分布式多传感器决策融合系统求解

本文研究了分布式多传感器决策融合的信号处理，推导和求解在“双阈检验准则”下两个级别上的优化决策规则：一个是当局部检测器生成的个体决策结果被送到数据融合中心时，基于这些个体决策集合作出总的决策的融合规则；另一个是在总体决策融合规则给定情况下求解某一局部检测器的优化决策规则．所采用的“双阈检验法”是作者在Ｎ－Ｐ检验法基础上提出的新的融合方法，该方法由于引入了两类不明概率区而使传统的Ｂａｙｅｓ决策能力和适用范围得以扩大．本文还从减少计算量角度考察了分布式检测系统在观测独立情形下的优化决策规则简化计算公式．最后给出了简单算例，并加以验证．

Optimum Decision Fusion Solving of Distributed Multiple Sensor Systems

This study deals with signal processing for distributed multiple sensor systems that employ binary integration at each local .detector. Local decisions from individual sensors are fed to a data fusion center which then yields a global decision based on a fusion rule. A DHT formulation of the problem is considered and a person-by-person optimization of the overall system is carried out.Decision rules at the individual detectors and the fusion rule are obtained.The DHT method that was derived by improving Neyman-Pearson test is more applicable because of introduction of an indecision region between two decision regions which asserts the existence of "ignorance" and "uncertainty".The special case of identical detectors with independent observation is considered as well. An illustrative example is presented.