A multi-sensor decision fusion scheme is presented in which the probabiliti
es associated with the local sensor decisions are known to vary in a nonran
dom fashion around their design values. The uncertainties associated with t
he local decisions are modeled by means of fuzzy sets. A Bayesian approach
is used to design the optimum fusion rule for the case where the local sens
or decisions are statistically independent across the sensors. In order to
reach a crisp decision, the global Bayesian risk is defuzzified using a cri
terion for mapping fuzzy sets on to the real line. The performance of the o
ptimum fusion rule obtained is illustrated by means of a numerical example.
(C) 2000 Elsevier Science B.V. All rights reserved.