Analyzing the acquisition and management of context

Abstract

Mobile users want mobile services tailored to their current context and needs. These context-aware services have primarily focused on position information; using other types of user information would enhance the development of smarter services. There is a range of frameworks that manage and distribute user context; however, when several information sources and inference techniques are available, these context frameworks face the need to make appropriate decisions to facilitate the most suitable context information to applications. This article describes strategies to solve a context acquisition problem, namely the choice of the information channel, given available user information and context obtaining services. The proposed context acquisition strategy, based on Bayesian decision theory, improves the frameworks' decision making and enables integrating and encapsulating a wide set of context inference and reasoning algorithms and data sources, in a well-documented, transparent, and principled way.