Research Article
Bayesian Inference Federated Learning for Heart Rate Prediction
@INPROCEEDINGS{10.1007/978-3-030-70569-5_8, author={Lei Fang and Xiaoli Liu and Xiang Su and Juan Ye and Simon Dobson and Pan Hui and Sasu Tarkoma}, title={Bayesian Inference Federated Learning for Heart Rate Prediction}, proceedings={Wireless Mobile Communication and Healthcare. 9th EAI International Conference, MobiHealth 2020, Virtual Event, November 19, 2020, Proceedings}, proceedings_a={MOBIHEALTH}, year={2021}, month={7}, keywords={Federated learning Bayesian inference Wearable computing Heart rate prediction}, doi={10.1007/978-3-030-70569-5_8} }- Lei Fang
Xiaoli Liu
Xiang Su
Juan Ye
Simon Dobson
Pan Hui
Sasu Tarkoma
Year: 2021
Bayesian Inference Federated Learning for Heart Rate Prediction
MOBIHEALTH
Springer
DOI: 10.1007/978-3-030-70569-5_8
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.
