University of Oulu

Fang L. et al. (2021) Bayesian Inference Federated Learning for Heart Rate Prediction. In: Ye J., O'Grady M.J., Civitarese G., Yordanova K. (eds) Wireless Mobile Communication and Healthcare. MobiHealth 2020. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 362. Springer, Cham. https://doi.org/10.1007/978-3-030-70569-5_8

Bayesian Inference Federated Learning for Heart Rate Prediction

Saved in:
Author: Fang, Lei1; Liu, Xiaoli2; Su, Xiang2,3;
Organizations: 1University of St Andrews, St Andrews, KY16 9SX, UK
2University of Helsinki, Helsinki, 00014, Finland
3University of Oulu, Oulu, 90014, Finland
4The Hong Kong University of Science and Technology, Hong Kong
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 0.4 MB)
Persistent link: http://urn.fi/urn:nbn:fi-fe2021102151851
Language: English
Published: Springer Nature, 2021
Publish Date: 2021-10-21
Description:

Abstract

The 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.

see all

Series: Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
ISSN: 1867-8211
ISSN-E: 1867-822X
ISSN-L: 1867-8211
ISBN: 978-3-030-70569-5
ISBN Print: 978-3-030-70568-8
Pages: 116 - 130
DOI: 10.1007/978-3-030-70569-5_8
OADOI: https://oadoi.org/10.1007/978-3-030-70569-5_8
Host publication: Wireless Mobile Communication and Healthcare : 9th EAI International Conference, MobiHealth 2020, Virtual Event, November 19, 2020, Proceedings
Host publication editor: Ye, J.
O'Grady, M. J.
Civitarese, G.
Yordanova, K.
Conference: International Conference on Wireless Mobile Communication and Healthcare
Type of Publication: A4 Article in conference proceedings
Field of Science: 213 Electronic, automation and communications engineering, electronics
Subjects:
Funding: This 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.
Academy of Finland Grant Number: 326305
Detailed Information: 326305 (Academy of Finland Funding decision)
Copyright information: © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2021. This is a post-peer-review, pre-copyedit version of an article published in Wireless Mobile Communication and Healthcare : 9th EAI International Conference, MobiHealth 2020, Virtual Event, November 19, 2020, Proceedings. The final authenticated version is available online at: https://doi.org/10.1007/978-3-030-70569-5_8.