Minimax Decentralized Hypothesis Testing
The source of uncertainty in hypothesis testing can either be the distribution functions conditioned on each hypothesis, or the a priori probabilities as introduced in Chap. 2. In this chapter, implications of the uncertainty caused by an unknown a priori probability is exploited for decentralized detection networks with (DDN-WF) and without a fusion center (DDN-WoF), which are illustrated in Figs. 7.1 and 7.2.
KeywordsDecision Maker Sensor Network Error Probability Detection Performance Fusion Center
- [Tsi93]S. Barbarossa and G. Scutari, “Decentralized detection,” in In Advances in Statistical Signal Processing. JAI Press, 1993, pp. 297–344.Google Scholar
- [BS07]S. Barbarossa and G. Scutari, “Bio-inspired sensor network design,” Signal Processing Magazine, IEEE, vol. 24, no. 3, pp. 26–35, May 2007.Google Scholar
- [CS11]F. S. Cattivelli and A. H. Sayed, “Distributed detection over adaptive networks using diffusion adaptation,” IEEE Transactions on Signal Processing, vol. 59, no. 5, pp. 1917–1932, May 2011.Google Scholar
- [Tsi88]J. N. Tsitsiklis, “Decentralized detection by a large numb. of sensors,” Mathematics of Control, Signals, and Systems, pp. 167–182, 1988.Google Scholar
- [Var96]P. K. Varshney, Distributed detection and data fusion, 1st ed. Secaucus, NJ, USA: Springer-Verlag New York, Inc., 1996.Google Scholar