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

神经Chebyshev正交多项式均衡器及自适应算法
引用本文:邓晓红,张家树.神经Chebyshev正交多项式均衡器及自适应算法[J].西南交通大学学报,2005,40(2):163-167,178.
作者姓名:邓晓红  张家树
作者单位:1. 西南交通大学科学研究处,四川,成都,610031
2. 西南交通大学计算机与通信工程学院,四川,成都,610031
基金项目:国家自然科学基金资助项目(60792096)
摘    要:提出一种全新结构的非线性均衡器———神经Chebyshev正交多项式自适应均衡器.该均衡器由1个非线性神经自适应滤波器和1个Chebyshev正交多项式滤波器级联而成.基于最陡下降方法,推导出了相应的自适应算法.仿真结果表明,在线性信道中,该均衡器的均方误差(MSE)比神经自适应均衡器和二阶Volterra均衡器小;在非线性信道中,以更为简单的结构达到了和BP算法训练的三层神经网络相似的性能.

关 键 词:信道均衡  自适应算法  Chebyshev正交多项式  神经自适应滤波器
文章编号:0258-2724(2005)02-0163-06

Neural Chebyshev Orthogonal Polynomial Equalizer and Its Adaptive Algorithm
DENG Xiao-hong,ZHANG Jia-shu.Neural Chebyshev Orthogonal Polynomial Equalizer and Its Adaptive Algorithm[J].Journal of Southwest Jiaotong University,2005,40(2):163-167,178.
Authors:DENG Xiao-hong  ZHANG Jia-shu
Abstract:A new structure of nonlinear equalizer-neural Chebyshev orthogonal polynomial adaptive equalizer was proposed. It is composed of a nonlinear neural adaptive filter and a Chebyshev orthogonal polynomial filter. The corresponding adaptive algorithm was derived based on the steepest descent method. Simulation results show that the proposed equalizer has less mean square error (MSE ) compared with the neural adaptive equalizer and the SVE ( second-order volterra equalizer )in linear channel, and that it can achieve similar good performances as the 3-layered neural network trained with BP algorithm in the nonlinear channel with a simpler structure.
Keywords:channel equalization  adaptive algorithm  Chebyshev orthogonal polynomial  neural adaptive filter
本文献已被 CNKI 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