基于神经网络的MUSIC计算方法  

A Novel MUSIC Algorithm Based on Neural Network

作　　者：邵东淼[1] 丁亚非[1] 王江[1] 

机构地区：[1]合肥电子工程学院404室,合肥230037

出　　处：《舰船电子工程》2012年第7期48-50,共3页Ship Electronic Engineering

摘　　要：MUSIC方法是空间谱估计中经典的子空间方法,这类算法有个共同特点就是要对输出数据的协方差矩阵进行数学分解,其计算量较大,不适合实时处理。因此,文章提出了基于神经网络的高效迭代方法,不需进行数学分解,计算过程相对简单。仿真结果证明了该方法的有效性。MUSIC algorithm is a classic suhspace method for spatial estimation. The MUSIC as high-resolution spatial estimation algo- rithm need to decompose eovariance matrix of the array output data, which involves large amount of computation and is not suitable for real- time processing. Therefore, a novel MUSIC algorithm based on neural network is proposed in this paper. This algorithm that needs no de- compose covariance matrix of the array, is relatively simple in the calculation process. Simulation results demonstrate the effectiveness of the new method.

关 键 词：MUSIC算法 神经网络 迭代算法 DOA估计 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]