{"authors":[{"id":"orcid_______::9b3e3ae1bc9d6a0e99d932eb1dc46eea","fullName":"Kattepur, Ajay","name":"Ajay","surname":"Kattepur","rank":1,"pid":{"id":{"scheme":"orcid","value":"0000-0002-6540-1097"},"provenance":null}},{"id":null,"fullName":"Maruvada, K","name":"K","surname":"Maruvada","rank":2,"pid":null},{"id":"orcid_______::cd4bd752b09ab67fe4996edb008c7494","fullName":"Hassan, H","name":"H","surname":"Hassan","rank":3,"pid":{"id":{"scheme":"orcid","value":"0000-0001-8455-4577"},"provenance":null}},{"id":null,"fullName":"Bouloukakis, Georgios","name":"Georgios","surname":"Bouloukakis","rank":4,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0003-0109-9527"},"provenance":null}}],"openAccessColor":null,"publiclyFunded":false,"eoscIfGuidelines":null,"type":"publication","language":{"code":"und","label":"Undetermined"},"countries":null,"subjects":[{"subject":{"scheme":"FOS","value":"0202 electrical engineering, electronic engineering, information engineering"},"provenance":null},{"subject":{"scheme":"keyword","value":"Meta Models"},"provenance":null},{"subject":{"scheme":"FOS","value":"02 engineering and technology"},"provenance":null},{"subject":{"scheme":"keyword","value":"Model selection"},"provenance":null},{"subject":{"scheme":"keyword","value":"Model adaptation"},"provenance":null},{"subject":{"scheme":"keyword","value":"Drift detection"},"provenance":null}],"mainTitle":"Adaptive Model Selection using Meta Models and Drift Adaptation","subTitle":null,"descriptions":["Smart spaces that have deployed machine learning (ML) models for intelligent decision typically evolve over time. Model selection is a key step in deploying (ML) models, particularly in dynamic environments where data distribution shifts can impact model accuracy over time. Existing approaches often rely on evaluating many candidate models against predefinedmetrics, which is computationally expensive and neither suitable for real-time applications nor dynamic environments. This paper presents an adaptive model selection technique that combines meta-modeling with drift detection to improve efficiency and robustness. Meta-models are used to evaluate the suitability of candidate models under different constraints, such as predictive accuracy and computational cost, without requiring full evaluation on the target data. This reduces the overhead of model selection while preserving deployment quality. In addition, a drift detection mechanism monitors changes in the data distribution and updates the selection strategy accordingly. The proposed approach contributes to automated machine learning (AutoML) by enabling adaptive, efficient, and reliable model selection in real-time environments."],"publicationDate":"2026-01-06","publisher":"IEEE","embargoEndDate":null,"sources":["Crossref"],"formats":null,"contributors":null,"coverages":null,"bestAccessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/"},"container":{"name":"2026 18th International Conference on COMmunication Systems and NETworks (COMSNETS)","issnPrinted":null,"issnOnline":null,"issnLinking":null,"ep":"1366","iss":null,"sp":"1361","vol":null,"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___::820f3ad995544a8ab4a7c3b5efaa8a94","originalIds":["10.1109/comsnets67989.2026.11417773","50|doiboost____|8433f6559840c2bef376fc66bea8021d","50|datacite____::820f3ad995544a8ab4a7c3b5efaa8a94","10.5281/zenodo.17831047","oai:zenodo.org:17831047","50|od______2659::820f3ad995544a8ab4a7c3b5efaa8a94","50|datacite____::cf4f6e69fc336297ad14b8e137badf4e","10.5281/zenodo.17831046","50|dblp________::96bdb6e7a13bca2536a3a127be315019"],"pids":[{"scheme":"doi","value":"10.1109/comsnets67989.2026.11417773"},{"scheme":"doi","value":"10.5281/zenodo.17831047"},{"scheme":"doi","value":"10.5281/zenodo.17831046"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":0.0,"influence":2.2251732E-9,"popularity":2.7165745E-9,"impulse":0.0,"citationClass":"C5","influenceClass":"C5","impulseClass":"C5","popularityClass":"C5"}},"projects":[{"id":"corda_____he::679ba2587b03b4e6c4ca150b628d6975","code":"101135775","acronym":"PANDORA","title":"A Comprehensive Framework enabling the Delivery of Trustworthy Datasets for Efficient AIoT Operation","funder":"European Commission","pids":[{"scheme":"doi","value":"10.3030/101135775"}]}],"organizations":[{"legalName":"University of Patras","acronym":"PANEPISTIMIO PATRON