| 基于余弦基神经网络的FIR滤波器设计 |
| Design of FIR Filter Based on Cosine-basis Neural Network |
| 投稿时间：2004-11-30 修订日期：2004-12-30 |
| HTML 查看全文 查看/发表评论 下载PDF阅读器 |
| 中文摘要: |
| 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。 |
| 英文摘要: |
| 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. |
| 周维 许海霞 |
| 湘潭大学信息工程学院,湖南湘潭411105 |
| 中文关键词: 神经网络 余弦基 FIR滤波器 幅频特性 |
| 英文关键词:neural network cosine basis FIR filter amplitude-frequency characteristic |
| 基金项目: |
| DOI： |
| 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].计测技术,2005,25(4):9~10,58. |
| 关闭 |
