Show simple item record

Files in this item

Thumbnail

Item metadata

dc.contributor.authorFang, L.
dc.contributor.authorLiu, X.
dc.contributor.authorSu, X.
dc.contributor.authorYe, J.
dc.contributor.authorDobson, S.
dc.contributor.authorHui, P.
dc.contributor.authorTarkoma, S.
dc.contributor.editorYe, Juan
dc.contributor.editorO'Grady, Michael J.
dc.contributor.editorCivitarese, Gabriele
dc.contributor.editorYordanova, Kristina
dc.date.accessioned2021-05-10T14:30:14Z
dc.date.available2021-05-10T14:30:14Z
dc.date.issued2021
dc.identifier.citationFang , L , Liu , X , Su , X , Ye , J , Dobson , S , Hui , P & Tarkoma , S 2021 , Bayesian inference federated learning for heart rate prediction . in J Ye , M J O'Grady , G Civitarese & K Yordanova (eds) , Wireless Mobile Communication and Healthcare : 9th EAI International Conference, MobiHealth 2020, Virtual Event, November 19, 2020, Proceedings . Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering , vol. 362 LNICST , Springer , Cham , pp. 116-130 . https://doi.org/10.1007/978-3-030-70569-5_8en
dc.identifier.isbn9783030705688
dc.identifier.isbn9783030705695
dc.identifier.issn1867-8211
dc.identifier.otherPURE: 274091840
dc.identifier.otherPURE UUID: 54d8fcab-dc8c-40cc-b2df-b1a56bf9f60d
dc.identifier.otherRIS: urn:F8C5BFBDC620D3C5B22CAA6E99E01CD7
dc.identifier.otherScopus: 85104410779
dc.identifier.otherORCID: /0000-0002-2838-6836/work/93515174
dc.identifier.otherORCID: /0000-0001-9633-2103/work/93515195
dc.identifier.urihttp://hdl.handle.net/10023/23145
dc.descriptionThis work has been partially supported by the UK EPSRC under grant number EP/N007565/1, “Science of Sensor Systems Software”, and by Academy of Finland projects, grant number 325774, 3196669, 319670, 326305, and 325570.en
dc.description.abstractThe advances of sensing and computing technologies pave the way to develop novel applications and services for wearable devices. For example, wearable devices measure heart rate, which accurately reflects the intensity of physical exercise. Therefore, heart rate prediction from wearable devices benefits users with optimization of the training process. Conventionally, Cloud collects user data from wearable devices and conducts inference. However, this paradigm introduces significant privacy concerns. Federated learning is an emerging paradigm that enhances user privacy by remaining the majority of personal data on users’ devices. In this paper, we propose a statistically sound, Bayesian inference federated learning for heart rate prediction with autoregression with exogenous variable (ARX) model. The proposed privacy-preserving method achieves accurate and robust heart rate prediction. To validate our method, we conduct extensive experiments with real-world outdoor running exercise data collected from wearable devices.
dc.format.extent15
dc.language.isoeng
dc.publisherSpringer
dc.relation.ispartofWireless Mobile Communication and Healthcareen
dc.relation.ispartofseriesLecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineeringen
dc.rightsCopyright © 2021 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering. 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/10.1007/978-3-030-70569-5_8.en
dc.subjectBayesian inferenceen
dc.subjectFederated learningen
dc.subjectHeart rate predictionen
dc.subjectWearable computingen
dc.subjectQA75 Electronic computers. Computer scienceen
dc.subjectQP Physiologyen
dc.subjectI-PWen
dc.subject.lccQA75en
dc.subject.lccQPen
dc.titleBayesian inference federated learning for heart rate predictionen
dc.typeConference itemen
dc.description.versionPostprinten
dc.contributor.institutionUniversity of St Andrews.School of Computer Scienceen
dc.contributor.institutionUniversity of St Andrews.School of Chemistryen
dc.contributor.institutionUniversity of St Andrews.Sir James Mackenzie Institute for Early Diagnosisen
dc.identifier.doihttps://doi.org/10.1007/978-3-030-70569-5_8


This item appears in the following Collection(s)

Show simple item record