OPTIMIZATION OF DETECTION NETWORKS WITH MULTIPLE EVENT STRUCTURES

We consider a multilevel hierarchical decision network faced with a di stributed binary detection problem with partial information at the ind ividual decisionmaker (DM). The partial information is modeled by diff erent local events at the DM's, and these local events are probabilist ically related to one another. Solution to this generalized hypothesis testing problem is obtained using the optimal control approach, where the optimization criterion is the expected decision cost of the netwo rk. The impacts of variations in the correlation of events at two comm unicating nodes on the aggregated expertise of the network and on the overall decision cost are illustrated via a numerical example.