基于遗传算法和神经网络的多用户检测器  

A Multiuser Detector Based on Genetic Algorithm and Neural Network

作　　者：唐普英[1] 陈永倩[1] 黄顺吉[1] 

机构地区：[1]电子科技大学光电信息学院,成都610054

出　　处：《信号处理》2002年第6期526-529,共4页Journal of Signal Processing

摘　　要：利用两种方法的优点,并将它们应用于CDMA多用户检测中,提出一种基于并行遗传算法和递归神经网络的多用户检测器。该检测器中,遗传算法首先给神经网络提供较好的初始值,然后神经网络实时快速地获得最优解。计算机模拟结果表明:本文所提出的检测器在误码率和抗“远近”效应方面均具有良好的性能。The advantages of GA and NN are applied to the multiuser detection in CDMA communication. A multiuser detector based on parallel genetic algorithm and recurrent neural network is proposed. In this detector, GA providces the initial value to NN, and then the NN gets the optimal solution in real time and quickly. Computer simulation results show that the method has powerful properties both in bit error rate and near-far resistance.

关 键 词：遗传算法 神经网络 多用户检测器 信号检测 码分多址 多址干扰 

分 类 号：TN911.23[电子电信—通信与信息系统]