Statistical Signal Processing in Sensor Networks

Organizer: Venkatesh Saligrama, Boston University

Distributed sensing systems hold the promise of providing an inexpensive, non-intrusive means to understand phenomena that exhibit spatial and temporal variations at multiple scales. This has become possible on account of rapid advances in sensor and computing technologies and provided the impetus for deploying networks of sensors. While significant effort over the last decade in sensor development, physical layer transmission and networking infrastructure has laid the initial groundwork for practical deployment, the full potential for networked sensing systems can only be realized through a fundamental understanding of statistical decision making in networked and uncertain environments.

The challenges to signal processing primarily arise from two sources: (1) communication constraints, which arises due to the fact communication consumes significantly more energy than sensing and processing; (2) uncertainty, which arises from spatial and temporal variability as well as observation noise.

Regular lectures:

• Title: How Dense Should a Sensor Network be for Detection Applications?
  Authors: Jean-Francois Chamberland, Venugopal V. Veeravalli
• Title: Decentralized Detection and Estimation of localized phenomena
  Author: Erhan Ermis, Venkatesh Saligrama
• Title: A Distributed Broadcasting Time-Synchronization Scheme for Wireless Sensor Networks
  Author: Nima Khajehnouri, Ali H. Sayed
• Title: Robust Decentralized Source Localization via Averaging
  Authors: Michael Rabbat, Robert Nowak, James Bucklew
• Title: Communication- Estimation Tradeoffs in Wireless Sensor Networks
  Authors: S.-H. Son, S. Schwartz, S. Kulkarni, M. Roan
• Title: Optimization Approaches to Dynamic Routing in Sensor Networks
  Authors: Jason L. Williams, John W. Fisher III, Alan S. Willsky