摘要
该文考虑用带有噪声输出数据的累计量实现对非最小相位FIR系统的参数辨识问题。提出一个新的基于高阶累计量的方法。其特点如下,(1)灵活性:采用了两个任意阶次相邻的输出累计量;(2)线性:方法的表达式相对于未知量为线性。这不同于其它一些已存在的算法。因而,避免了额外的滞后处理,可提高参数估计的准确性。本文在ARMA高斯噪声及三种实际噪声情况下,做了大量的实验。结果表明,本文提出的算法不仅能有效地完成参数估计,而且,在低信噪比下,其估计结果比其它已有的算法更准确。
The problem of identifying the parameters of the nonminimum phase FIR system from the cumulants of noisy output samples is addressed. A novel method by using higher-order cumulants is proposed with the following advantages. (1) Flexibility: the method employs two arbitrary adjacent order cumulants of output. (2) Linearity: the formulation in the method is linear with respect to the unknowns, unlike the existing cumulant-based algorithms. The post-processing is thus avoided.
