Optimization of distributed detection systems under the minimum average misclassification risk criterion

A common model for distributed detection systems is that of several separat ed sensors each of which measures some observable, quantizes it, and commun icates to a fusion center the quantized observation. The fusion center coll ects the quantized observations and takes the decision. The present corresp ondence deals with the design of the quantizers and of the fusion center un der a rate constraint. The system of interest allows soft nonbreakpoint qua ntizers and nonindependent observations. Our finding is that locally optima l design of the distributed detection system is feasible via alternate mini mization of the average misclassification risk.