基于D-S证据理论和BP神经网络的多传感器信息融合

针对多传感器信息融合的基本可信度分配在实际应用中难以解决的问题,提出了一种基于D-S证据理论与BP网络相结合的多传感器信息融合的改进方法。该方法充分发挥BP神经网络自学习、自适应和容错的能力,利用BP神经网络处理证据理论的基本可信度问题,再利用D-S证据理论来处理不精确、模糊的信息。最后通过一个实例证明了该方法的有效性。

Multisensor information fusion based on D-S evidence theory and BP neural network

Based on multisensor information fusion for the basic probability assignment in the practical application problem difficult to solve,This paper presents a method of multisensor information fusion based on BP neural network and DS evidence theory.The method can give full play to self-study of BP neural network,self-adapting and fault-tolerant ability,And also it use D-S＇s Evidence to deal with the in accuracy and fuzzy information.Finally,an example shows the effectiveness of the method.