Statistical ranking of sensor observations for centralized detection with distributed sensors

This paper investigates data reduction strategies from signal processing perspective for centralized detection with distributed sensors. We consider a deterministic source observed by a network of sensors and develop an analytical strategy for ranking sensor transmissions based on their test statistics. The benefit of the proposed strategy is that in certain scenarios, the decision to transmit or not to transmit to the fusion center can be made at the sensor level, resulting in significant savings in transmission costs. We derive a theoretical bound on the number of sensor transmissions saved. Our results complement existing results in the literature. We simulate the proposed strategy and demonstrate its benefits over the unconstrained energy approach.