Towards a Human-Aware Operating System

Body-area networks have become a key scenario for pattern recognition technologies. Applications range from implicit human-machine interactions, to autonomous monitoring of user habits and activities. This paper presents a general framework that provide developers with tools to orchestrate the continuous process of collecting and classifying data streams. This can facilitate the development of human-aware applications, i.e., applications that can adapt to the context of their users. The framework supports service oriented, reconfigurable components and provides a solid background to put at joint work specification- and data-driven approaches. It also provides an innovative meta-classification scheme allowing developers to implement applications by editing a state automata. Experimental results suggest that the approach could be integrated in a number of applications for: \textit{(i)} improving energy efficiency, \textit{(ii)} improving classification accuracy and \textit{(iii)} improving software engineering of aware systems.