Collecting Health Lifelog Data from Smartwatch Users in a Privacy-Preserving Manner

Jong Wook Kim; Jong Hyun Lim; Su Mee Moon; Beakcheol Jang

doi:10.1109/TCE.2019.2924466

Collecting Health Lifelog Data from Smartwatch Users in a Privacy-Preserving Manner

Jong Wook Kim, Jong Hyun Lim, Su Mee Moon, Beakcheol Jang

Graduate School of Information

Research output: Contribution to journal › Article › peer-review

23 Citations (Scopus)

Abstract

With the development of easily wearable devices for humans, monitoring, and collecting lifelog data related to personal health status is easier than ever before. The advances in such wearable devices allow healthcare service providers to easily collect a vast amount of health lifelogs from diverse users for the purpose of data analysis. However, collecting health information of individual users indiscriminately may lead to serious privacy issues, because health lifelog data usually contain sensitive information. Thus, in this paper, we develop methods capable of collecting sensitive health lifelogs from a smartwatch, which is the most popular wearable device, while protecting the data privacy of smartwatch users. Experimental results show that the proposed approach can achieve an effective tradeoff between the degree of privacy protection and the accuracy in aggregate statistics. A correlation coefficient with an absolute value ranging from 0.808 to 0.945 between the degree of privacy protection and the accuracy in aggregate statistics can be accomplished using the proposed methods.

Original language	English
Article number	8744248
Pages (from-to)	369-378
Number of pages	10
Journal	IEEE Transactions on Consumer Electronics
Volume	65
Issue number	3
DOIs	https://doi.org/10.1109/TCE.2019.2924466
Publication status	Published - 2019 Aug

Bibliographical note

Funding Information:
This work was supported by the Institute of Information and Communications Technology Planning and Evaluation grant funded by the Korea Government (MSIT) (A Research on Safe and Convenient Big Data Processing Methods) under Grant 2018-0-00269

Funding Information:
Manuscript received February 21, 2019; revised May 21, 2019; accepted June 18, 2019. Date of publication June 24, 2019; date of current version July 24, 2019. This work was supported by the Institute of Information and Communications Technology Planning and Evaluation grant funded by the Korea Government (MSIT) (A Research on Safe and Convenient Big Data Processing Methods) under Grant 2018-0-00269. (Corresponding author: Beakcheol Jang.) The authors are with the Department of Computer Science, Sangmyung University, Seoul 03016, South Korea (e-mail: jkim@smu.ac.kr; dlsrks2019@naver.com; sumeedi@naver.com; bjang@smu.ac.kr). Digital Object Identifier 10.1109/TCE.2019.2924466

Publisher Copyright:
© 1975-2011 IEEE.

All Science Journal Classification (ASJC) codes

Media Technology
Electrical and Electronic Engineering

Access to Document

10.1109/TCE.2019.2924466

Cite this

@article{96553cfa19be472b99a4a7443944cc95,

title = "Collecting Health Lifelog Data from Smartwatch Users in a Privacy-Preserving Manner",

abstract = "With the development of easily wearable devices for humans, monitoring, and collecting lifelog data related to personal health status is easier than ever before. The advances in such wearable devices allow healthcare service providers to easily collect a vast amount of health lifelogs from diverse users for the purpose of data analysis. However, collecting health information of individual users indiscriminately may lead to serious privacy issues, because health lifelog data usually contain sensitive information. Thus, in this paper, we develop methods capable of collecting sensitive health lifelogs from a smartwatch, which is the most popular wearable device, while protecting the data privacy of smartwatch users. Experimental results show that the proposed approach can achieve an effective tradeoff between the degree of privacy protection and the accuracy in aggregate statistics. A correlation coefficient with an absolute value ranging from 0.808 to 0.945 between the degree of privacy protection and the accuracy in aggregate statistics can be accomplished using the proposed methods.",

author = "Kim, {Jong Wook} and Lim, {Jong Hyun} and Moon, {Su Mee} and Beakcheol Jang",

