University of Oulu

Qingyuan Gong1,2, Hui Ruan1,2, Yang Chen1,2, Xiang Su3,4. 2022. CloudyFL: A Cloudlet-Based Federated Learning Framework for Sensing User Behavior Using Wearable Devices. In International Workshop on Embedded and Mobile Deep learning (EMDL ’22), July 1, 2022, Portland, OR, USA. ACM, New York, NY, USA, 6 pages.

CloudyFL : a cloudlet-based federated learning framework for sensing user behavior using wearable devices

Saved in:
Author: Gong, Qingyuan1,2; Ruan, Hui1,2; Chen, Yang1,2;
Organizations: 1School of Computer Science, Fudan University, China
2BirenTech Research, China
3Department of Computer Science, Norwegian University of Science and Technology, Norway
4Center for Ubiquitous Computing, University of Oulu, Finland
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 0.6 MB)
Persistent link:
Language: English
Published: Association for Computing Machinery, 2022
Publish Date: 2023-04-13


Wearable devices have been widely utilized by the general public for tracking physical activities. Many complex machine learning models leverage wearable devices to address application problems, such as predicting pedestrian behaviors and health management. These models often incur heavy computing load and energy cost, which is challenging for wearable devices. However, aggregating the data from different wearable devices to a central server introduces privacy concerns. To address these challenges, we propose an architecture, CloudyFL, by deploying cloudlets close to wearable devices. In CloudyFL, each cloudlet forms a trusted zone covering a subset of nearby wearable devices. Models are trained in this trusted zone, and then, only the model parameters are transmitted to a centralized aggregator using a federated learning framework. We additionally propose an LSTM-based model for user behavior sensing, with a neural network design to adjust to the non-IID data distribution on multiple cloudlets. Experimental results show that our training model within the CloudyFL architecture can achieve a performance better than existing methodologies.

see all

ISBN Print: 978-1-4503-9404-8
Pages: 13 - 18
DOI: 10.1145/3539491.3539592
Host publication: Proceedings of the 6th International Workshop on Embedded and Mobile Deep Learning, 1 July 2022, Portland Oregon
Conference: Annual International Conference on Mobile Systems, Applications and Services
Type of Publication: A4 Article in conference proceedings
Field of Science: 113 Computer and information sciences
Funding: This work is sponsored by BirenTech Research, China Postdoctoral Science Foundation (No. 2021M690667), and Academy of Finland grant 326305, 325774, and 319690.
Academy of Finland Grant Number: 326305
Detailed Information: 326305 (Academy of Finland Funding decision)
Copyright information: © 2022 ACM. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in International Workshop on Embedded and Mobile Deep learning (EMDL ’22),