Situation-aware mobile health monitoring

Abstract

Recent advances in mobile computing coupled with the widespread availability of inexpensive mobile devices are the key motivating factors for the development of mobile health monitoring systems. However, to leverage the full potential of such systems for continuous and real time monitoring, there are a number of challenges that need to be addressed. This paper proposes a situation-aware mobile health monitoring framework that aims to increase not only the accuracy in identifying the occurring health conditions but also the cost-efficiency of running algorithms (e.g. the activity recognition classifier) using a situation-aware adaptation technique. The proposed framework integrates high level knowledge (i.e. user activity) with low level sensory data (e.g. heart rate) in situation reasoning and data fusion. Such holistic situational information can significantly improve accuracy of clinical decision making and selfmanagement of chronic diseases. The implementation and evaluation of the framework for a health monitoring application is described.