Concept drift mitigation on resource-constrained IoT devices via self-learning

Simple item page
dc.contributor.authorKargar, Aminen
dc.contributor.authorZorbas, Dimitriosen
dc.contributor.authorGaffney, Michaelen
dc.contributor.authorO’Flynn, Brendanen
dc.contributor.authorTedesco, Salvatoreen
dc.contributor.funderResearch Irelanden
dc.contributor.funderEuropean Regional Development Funden
dc.contributor.funderDepartment of Agriculture, Food and the Marine, Irelanden
dc.contributor.funderTeagascen
dc.date.accessioned2025-11-12T11:48:03Z
dc.date.available2025-11-12T11:48:03Z
dc.date.issued2025-08-13en
dc.description.abstractReal-world deployments of Internet of Things (IoT) sensing systems equipped with artificial intelligence (AI) models generally experience a reduction in accuracy over time due to concept drift and data shift. To overcome this issue, it is suggested to periodically retrain the embedded AI model using new incoming data. However, this requires powerful processing hardware and labelled data, which are not generally available on IoT edge-based devices deployed in the real-world. In this study, we propose a method that benefits from a Deep Learning (DL) model for feature extraction and K-Means clustering for classification. The K-Means clustering technique can use the new incoming unlabeled data to update the model, thus helping the system to adapt to any changes that might occur in the new data. The proposed method is evaluated on two image datasets: the first is a public dataset with artificially added concept drift, and the second is a real-world dataset that suffers from concept drift issues. This is a lightweight model with only 610 KB of size and 608 KB of peak memory, which needs less than 0.6 s to perform and lower than 0.7 J to analyse each sample and update the model. Therefore, the method could easily be stored and executed on resource-constrained microcontroller-based (MCU-based) devices to deal with concept drift.en
dc.description.sponsorshipDepartment of Agriculture, Food and the Marine (2020 Trans National ERA-NET); Teagasc (Walsh Scholarship); Research Ireland (Grant 12/RC/2289-P2-INSIGHT2; 13/RC/2077-CONNECT; 21/RC/10303_P2-VISTAMILK2)en
dc.description.statusPeer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationKargar, A., Zorbas, D., Gaffney, M., O’Flynn, B. and Tedesco, S. (2025) 'Concept drift mitigation on resource-constrained IoT devices via self-learning', 2025 IEEE Sensors Applications Symposium (SAS), Newcastle, United Kingdom, 8-10 July 2025, pp. 1-6. https://doi.org/10.1109/SAS65169.2025.11105109en
dc.identifier.doi10.1109/sas65169.2025.11105109en
dc.identifier.eissn2766-3078en
dc.identifier.endpage6en
dc.identifier.isbn979-8-3315-1193-7en
dc.identifier.isbn979-8-3315-1194-4en
dc.identifier.issn2994-9300en
dc.identifier.startpage1en
dc.identifier.urihttps://hdl.handle.net/10468/18194
dc.language.isoenen
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.relation.ispartof2025 IEEE Sensors Applications Symposium (SAS), Newcastle, United Kingdom, 8-10 July 2025en
dc.rights© 2025, IEEE. For the purpose of Open Access, the author has applied a CC BY public copyright licence to any Author Accepted Manuscript version arising from this submission.en
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en
dc.subjectContinual learningen
dc.subjectEdge AIen
dc.subjectOn-device learningen
dc.subjectMicrocontrolleren
dc.subjectTinyMLen
dc.subjectConcept driften
dc.titleConcept drift mitigation on resource-constrained IoT devices via self-learningen
dc.typeConference itemen
dc.typeproceedings-articleen
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Concept_Drift_Mitigation_on_Resource-Constrained_IoT_Devices_via_Self-Learning (003).pdf
Size:
1.48 MB
Format:
Adobe Portable Document Format
Description:
Accepted Version
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Tyndall National Institute - Conference Items