Search

Sedentary behavior is considered as a major public health challenge, linked with many chronic diseases and premature mortality. In this paper, we propose a steps counting -based machine learning approach for the prediction of sedentary behavior. Our work focuses on analyzing historical data from multiple users of wearable physical activity trackers and exploring the performance of four machine learning algorithms, i.e., Logistic Regression, Random Forest, XGBoost, Convolutional Neural Networks, as well as a Majority Vote Ensemble of the algorithms. To train and test our models we employed a crowd sourced dataset containing a month's data of 33 users. For further evaluation, we employed a dataset containing 6 months of data of an additional user. The results revealed that while all models succeed in predicting next-day sedentary behavior, the ensemble model outperforms all baselines, as it manages to predict sedentary behavior and reduce false positives more effectively. On the multi-subjects test dataset, our ensemble model achieved an accuracy of 82.12% with a sensitivity of 74.53% and a specificity of 85.71%. On the additional unseen dataset, we achieved 76.88% in accuracy, 63.27% in sensitivity and 81.75% in specificity. These outcomes provide the ground towards the development of real-life artificially intelligent systems for sedentary behavior prediction.

Although a plethora of remote health monitoring systems have been proposed for chronic conditions, the challenge posed by the changing patient needs and the requirement for personalization in health monitoring to move beyond proprietary, difficult to extend, and unsustainable solutions still pertains. In this direction, we describe a mobile health system based on a smartphone, portable/wearable sensors for measuring the patient's physiological parameters, and back-end platforms for the health professionals to monitor the patient condition and configure monitoring plans in an individualized manner. A prototype system was developed based on a Service-oriented Architecture and integrating commercially available sensing devices. An experimental study has been conducted with 53 patients in order to investigate the usability of the proposed system. The patients were able to perform the majority of the target tasks successfully (Success Rate = 77%), while the perceived usability using the System Usability Scale (SUS) was found to be above average (SUS score = 73%), indicating that the patients overall perceived the system as both easy to use and useful.

A flexible, scaleable and cost-effective medical telemetry system is described for monitoring sleep-related disorders in the home environment. The system was designed and built for real-time data acquisition and processing, allowing for additional use in intensive care unit scenarios where rapid medical response is required in case of emergency. It comprises a wearable body area network of Zigbee-compatible wireless sensors worn by the subject, a central database repository residing in the medical centre and thin client workstations located at the subject's home and in the clinician's office. The system supports heterogeneous setup configurations, involving a variety of data acquisition sensors to suit several medical applications. All telemetry data is securely transferred and stored in the central database under the clinicians' ownership and control.