In a traditional communication system, a single sensor such as a radar or a sonar is used to detect targets. Since the reliability of a single sensor is limited, distributed detection systems in which several sensors are employed simultaneously have received increasing attention in recent years. We consider a distributed detection system which consists of a number of independent local detectors and a fusion center. Chair and Varshney have derived an optimal decision rule for fusing decisions based on. the Baysian criterion. To implement such a rule, the probability of detection P_D and the probability of false alarm P_F for each local detector must be known. This thesis introduces an adaptive fusion model using the fusion result as a supervisor to estimate the P_D and P_F The fusion results are classified as "reliable" and "unreliable". Reliable results will be used as a reference to update the weights in the fusion center. Unreliable results will be discarded. The thesis concludes with simulation results which conform to the analysis.