UPAT","id":"openorgs____::4ac562f0376fce3539504567649cb373","pids":[{"scheme":"OrgRef","value":"19121920"},{"scheme":"PIC","value":"997985374"},{"scheme":"ROR","value":"https://ror.org/017wvtq80"},{"scheme":"wikidata","value":"Q7692473"},{"scheme":"PIC","value":"999894528"},{"scheme":"OrgRef","value":"477180"},{"scheme":"OrgRef","value":"34405046"},{"scheme":"PIC","value":"947610461"},{"scheme":"FundRef","value":"100009043"},{"scheme":"ISNI","value":"0000000405765395"},{"scheme":"Wikidata","value":"Q16737917"},{"scheme":"fundref","value":"100009043"},{"scheme":"GRID","value":"grid.11047.33"},{"scheme":"wikidata","value":"Q16737917"},{"scheme":"wikidata","value":"Q7692472"},{"scheme":"OrgReg","value":"GR0016"},{"scheme":"OrgReg","value":"GR0064"},{"scheme":"Wikidata","value":"Q7692473"},{"scheme":"mag_id","value":"174878644"},{"scheme":"GRID","value":"grid.494510.d"},{"scheme":"PIC","value":"964776454"},{"scheme":"Wikidata","value":"Q7692472"},{"scheme":"ROR","value":"https://ror.org/01mymm084"},{"scheme":"Wikidata","value":"Q1462246"},{"scheme":"OrgRef","value":"35582262"},{"scheme":"wikidata","value":"Q1462246"}]}],"communities":[{"code":"eosc","label":"EOSC","provenance":null}],"collectedFrom":[{"key":"openaire____::9e3be59865b2c1c335d32dae2fe7b254","value":"Datacite"},{"key":"opendoar____::358aee4cc897452c00244351e4d91f69","value":"ZENODO"},{"key":"openaire____::081b82f96300b6a6e3d282bad31cb6e2","value":"Crossref"},{"key":"openaire____::d8b68cc0a53121f6f896883a7d60c1db","value":"DBLP"}],"instances":[{"pids":[{"scheme":"doi","value":"10.1109/comsnets67989.2026.11417773"}],"license":"STM Policy #29","accessRight":{"code":"c_14cb","label":"CLOSED","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Article","urls":["https://doi.org/10.1109/comsnets67989.2026.11417773"],"publicationDate":"2026-01-06","refereed":"peerReviewed","hostedBy":{"key":"openaire____::55045bd2a65019fd8e6741a755395c8c","value":"Unknown Repository"},"collectedFrom":{"key":"openaire____::081b82f96300b6a6e3d282bad31cb6e2","value":"Crossref"}},{"pids":[{"scheme":"doi","value":"10.5281/zenodo.17831047"}],"license":"CC BY","type":"Conference object","urls":["https://dx.doi.org/10.5281/zenodo.17831047"],"publicationDate":"2026-01-01","refereed":"nonPeerReviewed","hostedBy":{"key":"opendoar____::358aee4cc897452c00244351e4d91f69","value":"ZENODO"},"collectedFrom":{"key":"openaire____::9e3be59865b2c1c335d32dae2fe7b254","value":"Datacite"}},{"pids":[{"scheme":"doi","value":"10.5281/zenodo.17831047"}],"alternateIdentifiers":[{"scheme":"oai","value":"oai:zenodo.org:17831047"}],"license":"CC BY","accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Conference object","urls":["http://dx.doi.org/10.5281/zenodo.17831047","https://zenodo.org/records/17831047"],"publicationDate":"2026-01-01","refereed":"nonPeerReviewed","hostedBy":{"key":"opendoar____::358aee4cc897452c00244351e4d91f69","value":"ZENODO"},"collectedFrom":{"key":"opendoar____::358aee4cc897452c00244351e4d91f69","value":"ZENODO"}},{"pids":[{"scheme":"doi","value":"10.5281/zenodo.17831046"}],"license":"CC BY","type":"Conference object","urls":["https://dx.doi.org/10.5281/zenodo.17831046"],"publicationDate":"2026-01-01","refereed":"nonPeerReviewed","hostedBy":{"key":"opendoar____::358aee4cc897452c00244351e4d91f69","value":"ZENODO"},"collectedFrom":{"key":"openaire____::9e3be59865b2c1c335d32dae2fe7b254","value":"Datacite"}},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1109/comsnets67989.2026.11417773"}],"type":"Conference object","urls":["https://doi.org/10.1109/COMSNETS67989.2026.11417773"],"refereed":"nonPeerReviewed","hostedBy":{"key":"openaire____::d8b68cc0a53121f6f896883a7d60c1db","value":"DBLP"},"collectedFrom":{"key":"openaire____::d8b68cc0a53121f6f896883a7d60c1db","value":"DBLP"}}],"links":[{"header":{"relationType":"resultProject","relationClass":"isProducedBy","relatedIdentifier":"corda_____he::679ba2587b03b4e6c4ca150b628d6975","relatedRecordType":"project","relationProvenance":"sysimport:crosswalk:repository","trust":"0.9"},"collectedfrom":[{"dsId":"openaire____::3f264f93cf3b0cfc4ede188a6300455c","dsName":"CORDA - COmmon Research DAta Warehouse - Horizon Europe"}],"projectTitle":"A Comprehensive Framework enabling the Delivery of Trustworthy Datasets for Efficient AIoT Operation","code":"101135775","funding":{"funder":{"id":"ec__________::EC","shortname":"EC","name":"European Commission","jurisdiction":{"code":"EU","label":"European Union"},"pid":null},"level0":{"id":"ec__________::EC::HE","description":"Horizon Europe Framework Programme","name":"HE"},"level1":{"id":"ec__________::EC::HE::HORIZON-RIA","description":"HORIZON  Research and Innovation Actions","name":"HORIZON-RIA"},"level2":{"id":null,"description":null,"name":null}},"startDate":"2024-04-01","endDate":"2027-03-31"}],"otherTitles":null,"inDiamondJournal":false,"green":true,"isGreen":true,"isInDiamondJournal":false}