基于云模型和矢量神经网络的辐射源识别方法  

Approach Based on Cloud Model and Vector Neural Network for Emitter Identification

作　　者：刘海军[1] 柳征[1] 姜文利[1] 周一宇[1] 

机构地区：[1]国防科技大学电子科学与工程学院,湖南长沙410073

出　　处：《电子学报》2010年第12期2797-2804,共8页Acta Electronica Sinica

摘　　要：矢量神经网络在训练阶段既不能处理语义信息,也没有考虑训练样本本身的可靠性,因而造成辐射源不能正确识别的问题,为此提出了一种基于云模型和矢量神经网络的识别算法.该算法利用云模型来实现定性概念到定量区间值的转换,并利用改进后的矢量神经网络实现区间类型的矢量输入到区间类型型号输出的非线性映射.仿真实验表明,本文方法不仅能处理语义类型的输入矢量,而且能够处理数字类型的输入矢量,并且在测量误差环境中具有较高的识别率.To deal with the problem of emitter identification caused by the vector neural network（VNN）,which is incapable of processing the linguistic information and considering the reliability of the training samples in training phases,this paper proposes a new identification method based on cloud model and vector neural network（CMVNN）.The new method,which utilizes the cloud model to realize the transformation from qualitative concepts to their quantitative interval expressions,can make use of the improved vector neural network to come true the nonlinear mapping between the interval-value input data and the interval-value output emitter types.A number of simulations are presented to demonstrate the performance of the CMVNN algorithm,including processing 3-type emitter identification problem. Simulation results show that the CMVNN algorithm not only processes the linguistic and numerical input data,but also has higher identification rate in environment with measure errors.

关 键 词：雷达 辐射源识别 云模型 矢量神经网络 区间值 识别率 

分 类 号：TN95[电子电信—信号与信息处理]