基于神经网络的宽带相干DOA估计方法的改进
An Improved Neural Network for Wideband Doa Estimates
-
摘要: 相干信号子空间处理方法(CSM)是一种通过构造聚焦(focusing)矩阵来估计宽带 相干源波达方向(DOA)的有效方法.基于逆传播(Back-propagation)学习算法.对神经网 络实现聚焦过程的方法进行了网络结构及模式的改进,使网络可以在未知波达方向个数时完 成聚焦过程;同时,使学习空间从D(DOA个数)维降为1维,大大地简化了学习过程,加速了 网络的收敛过程.Abstract: Coherent signal-subspace method (CSM) is an efficient method for wideband DOA estimates based on constructing focusing matrices. In this paper, a new BP neural network is proposed to complete the contruction procedure. The proposed network has much less neutrons in the input and output layers than before. The leraning procedure and convergence procedure are also accelerated. Further, the network is generlized to the case that the number of DOA's is unknown.
-
Key words:
- DOA /
- wideband /
- neural network
-
计量
- 文章访问数: 2211
- HTML全文浏览量: 60
- PDF下载量: 961
- 被引次数: 0
下载:
