Acquiring and Learning User Information in the Context of Cognitive Device Management

One of the key features of emerging and future wireless systems is the continuous increase in the number and diversity of available radio access technologies. A great number of research efforts in the past decade have focused on ways to more efficiently exploit the various wireless access technologies. Among the recent trends in this direction are cognitive wireless networks and systems, targeting to tackle the complexity of the diversified radio environment. Eventually, the goal of these evolving systems is to provide personalised services to users at any time, at any place. Clearly in order to really improve the experience of all users, even technology agnostic ones, functionality is required, on both the network and the user-device side, for providing the "always best connection" in a transparent manner. This paper focuses on mechanisms for acquiring and learning information on user preferences, requirements and constraints as part of a cognitive device management system that enables optimal device configuration taking into account in addition to user requirements, environment characteristics and experience established through learning mechanisms. In this context, the paper presents a scheme for learning and estimating user preferences based on Bayesian networks.