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.
Bibliographical noteFunding 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
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: firstname.lastname@example.org; email@example.com; firstname.lastname@example.org; email@example.com). Digital Object Identifier 10.1109/TCE.2019.2924466
© 1975-2011 IEEE.
All Science Journal Classification (ASJC) codes
- Media Technology
- Electrical and Electronic Engineering