Lifelogging data validation model for internet of things enabled personalized healthcare

Abstract

Internet of Things (IoT) technology offers opportunities to monitor lifelogging data by a variety of assets, like wearable sensors, mobile apps, etc. But due to heterogeneity of connected devices and diverse human life patterns in an IoT environment, lifelogging personal data contains huge uncertainty and are hardly used for healthcare studies. Effective validation of lifelogging personal data for longitudinal health assessment is demanded. In this paper, it takes lifelogging physical activity (LPA) as a target to explore how to improve validity of lifelogging data in an IoT enabled healthcare system. A rule based adaptive lifelogging physical activity validation model, LPAV-IoT, is proposed for eliminating irregular uncertainties and estimating data reliability in IoT healthcare environments. A methodology specifying four layers and three modules in LPAV-IoT is presented for analyzing key factors impacting validity of lifelogging physical activity. A series of validation rules are designed with uncertainty threshold parameters and reliability indicators and evaluated through experimental investigations. Following LPAV-IoT, a case study on a personalized healthcare platform MHA [38] connecting three state-of-the-art wearable devices and mobile apps are carried out. The results reflect that the rules provided by LPAV-IoT enable efficiently filtering at least 75% of irregular uncertainty and adaptively indicating the reliability of LPA data on certain condition of IoT environments