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.
出处
《电子与信息学报》
EI
CSCD
北大核心
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
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
Signal processing
1/f-type fractal signal
Parameter estimation
Wavelet transform
White-Gauss noise
