Uncertainty management of intelligent feature selection in wireless sensor networks

Wireless sensor networks (WSN) are envisioned to revolutionize the paradigm of monitoring complex real-world systems at a very high resolution. However, the deployment of a large number of unattended sensor nodes in hostile environments, frequent changes of environment dynamics, and severe resource constraints pose uncertainties and limit the potential use of WSN in complex real-world applications. Although uncertainty management in Artificial Intelligence (AI) is well developed and well investigated, its implications in wireless sensor environments are inadequately addressed. This dissertation addresses uncertainty management issues of spatio-temporal patterns generated from sensor data. It provides a framework for characterizing spatio-temporal pattern in WSN. Using rough set theory and temporal reasoning a novel formalism has been developed to characterize and quantify the uncertainties in predicting spatio-temporal patterns from sensor data. This research also uncovers the trade-off among the uncertainty measures, which can be used to develop a multi-objective optimization model for real-time decision making in sensor data aggregation and sampling.