首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于特征矢量输入的神经网络测向方法
引用本文:陈荆花,易辉跃,周希朗.基于特征矢量输入的神经网络测向方法[J].上海交通大学学报,2003,37(3):373-375,379.
作者姓名:陈荆花  易辉跃  周希朗
作者单位:上海交通大学电子工程系,上海,200030
摘    要:提出了一种新的基于特征矢量的采集输入数据方法,经该方法训练的径向基函数神经网络(RBFNN)可用于码多分址(CDMA)系统中多源信号波达角(DOA)的估计。该方法对信道噪声不敏感,能以较少的训练样本就可得到推广能力较好的神经网络。仿真结果表明,以新方法训练的RBFNN对多源信号DOA估计精度较高,实时性好,适用于CDMA通信系统的高分辨率测向。

关 键 词:码分多址  径向基函数神经网络  波达角估计
文章编号:1006-2467(2003)03-0373-03

Direction of Arrival Estimation Method with Eigenvector- Based Radial Basis Function Neural Network
CHEN Jing hua,YI Hui yue,ZHOU Xi lang.Direction of Arrival Estimation Method with Eigenvector- Based Radial Basis Function Neural Network[J].Journal of Shanghai Jiaotong University,2003,37(3):373-375,379.
Authors:CHEN Jing hua  YI Hui yue  ZHOU Xi lang
Abstract:A new direction of arrival (DOA) estimation method with eigenvector based radial basis function neural network (RBFNN) was presented. This new method is not sensitive to noise and takes fewer training data to get RBFNN with good generalization ability. The computer simulation shows that the RBFNN trained with this algorithm is excellent at DOA estimation, and it is more suitable for real time application than classic superresolution algorithms. This DOA estimation method is promising in smart antenna of CDMA communication.
Keywords:code  division multiple access (CDMA)  radial basis function neural network (RBFNN)  direction of arrival (DOA ) estimation
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号