ActivityAware: An app for real-time daily activity level monitoring on the Amulet wrist-worn device

• Published in: 2017 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) Vol. 2017; pp. 431 - 435
• Main Authors: Boateng, George, Batsis, John A., Halter, Ryan, Kotz, David
• Format: Conference Proceeding Journal Article
• Language: English
• Published: United States IEEE 01.03.2017
• Subjects: Acceleration; Biomedical monitoring; Data collection; Data models; machine learning; mobile health (mHealth); Monitoring; physical activity; Real-time systems; support vector machine; Support vector machines; wearables; mobile health (mHealth); wearables; support vector machine; machine learning; physical activity
• DOI: 10.1109/PERCOMW.2017.7917601

Physical activity helps reduce the risk of cardiovascular disease, hypertension and obesity. The ability to monitor a person's daily activity level can inform self-management of physical activity and related interventions. For older adults with obesity, the importance of regular, physical activity is critical to reduce the risk of long-term disability. In this work, we present ActivityAware, an application on the Amulet wrist-worn device that measures daily activity levels (sedentary, moderate and vigorous) of individuals, continuously and in real-time. The app implements an activity-level detection model, continuously collects acceleration data on the Amulet, classifies the current activity level, updates the day's accumulated time spent at that activity level, logs the data for later analysis, and displays the results on the screen. We developed an activity-level detection model using a Support Vector Machine (SVM). We trained our classifiers using data from a user study, where subjects performed the following physical activities: sit, stand, lay down, walk and run. With 10-fold cross validation and leave-one-subject-out (LOSO) cross validation, we obtained preliminary results that suggest accuracies up to 98%, for n=14 subjects. Testing the ActivityAware app revealed a projected battery life of up to 4 weeks before needing to recharge. The results are promising, indicating that the app may be used for activity-level monitoring, and eventually for the development of interventions that could improve the health of individuals.