节点文献
1/f类分形信号的小波去噪方法
Study on the Wavelet-based Denoising for 1/f Fractional Signals
【摘要】 提出了一种用基于分形信号在不同尺度下小波系数方差来估计噪声方差及分形信号参数的新方法,进而从加性白噪声背景下估计出1/f类分形信号。仿真实验结果表明:该方法简单可靠,有效可行,且事先不需要知道分形信号参数及加性白噪声的统计特性,并对信噪比估计误差有很好的鲁棒性。
【Abstract】 Based on the variance of the wavelet coefficients of fractal signal at different levels,a new method of estimating the variance of added noise and the parameters of fractal signal was proposed in this paper,then the 1/f fractal signal can be estimated from the additive white noise.The simulation results show that this method is simple,reliable,practicable and effective because it doesn′t need to know the parameters of fractal signal and the statistical characteristics of added white noise in advance,besides that,this method is robust to the error of SNR estimated.
【关键词】 1/f类分形信号;
信号估计;
小波变换;
【Key words】 1/f fractal signal; signal estimation; wavelet transformation;
【Key words】 1/f fractal signal; signal estimation; wavelet transformation;
- 【文献出处】 吉林大学学报(工学版) ,Journal of Jilin University of Technology(Natural Science Edition) , 编辑部邮箱 ,2003年01期
- 【分类号】TN911.72
- 【被引频次】12
- 【下载频次】226