A General Fuzzy Modeling Approach to Detection Decision Fusion

A general fuzzy modeling approach to detection decision fusion is considered where local false and miss probabilities, priori probabilities, and cost functions are fuzzy numbers with trapezoidal memberships. A Bayesian approach is used to design the optimum fusion rule for the case where the local sensor decisions are statistically independent across the sensors. By using the approaches of defuzzification and total distance criterion (TDC) fuzzy set ranking method, three decision fusion rules are derived and the average Bayesian risks at the fusion center are correspondingly obtained. The performance of each fusion rule obtained is illustrated by means of some numerical examples. The fusion rule based on TDC fuzzy set ranking method may be a good choice.