A UNIFIED APPROACH TO THE DESIGN OF DECENTRALIZED DETECTION SYSTEMS

A unified approach to the design of decentralized detection networks w ith arbitrary topologies is proposed and analyzed In this approach, a decentralized detection system of arbitrary topology is represented by a communication matrix that specifies the interconnection structure o f the detection network. This matrix is used to derive the general dec ision rule using the person-by-person-optimal (PBPO) solution methodol ogy. It is shown that the PBPO decision rule is a likelihood ratio tes t for statistically independent observations. The threshold of the tes t is shown to be a function of the decision input vector of the detect or under consideration. This unified approach is used to obtain the PB PO decision rules of decentralized detection systems with various topo logies. Various results in the literature are verified. In addition, t he PBPO decision rules for a decentralized detection system with peer communication are presented Numerical examples are presented for illus tration.