Show simple item record

Files in this item

Thumbnail

Item metadata

dc.contributor.authorYe, Juan
dc.contributor.authorDobson, Simon Andrew
dc.contributor.authorZambonelli, Franco
dc.date.accessioned2020-01-15T13:30:08Z
dc.date.available2020-01-15T13:30:08Z
dc.date.issued2020-01
dc.identifier.citationYe , J , Dobson , S A & Zambonelli , F 2020 , ' XLearn : learning activity labels across heterogeneous datasets ' , ACM Transactions on Intelligent Systems and Technology , vol. 11 , no. 2 , 17 . https://doi.org/10.1145/3368272en
dc.identifier.issn2157-6904
dc.identifier.otherPURE: 264040093
dc.identifier.otherPURE UUID: c926f1a5-9b77-4247-8855-9adc959dd227
dc.identifier.otherORCID: /0000-0002-2838-6836/work/68280984
dc.identifier.otherScopus: 85078822927
dc.identifier.otherORCID: /0000-0001-9633-2103/work/70234210
dc.identifier.otherWOS: 000567261000004
dc.identifier.urihttp://hdl.handle.net/10023/19291
dc.description.abstractSensor-driven systems often need to map sensed data into meaningfully labelled activities to classify the phenomena being observed. A motivating and challenging example comes from human activity recognition in which smart home and other datasets are used to classify human activities to support applications such as ambient assisted living, health monitoring, and behavioural intervention. Building a robust and meaningful classifier needs annotated ground truth, labelled with what activities are actually being observed—and acquiring high-quality, detailed, continuous annotations remains a challenging, time-consuming, and error-prone task, despite considerable attention in the literature. In this article, we use knowledge-driven ensemble learning to develop a technique that can combine classifiers built from individually labelled datasets, even when the labels are sparse and heterogeneous. The technique both relieves individual users of the burden of annotation and allows activities to be learned individually and then transferred to a general classifier. We evaluate our approach using four third-party, real-world smart home datasets and show that it enhances activity recognition accuracies even when given only a very small amount of training data.
dc.format.extent28
dc.language.isoeng
dc.relation.ispartofACM Transactions on Intelligent Systems and Technologyen
dc.rightsCopyright © 2020 the owner/author(s). Publication rights licensed to ACM. This work has been made available online in accordance with publisher policies or with permission. Permission for further reuse of this content should be sought from the publisher or the rights holder. This is the author created accepted manuscript following peer review and may differ slightly from the final published version. The final published version of this work is available at https://doi.org/10.1145/3368272en
dc.subjectHuman activity recognitionen
dc.subjectEnsemble learningen
dc.subjectTransfer learningen
dc.subjectClusteringen
dc.subjectSmart homeen
dc.subjectQA75 Electronic computers. Computer scienceen
dc.subjectT Technologyen
dc.subject3rd-DASen
dc.subjectBDCen
dc.subjectR2Cen
dc.subject~DC~en
dc.subject.lccQA75en
dc.subject.lccTen
dc.titleXLearn : learning activity labels across heterogeneous datasetsen
dc.typeJournal articleen
dc.description.versionPostprinten
dc.contributor.institutionUniversity of St Andrews.School of Computer Scienceen
dc.contributor.institutionUniversity of St Andrews.Sir James Mackenzie Institute for Early Diagnosisen
dc.identifier.doihttps://doi.org/10.1145/3368272
dc.description.statusPeer revieweden
dc.date.embargoedUntil2020-01-10


This item appears in the following Collection(s)

Show simple item record