节点文献

基于Lagrange乘子法的神经网络盲多用户检测算法的研究

The Research of Blind Multiuser Detection Using Neural Network Based on Lagrange Penalty Function

【作者】 李福平

【导师】 张立毅;

【作者基本信息】 太原理工大学 , 信号与信息处理, 2006, 硕士

【摘要】 码分多址系统中,不同用户的随机接入,使得用户之间扩频码不完全正交,进而产生了多址干扰(Multi-access interference,MAI)和远近效应(Near-far effect,NFE)等问题,常规的匹配滤波器无法克服这些问题。多用户检测技术充分考虑造成多址干扰的用户结构和干扰信息,成为消除多址干扰和远近效应的关键技术。目前,大多数多用户检测算法存在算法复杂、收敛速度慢等缺点,使得长期以来没有真正的实现应用。近年来,基于神经网络的盲多用户检测结合了盲多用户检测对已知信息量需求少和神经网络运算速度快、并行处理能力强的优点,而成为研究的热点课题。 本文的主要工作如下: 1.在介绍多用户检测原理的基础上,对现有一些算法的性能、特点和不足进行了分析,并对今后的发展方向进行了研究。 2.针对现有算法收敛时间长、误码率高等不足,提出了两种盲多用户检测算法。第一种为多约束LNN盲多用户检测算法,通过增加约束项来使目标函数较快地收敛到最小点;第二种为改进型LNN盲多用户检测算法,通过将罚函数与Lagrange函数结合,构造出更适合

【Abstract】 In the CDMA wireless communications system , multi-access interference and near-far effect exist because spread codes between users are not completely orthogonal along with different users random accessing, regular filter can not overcome these questions. Multiuser detection is a key technique erasing MAI and NFE due to think fully about user structure making MAI and interference information. Nowadays, a lot of multiuser detection algorithms hold flaws such as sophisticated algorithm, low speed of convergence and so on, thus, MUD isn’t really realized using. Recently, blind multiuser detection based on neural network became a research focus, integrates merits needing a few using informations of blind MUD with merits of neural network such as quickly speed, stronge processing, and so on.The major works of this paper are summarized as follow:1. The principle of MUD is introduced in this paper, and the

  • 【分类号】TN929.533
  • 【被引频次】1
  • 【下载频次】82
节点文献中: 

本文链接的文献网络图示:

本文的引文网络