Abstract :
Rapid advancements in embedded systems, sensors and wireless communication technologies have led to the development of cyber-physical systems, pervasive computing and smart environments with important applications such as smart grids, sustainability, health care and security. Wireless sensor networks play significant role in building such systems as they can effectively act as the human-physical interface with the digital world through sensing, communication, computing and control or actuation. However, the inherent characteristics of wireless sensor networks, typified by resource constraints, high degree of uncertainty, heterogeneity and distributed control pose significant challenges. After introducing the basic challenges, opportunities and applications, this talk will present a novel framework for multi-modal context recognition from sensor streaming data, context-aware data fusion, and situation-aware decision making with a trade-off between information accuracy (hence inference quality) and energy consumption. The underlying approach is based on dynamic Bayesian model, information theoretic reasoning, and game theory. The talk will be concluded with open issues and future directions of research.
