Federated learning on wearable devices: Demo abstract

Xiaoxin He; Xiang Su; Yang Chen; Pan Hui

doi:10.1145/3384419.3430446

Federated learning on wearable devices: Demo abstract

Xiaoxin He, Xiang Su, Yang Chen, Pan Hui

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

6 Citations (Scopus)

Abstract

Wearable devices collect user information about their activities and provide insights to improve their daily lifestyles. Smart health applications have achieved great success by training Machine Learning (ML) models on a large quantity of user data from wearables. However, user privacy and scalability are becoming critical challenges for training ML models in a centralized way. Federated learning (FL) is a novel ML paradigm with the goal of training high quality models while distributing training data over a large number of devices. In this demo, we present FL4W, a FL system with wearable devices enabling training a human activity recognition classifier. We also perform preliminary analytics to investigate the model performance with increasing computation of clients.

Original language	English
Title of host publication	SenSys 2020 - Proceedings of the 2020 18th ACM Conference on Embedded Networked Sensor Systems
Publisher	Association for Computing Machinery, Inc
Pages	613-614
Number of pages	2
ISBN (Electronic)	9781450375900
DOIs	https://doi.org/10.1145/3384419.3430446
Publication status	Published - 16 Nov 2020
Externally published	Yes
Event	18th ACM Conference on Embedded Networked Sensor Systems, SenSys 2020 - Virtual, Online, Japan Duration: 16 Nov 2020 → 19 Nov 2020

Publication series

Name	SenSys 2020 - Proceedings of the 2020 18th ACM Conference on Embedded Networked Sensor Systems

Conference

Conference	18th ACM Conference on Embedded Networked Sensor Systems, SenSys 2020
Country/Territory	Japan
City	Virtual, Online
Period	16/11/20 → 19/11/20

Bibliographical note

Publisher Copyright:
© 2020 ACM.

Keywords

federated learning
human activity recognition
wearable devices

Access to Document

10.1145/3384419.3430446

Cite this

He, X., Su, X., Chen, Y., & Hui, P. (2020). Federated learning on wearable devices: Demo abstract. In SenSys 2020 - Proceedings of the 2020 18th ACM Conference on Embedded Networked Sensor Systems (pp. 613-614). (SenSys 2020 - Proceedings of the 2020 18th ACM Conference on Embedded Networked Sensor Systems). Association for Computing Machinery, Inc. https://doi.org/10.1145/3384419.3430446

@inproceedings{f8800ac367894489abaf63b4a0c1c52a,

title = "Federated learning on wearable devices: Demo abstract",

abstract = "Wearable devices collect user information about their activities and provide insights to improve their daily lifestyles. Smart health applications have achieved great success by training Machine Learning (ML) models on a large quantity of user data from wearables. However, user privacy and scalability are becoming critical challenges for training ML models in a centralized way. Federated learning (FL) is a novel ML paradigm with the goal of training high quality models while distributing training data over a large number of devices. In this demo, we present FL4W, a FL system with wearable devices enabling training a human activity recognition classifier. We also perform preliminary analytics to investigate the model performance with increasing computation of clients.",

keywords = "federated learning, human activity recognition, wearable devices",

author = "Xiaoxin He and Xiang Su and Yang Chen and Pan Hui",

note = "Publisher Copyright: {\textcopyright} 2020 ACM.; 18th ACM Conference on Embedded Networked Sensor Systems, SenSys 2020 ; Conference date: 16-11-2020 Through 19-11-2020",

year = "2020",

month = nov,

day = "16",

doi = "10.1145/3384419.3430446",

language = "English",

series = "SenSys 2020 - Proceedings of the 2020 18th ACM Conference on Embedded Networked Sensor Systems",

publisher = "Association for Computing Machinery, Inc",

pages = "613--614",

booktitle = "SenSys 2020 - Proceedings of the 2020 18th ACM Conference on Embedded Networked Sensor Systems",

}

He, X, Su, X, Chen, Y & Hui, P 2020, Federated learning on wearable devices: Demo abstract. in SenSys 2020 - Proceedings of the 2020 18th ACM Conference on Embedded Networked Sensor Systems. SenSys 2020 - Proceedings of the 2020 18th ACM Conference on Embedded Networked Sensor Systems, Association for Computing Machinery, Inc, pp. 613-614, 18th ACM Conference on Embedded Networked Sensor Systems, SenSys 2020, Virtual, Online, Japan, 16/11/20. https://doi.org/10.1145/3384419.3430446

Federated learning on wearable devices: Demo abstract. / He, Xiaoxin; Su, Xiang; Chen, Yang et al.
SenSys 2020 - Proceedings of the 2020 18th ACM Conference on Embedded Networked Sensor Systems. Association for Computing Machinery, Inc, 2020. p. 613-614 (SenSys 2020 - Proceedings of the 2020 18th ACM Conference on Embedded Networked Sensor Systems).

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

TY - GEN

T1 - Federated learning on wearable devices

T2 - 18th ACM Conference on Embedded Networked Sensor Systems, SenSys 2020

AU - He, Xiaoxin

AU - Su, Xiang

AU - Chen, Yang

AU - Hui, Pan

PY - 2020/11/16

Y1 - 2020/11/16

N2 - Wearable devices collect user information about their activities and provide insights to improve their daily lifestyles. Smart health applications have achieved great success by training Machine Learning (ML) models on a large quantity of user data from wearables. However, user privacy and scalability are becoming critical challenges for training ML models in a centralized way. Federated learning (FL) is a novel ML paradigm with the goal of training high quality models while distributing training data over a large number of devices. In this demo, we present FL4W, a FL system with wearable devices enabling training a human activity recognition classifier. We also perform preliminary analytics to investigate the model performance with increasing computation of clients.

AB - Wearable devices collect user information about their activities and provide insights to improve their daily lifestyles. Smart health applications have achieved great success by training Machine Learning (ML) models on a large quantity of user data from wearables. However, user privacy and scalability are becoming critical challenges for training ML models in a centralized way. Federated learning (FL) is a novel ML paradigm with the goal of training high quality models while distributing training data over a large number of devices. In this demo, we present FL4W, a FL system with wearable devices enabling training a human activity recognition classifier. We also perform preliminary analytics to investigate the model performance with increasing computation of clients.

KW - federated learning

KW - human activity recognition

KW - wearable devices

UR - https://www.scopus.com/pages/publications/85097563015

U2 - 10.1145/3384419.3430446

DO - 10.1145/3384419.3430446

M3 - Conference Paper published in a book

AN - SCOPUS:85097563015

T3 - SenSys 2020 - Proceedings of the 2020 18th ACM Conference on Embedded Networked Sensor Systems

SP - 613

EP - 614

BT - SenSys 2020 - Proceedings of the 2020 18th ACM Conference on Embedded Networked Sensor Systems

PB - Association for Computing Machinery, Inc

Y2 - 16 November 2020 through 19 November 2020

ER -

Federated learning on wearable devices: Demo abstract

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this