Optimum consultation for serial distributed detection systems

Abstract

This paper considers a distributed detection system which consists of  sensors that are connected in series. The observations of each sensor in this system design are considered to be statistically independent of all other sensors. In contrast to the popular serial decision fusion systems, we assume that consultations are allowed in a serial manner between successive sensors that make up the system. In addition, the paper demonstrates the similarity between the proposed consulting serial system and the optimal serial one in terms of detection probabilities for a give probability of false alarm. However, it should be emphasized that the proposed system has the benefit of conditional nonrandom consultation among the sensors. Consequently, its survivability is higher than that of serial systems. Numerical evaluations for the cases of two and three sensors are provided and compared with those of the serial as well as the centralized schemes.