首页 | 官方网站   微博 | 高级检索  
     

基于自适应神经网络的二维线性相位FIR滤波器优化设计
引用本文:李目,何怡刚,刘祖润,周少武.基于自适应神经网络的二维线性相位FIR滤波器优化设计[J].电路与系统学报,2011,16(2):94-98.
作者姓名:李目  何怡刚  刘祖润  周少武
作者单位:湖南大学电气与信息工程学院;湖南科技大学信息与电气工程学院;
基金项目:国家杰出青年科学基金(50925727); 国家自然科学基金项目(50677014,60876022); 高校博士点基金项目(20060532016); 湖南省科技计划项目(2010J4); 广东省教育部产学研项目(2009B090300196)
摘    要:提出一种基于自适应三角函数基神经网络的二维线性相位FIR滤波器优化设计方法.该方法根据二维线性相位FIR滤波器幅频响应特性,采用三角函数基神经网络优化算法计算滤波器系数,同时在神经网络训练过程引入自适应学习率算法,提高神经网络的学习效率和收敛速度.通过训练神经网络的权值,使二维线性相位FIR滤波器幅频响应与理想幅频响应...

关 键 词:三角函数  神经网络  自适应学习率  二维圆形低通滤波器

Optimum design of two-dimensional linear-phase FIR filters based on adaptive neural network
LI Mu,HE Yi-gang,LIU Zu-run,ZHOU Shao-wu.Optimum design of two-dimensional linear-phase FIR filters based on adaptive neural network[J].Journal of Circuits and Systems,2011,16(2):94-98.
Authors:LI Mu  HE Yi-gang  LIU Zu-run  ZHOU Shao-wu
Affiliation:LI Mu1,2,HE Yi-gang1,LIU Zu-run2,ZHOU Shao-wu2(1.College of Electrical and Information Engineering,Hunan University,Changsha 410082,China,2.School of Information and Electrical Engineering,Hunan University of Science and Technology,Xiangtan 411201,China)
Abstract:A novel design method of two-dimensional(2-D) linear-phase FIR filters based on adaptive triangle function basis neural network is presented.According to the amplitude-frequency response characteristics of 2-D linear-phase FIR filters,coefficients of the filters are calculated using triangle function basis neural network algorithm.In the training of neural network,adaptive learning algorithm is applied in order to enhance learning efficiency and convergence rate.By training neural network weights,the algori...
Keywords:triangle function  neural network  adaptive learning rate  2-D circular low-pass filters  
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-23

京公网安备 11010802026262号