Multiple density maps information fusion for effectively assessing intensity pattern of lifelogging physical activity

Physical activity (PA) measurement is a crucial task in healthcare technology aimed at monitoring the progression and treatment of many chronic diseases. Traditional lifelogging PA measures require relatively high cost and can only be conducted in controlled or semi-controlled environments, though they exhibit remarkable precision of PA monitoring outcomes. Recent advancement of commercial wearable devices and smartphones for recording one's lifelogging PA has popularized data capture in uncontrolled environments. However, due to diverse life patterns and heterogeneity of connected devices as well as the PA recognition accuracy, lifelogging PA data measured by wearable devices and mobile phones contains much uncertainty thereby limiting their adoption for healthcare studies. To improve the feasibility of PA tracking datasets from commercial wearable/mobile devices, this paper proposes a lifelogging PA intensity pattern decision making approach for lifelong PA measures. The method is to firstly remove some irregular uncertainties (IU) via an Ellipse fitting model, and then construct a series of monthly based hour-day density map images for representing PA intensity patterns with regular uncertainties (RU) on each month. Finally it explores Dempster-Shafer theory of evidence fusing information from these density map images for generating a decision making model of a final personal lifelogging PA intensity pattern. The approach has significantly reduced the uncertainties and incompleteness of datasets from third party devices. Two case studies on a mobile personalized healthcare platform MHA [1] connecting the mobile app Moves are carried out. The results indicate that the proposed approach can improve effectiveness of PA tracking devices or apps for various types of people who frequently use them as a healthcare indicator.