.3030/955422"}]}],"organizations":[{"legalName":"University of Strathclyde","acronym":"University of Strathclyde","id":"openorgs____::0c2df843d882346e6b35ea98569ac268","pids":[{"scheme":"fundref","value":"100009138"},{"scheme":"UCAS","value":"S78"},{"scheme":"FundRef","value":"100009138"},{"scheme":"RRID","value":"RRID:SCR_011705"},{"scheme":"Wikidata","value":"Q1859178"},{"scheme":"RRID","value":"RRID:nlx_158336"},{"scheme":"HESA","value":"0169"},{"scheme":"ISNI","value":"0000000121138138"},{"scheme":"FundRef","value":"100008078"},{"scheme":"fundref","value":"100016271"},{"scheme":"FundRef","value":"100016271"},{"scheme":"OrgRef","value":"8954620"},{"scheme":"ROR","value":"https://ror.org/00n3w3b69"},{"scheme":"OrgReg","value":"UK0160"},{"scheme":"UKPRN","value":"10007805"},{"scheme":"fundref","value":"100008078"},{"scheme":"OrgRef","value":"224318"},{"scheme":"mag_id","value":"181647926"},{"scheme":"GRID","value":"grid.11984.35"},{"scheme":"wikidata","value":"Q1859178"},{"scheme":"PIC","value":"999974068"}],"countries":[{"code":"GB","label":"United Kingdom"}],"websiteurl":"http://www.strath.ac.uk/"}],"communities":[{"code":"uarctic","label":"UArctic","provenance":null}],"collectedFrom":[{"key":"openaire____::a8db6f6b2ce4fe72e8b2314a9a93e7d9","value":"Sygma"},{"key":"openaire____::df45502607927471ecf8a6ae83683ff5","value":"Bielefeld Academic Search Engine (BASE)"},{"key":"openaire____::081b82f96300b6a6e3d282bad31cb6e2","value":"Crossref"},{"key":"opendoar____::2ac2406e835bd49c70469acae337d292","value":"Strathprints"},{"key":"openaire____::d8b68cc0a53121f6f896883a7d60c1db","value":"DBLP"},{"key":"re3data_____::c4b2081b224be6b3e79d0e5e5556f631","value":"European Union Open Data Portal"}],"instances":[{"pids":[{"scheme":"doi","value":"10.1016/j.engappai.2024.109766"}],"license":"CC BY","accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":"hybrid"},"type":"Article","urls":["https://doi.org/10.1016/j.engappai.2024.109766"],"publicationDate":"2025-02-01","refereed":"peerReviewed","hostedBy":{"key":"issn___print::0e71ff7fb97c3465bb18c81af9da3952","value":"Engineering Applications of Artificial Intelligence"},"collectedFrom":{"key":"openaire____::081b82f96300b6a6e3d282bad31cb6e2","value":"Crossref"}},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1016/j.engappai.2024.109766"}],"type":"Article","urls":["https://doi.org/10.1016/j.engappai.2024.109766","https://dblp.org/rec/journals/eaai/BaticSS25.html"],"publicationDate":"2025-01-01","refereed":"nonPeerReviewed","hostedBy":{"key":"openaire____::d8b68cc0a53121f6f896883a7d60c1db","value":"DBLP"},"collectedFrom":{"key":"openaire____::d8b68cc0a53121f6f896883a7d60c1db","value":"DBLP"}},{"license":"CC BY","accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Article","urls":["https://strathprints.strath.ac.uk/91519/"],"publicationDate":"2025-02-01","refereed":"nonPeerReviewed","hostedBy":{"key":"opendoar____::2ac2406e835bd49c70469acae337d292","value":"Strathprints"},"collectedFrom":{"key":"opendoar____::2ac2406e835bd49c70469acae337d292","value":"Strathprints"}},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1016/j.engappai.2024.109766"}],"type":"Article","urls":["http://dx.doi.org/10.1016/j.engappai.2024.109766"],"publicationDate":"2025-01-01","refereed":"peerReviewed","hostedBy":{"key":"issn___print::0e71ff7fb97c3465bb18c81af9da3952","value":"Engineering Applications of Artificial Intelligence"},"collectedFrom":{"key":"re3data_____::c4b2081b224be6b3e79d0e5e5556f631","value":"European Union Open Data Portal"}},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1016/j.engappai.2024.109766"}],"license":"Elsevier TDM","accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Article","urls":["http://dx.doi.org/10.1016/j.engappai.2024.109766"],"refereed":"nonPeerReviewed","hostedBy":{"key":"openaire____::55045bd2a65019fd8e6741a755395c8c","value":"Unknown Repository"},"collectedFrom":{"key":"openaire____::a8db6f6b2ce4fe72e8b2314a9a93e7d9","value":"Sygma"}},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1016/j.engappai.2024.109766"}],"license":"CC BY","accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Article","urls":["https://doi.org/https://doi.org/10.1016/j.engappai.2024.109766"],"publicationDate":"2025-02-01","refereed":"nonPeerReviewed","hostedBy":{"key":"opendoar____::2ac2406e835bd49c70469acae337d292","value":"Strathprints"},"collectedFrom":{"key":"openaire____::df45502607927471ecf8a6ae83683ff5","value":"Bielefeld Academic Search Engine (BASE)"}}],"links":[{"header":{"relationType":"resultProject","relationClass":"isProducedBy","relatedIdentifier":"corda__h2020::a6b279dae779065e947c11fe5da5749e","relatedRecordType":"project","relationProvenance":"sysimport:actionset","trust":"0.91"},"collectedfrom":[{"dsId":"openaire____::a55eb91348674d853191f4f4fd73d078","dsName":"CORDA - COmmon Research DAta Warehouse - Horizon 2020"}],"projectTitle":"building GrEener and more sustainable soCieties by filling the Knowledge gap in social science and engineering to enable responsible artificial intelligence co-creatiOn","code":"955422","funding":{"funder":{"id":"ec__________::EC","shortname":"EC","name":"European Commission","jurisdiction":{"code":"EU","label":"European Union"},"pid":null},"level0":{"id":"ec__________::EC::H2020","description":"Horizon 2020 Framework Programme","name":"H2020"},"level1":{"id":"ec__________::EC::H2020::MSCA-ITN-ETN","description":"European Training Networks","name":"MSCA-ITN-ETN"},"level2":{"id":null,"description":null,"name":null}},"startDate":"2021-01-01","endDate":"2025-06-30"}],"otherTitles":null,"green":true,"inDiamondJournal":false,"isGreen":true,"isInDiamondJournal":false}