1/f类分形信号的最小二乘法参数估计  

Parameter Estimation of 1/f-Type Fractal Signal Using Least Square Method

作　　者：郜峰利[1] 郭树旭[1] 张振国[1] 于思瑶[1] 李雪妍[1] 

机构地区：[1]吉林大学电子科学与工程学院,长春130012

出　　处：《电子与信息学报》2009年第7期1746-1748,共3页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(60471009);吉林省重大科技发展计划(200403001-4)资助课题

摘　　要：根据含噪1/f类分形信号的小波变换系数方差随尺度变化的特点,该文提出了一种估计1/f类分形信号参数的新方法,即对其小波系数方差进行简单的变换,使1/f类分形信号参数估计满足最小二乘法参数估计的条件。仿真实验结果表明,该方法可以有效地从加性白噪声背景下估计出1/f类分形信号的γ,σ2等参数,从而使1/f类分形信号与加性白噪声分离。A novel method to estimate the parameters of 1/f-type fractal signal is proposed according to characteristics of the wavelet coefficient variance versus scale of 1/f-type fractal signal in white noise, and namely, after the wavelet coefficient variance is simply transformed, the parameter estimation of 1/f-type fractal signal is according with parameter estimation conditions of least square method. The simulation experiment results demonstrate that, this method can effectively estimate parameters of 1/f-type fractal signal such as γ and （72 etc. to extract them from additive white noise.

关 键 词：信号处理 1/f类分形信号 参数估计 小波变换 高斯白噪声 

分 类 号：TN911.7[电子电信—通信与信息系统]