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

基于LMK准则的前馈神经网络盲多用户检测算法
引用本文:孙云山,李昌华,马学伟,杨淼,方英杰,谢蓓雷,杨艺.基于LMK准则的前馈神经网络盲多用户检测算法[J].天津商学院学报,2008,28(3):17-20.
作者姓名:孙云山  李昌华  马学伟  杨淼  方英杰  谢蓓雷  杨艺
作者单位:天津商业大学信息工程学院 天津300134
摘    要:提出了一种基于前馈神经网络的盲多用户检测算法,该算法基于最小平均峰度准则构造了一个代价函数,给出了算法的约束条件,利用罚函数方法对带约束的代价函数进行优化,获得前馈神经网络网络权值的迭代公式,从而实现盲多用户检测。计算机仿真结果表明,新算法具有较强的多址干扰抑制性能。

关 键 词:盲多用户检测  前馈神经网络  LMK准则

Blind Multi-user Detection Algorithm of Feed-forward Neural Network Based on LMK Criteria
SUN Yun-shan,LI Chang-hua,MA Xue-wei,YANG Miao,FANG Ying-jie,XIE Bei-lei,YANG Yi.Blind Multi-user Detection Algorithm of Feed-forward Neural Network Based on LMK Criteria[J].Journal of Tianjin University of Commerce,2008,28(3):17-20.
Authors:SUN Yun-shan  LI Chang-hua  MA Xue-wei  YANG Miao  FANG Ying-jie  XIE Bei-lei  YANG Yi
Institution:( School of Information Engineering, Tianjin University of Commerce, Tianjin 300134, China)
Abstract:A novel blind multi-user detection algorithm based on feed-forward neural network(FNN) is proposed in the paper.A cost function based on Least Mean Kurtosis(LMK) criterion is founded,and the restraint condition of cost function is deduced.Weights and parameters of feed-forward neural network are optimized by punishment function,iterative formulas of FNN are obtained,and then blind multi-user detection algorithm is realized.Simulation results indicate that the novel algorithm has lower bit-error ratio and better convergence ability.
Keywords:blind multi-user detection  feed-forward neural network  LMK criterion
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