note = "Funding Information: This work was supported by the Institute of Information and Communications Technology Planning and Evaluation grant funded by the Korea Government (MSIT) (A Research on Safe and Convenient Big Data Processing Methods) under Grant 2018-0-00269 Funding Information: Manuscript received February 21, 2019; revised May 21, 2019; accepted June 18, 2019. Date of publication June 24, 2019; date of current version July 24, 2019. This work was supported by the Institute of Information and Communications Technology Planning and Evaluation grant funded by the Korea Government (MSIT) (A Research on Safe and Convenient Big Data Processing Methods) under Grant 2018-0-00269. (Corresponding author: Beakcheol Jang.) The authors are with the Department of Computer Science, Sangmyung University, Seoul 03016, South Korea (e-mail: jkim@smu.ac.kr; dlsrks2019@naver.com; sumeedi@naver.com; bjang@smu.ac.kr). Digital Object Identifier 10.1109/TCE.2019.2924466 Publisher Copyright: {\textcopyright} 1975-2011 IEEE.",

year = "2019",

month = aug,

doi = "10.1109/TCE.2019.2924466",

language = "English",

volume = "65",

pages = "369--378",

journal = "IEEE Transactions on Consumer Electronics",

issn = "0098-3063",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "3",

}

TY - JOUR

T1 - Collecting Health Lifelog Data from Smartwatch Users in a Privacy-Preserving Manner

AU - Kim, Jong Wook

AU - Lim, Jong Hyun

AU - Moon, Su Mee

AU - Jang, Beakcheol

N1 - Funding Information: This work was supported by the Institute of Information and Communications Technology Planning and Evaluation grant funded by the Korea Government (MSIT) (A Research on Safe and Convenient Big Data Processing Methods) under Grant 2018-0-00269 Funding Information: Manuscript received February 21, 2019; revised May 21, 2019; accepted June 18, 2019. Date of publication June 24, 2019; date of current version July 24, 2019. This work was supported by the Institute of Information and Communications Technology Planning and Evaluation grant funded by the Korea Government (MSIT) (A Research on Safe and Convenient Big Data Processing Methods) under Grant 2018-0-00269. (Corresponding author: Beakcheol Jang.) The authors are with the Department of Computer Science, Sangmyung University, Seoul 03016, South Korea (e-mail: jkim@smu.ac.kr; dlsrks2019@naver.com; sumeedi@naver.com; bjang@smu.ac.kr). Digital Object Identifier 10.1109/TCE.2019.2924466 Publisher Copyright: © 1975-2011 IEEE.

PY - 2019/8

Y1 - 2019/8

N2 - With the development of easily wearable devices for humans, monitoring, and collecting lifelog data related to personal health status is easier than ever before. The advances in such wearable devices allow healthcare service providers to easily collect a vast amount of health lifelogs from diverse users for the purpose of data analysis. However, collecting health information of individual users indiscriminately may lead to serious privacy issues, because health lifelog data usually contain sensitive information. Thus, in this paper, we develop methods capable of collecting sensitive health lifelogs from a smartwatch, which is the most popular wearable device, while protecting the data privacy of smartwatch users. Experimental results show that the proposed approach can achieve an effective tradeoff between the degree of privacy protection and the accuracy in aggregate statistics. A correlation coefficient with an absolute value ranging from 0.808 to 0.945 between the degree of privacy protection and the accuracy in aggregate statistics can be accomplished using the proposed methods.

AB - With the development of easily wearable devices for humans, monitoring, and collecting lifelog data related to personal health status is easier than ever before. The advances in such wearable devices allow healthcare service providers to easily collect a vast amount of health lifelogs from diverse users for the purpose of data analysis. However, collecting health information of individual users indiscriminately may lead to serious privacy issues, because health lifelog data usually contain sensitive information. Thus, in this paper, we develop methods capable of collecting sensitive health lifelogs from a smartwatch, which is the most popular wearable device, while protecting the data privacy of smartwatch users. Experimental results show that the proposed approach can achieve an effective tradeoff between the degree of privacy protection and the accuracy in aggregate statistics. A correlation coefficient with an absolute value ranging from 0.808 to 0.945 between the degree of privacy protection and the accuracy in aggregate statistics can be accomplished using the proposed methods.

UR - http://www.scopus.com/inward/record.url?scp=85068149863&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068149863&partnerID=8YFLogxK

U2 - 10.1109/TCE.2019.2924466

DO - 10.1109/TCE.2019.2924466

M3 - Article

AN - SCOPUS:85068149863

SN - 0098-3063

VL - 65

SP - 369

EP - 378

JO - IEEE Transactions on Consumer Electronics

JF - IEEE Transactions on Consumer Electronics

IS - 3

M1 - 8744248

ER -

Collecting Health Lifelog Data from Smartwatch Users in a Privacy-Preserving Manner

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this