Managing context data for smart spaces

Describes our on-going efforts to construct a service infrastructure to support smart environments. We characterize "fusion services", which extract and infer useful context information from sensor data, using evidential reasoning techniques. We specify sensing services as Bayesian networks and use information-theoretic algorithms to optimize the resources consumed by the rendering of a service. We define a "quality-of-information" metric to characterize sensing service performance. We have implemented an infrastructure for supporting a dynamic set of sensors and services in a smart space. Using this infrastructure and an IEEE 802.11 network, we implemented a probabilistic indoor location system that optimizes the number of sensors consulted when determining the location of a user while maintaining a high degree of accuracy.