Pf. Swaszek et P. Willett, PARLEY AS AN APPROACH TO DISTRIBUTED DETECTION, IEEE transactions on aerospace and electronic systems, 31(1), 1995, pp. 447-457
Decentralized detection networks implement local likelihood ratio test
s at each sensor and combine the local decisions into a global decisio
n In general this is a ''one pass'' procedure, with data transmission
from the sensors (or subordinate decision makers) to the fusion center
. There have been treatments of multipass schemes, but usually the app
roach has been to update the local decisions based on the previous fus
ed decision. We explore the use of feedback (of all sensor decisions t
o all sensors) and successive retesting and rebroadcasting of the upda
ted decisions until a common decision or consensus is reached, an oper
ation we call parley due to its similarity to the process of discussio
n and negotiation by a team of human decision makers. We consider two
modes of operation of such a network. In the first, all sensors are as
correct as possible at all times. We see that this network is fast in
reaching consensus, but not particularly as ''correct'' as it could b
e. Under the second scheme, we observe that via feedback it is possibl
e for the network to make an optimum decision-this may, of course, req
uire several rounds of parley. Of particular interest is that under bo
th schemes a consensus always occurs-the sensors never ''agree to disa
gree''.