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

基于余弦基神经网络的FIR滤波器设计
引用本文:周维,许海霞.基于余弦基神经网络的FIR滤波器设计[J].航空计测技术,2005,25(4):9-10,58.
作者姓名:周维  许海霞
作者单位:湘潭大学信息工程学院,湖南湘潭411105
摘    要:提出了一种基于余弦基神经网络FIR滤波器的设计方法。根据线性相位FIR滤波器的幅频特性是有限项的傅里叶级数,构造了一个三层余弦基神经网络模型,并给出了最优隐层神经元的个数。经模拟仿真,滤波器性能非常理想,具有同时输出低通、高通、带通、带阻各种功能,通带、阻带无过冲无波动,边界频率可以精确控制。

关 键 词:神经网络  余弦基  FIR滤波器  幅频特性
文章编号:1002-6061(2005)04-0009-02
收稿时间:2004-11-30
修稿时间:2004-11-302004-12-30

Design of FIR Filter Based on Cosine-basis Neural Network
Zhou Wei;Xu HaiXia.Design of FIR Filter Based on Cosine-basis Neural Network[J].Aviation Metrology & Measurement Technology,2005,25(4):9-10,58.
Authors:Zhou Wei;Xu HaiXia
Abstract:A method of design of FIR filter based on neural network is proposed in this paper. Amplitude-frequency FIR filter with linear phase is characteristic of finite fourier progression. So a neural mode of cosine basis with three layers is set up, and optional net nodes are discussed. Simulation result shows that better result can be achieved to all kinds of digital filter. There is no fluctuating, frequency value is easy to control precisely.
Keywords:neural network  cosine basis  FIR filter  amplitude-frequency characteristic
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