Incremental Learning of Human Activities in Smart Homes

dc.citation.issue21
dc.citation.volume22
dc.contributor.authorChua S-L
dc.contributor.authorFoo LK
dc.contributor.authorGuesgen HW
dc.contributor.authorMarsland S
dc.contributor.editorMobilio M
dc.contributor.editorMicucci D
dc.coverage.spatialSwitzerland
dc.date.accessioned2023-11-13T22:14:32Z
dc.date.accessioned2023-11-20T01:37:50Z
dc.date.available2022-11-03
dc.date.available2023-11-13T22:14:32Z
dc.date.available2023-11-20T01:37:50Z
dc.date.issued2022-11-03
dc.description.abstractSensor-based human activity recognition has been extensively studied. Systems learn from a set of training samples to classify actions into a pre-defined set of ground truth activities. However, human behaviours vary over time, and so a recognition system should ideally be able to continuously learn and adapt, while retaining the knowledge of previously learned activities, and without failing to highlight novel, and therefore potentially risky, behaviours. In this paper, we propose a method based on compression that can incrementally learn new behaviours, while retaining prior knowledge. Evaluation was conducted on three publicly available smart home datasets.
dc.description.confidentialfalse
dc.edition.editionNovember 2022
dc.format.pagination8458-
dc.identifier.author-urlhttps://www.ncbi.nlm.nih.gov/pubmed/36366154
dc.identifier.citationChua S-L, Foo LK, Guesgen HW, Marsland S. (2022). Incremental Learning of Human Activities in Smart Homes.. Sensors (Basel). 22. 21. (pp. 8458-).
dc.identifier.doi10.3390/s22218458
dc.identifier.eissn1424-8220
dc.identifier.elements-typejournal-article
dc.identifier.issn1424-8220
dc.identifier.number8458
dc.identifier.piis22218458
dc.identifier.urihttps://mro.massey.ac.nz/handle/10179/69130
dc.languageeng
dc.publisherMDPI (Basel, Switzerland)
dc.publisher.urihttps://www.mdpi.com/1424-8220/22/21/8458
dc.relation.isPartOfSensors (Basel)
dc.rights(c) 2022 The Author/s
dc.rightsCC BY
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectactivity recognition
dc.subjectincremental learning
dc.subjectnovelty detection
dc.subjectprediction by partial matching
dc.subjectsmart homes
dc.subjectHumans
dc.subjectHuman Activities
dc.subjectMachine Learning
dc.titleIncremental Learning of Human Activities in Smart Homes
dc.typeJournal article
pubs.elements-id457985
pubs.organisational-groupOther
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
457985 PDF.pdf
Size:
508.46 KB
Format:
Adobe Portable Document Format
Description:
Collections