ROAMM: A software infrastructure for real-time monitoring of personal health

Mobile health (mHealth) based on smartphone and smartwatch technology is changing the landscape for how patients and research participants communicate about their health in real time. Flexible control of the different interconnected and frequently communicating mobile devices can provide a rich set of health care applications that can adapt dynamically to their environment. In this paper, we propose a real-time online activity and mobility monitoring (ROAMM) framework consisting of a smart-watch application for data collection, a server for data storage and retrieval as well as online monitoring and administrative tasks. We evaluated this framework to collect actigraphy data on the wrist and used it for feature detection and classification of different tasks of daily living conducted by participants. The information retrieved from the smartwatches yielded high accuracy for sedentary behavior prediction (accuracy = 97.44%) and acceptable performance for activity intensity level estimation (rMSE = 0.67 and R2 = 0.52).

[1]  Gert R. G. Lanckriet,et al.  A random forest classifier for the prediction of energy expenditure and type of physical activity from wrist and hip accelerometers , 2014, Physiological measurement.

[2]  Tina L Hurst,et al.  Physical activity classification using the GENEA wrist-worn accelerometer. , 2012, Medicine and science in sports and exercise.

[3]  Richard P Troiano,et al.  Evolution of accelerometer methods for physical activity research , 2014, British Journal of Sports Medicine.

[4]  Majid Sarrafzadeh,et al.  Determining the Single Best Axis for Exercise Repetition Recognition and Counting on SmartWatches , 2014, 2014 11th International Conference on Wearable and Implantable Body Sensor Networks.

[5]  Gary M. Weiss,et al.  Smartwatch-based activity recognition: A machine learning approach , 2016, 2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI).

[6]  Ian David Loram,et al.  The frequency of human, manual adjustments in balancing an inverted pendulum is constrained by intrinsic physiological factors , 2006, The Journal of physiology.

[7]  Todd M Manini,et al.  Metabolic Cost of Daily Activities and Effect of Mobility Impairment in Older Adults , 2011, Journal of the American Geriatrics Society.

[8]  Kevin Ashton,et al.  That ‘Internet of Things’ Thing , 1999 .

[9]  J. Staudenmayer,et al.  Methods to estimate aspects of physical activity and sedentary behavior from high-frequency wrist accelerometer measurements. , 2015, Journal of applied physiology.

[10]  Scott Shenker,et al.  Spark: Cluster Computing with Working Sets , 2010, HotCloud.