加性噪声背景下基于ICA的线性系统辨识算法

在加性噪声背景下,将线性系统辨识问题纳入到独立分量分析(ICA)瞬时混合模型中,提出了一种新的结合ICA技术的线性系统辨识算法.该算法无需对噪声信号的统计特性进行任何先验假定,根据ICA模型中瞬时混合矩阵的先验知识,准确估计出系统输出的加性噪声,从观测数据减去该噪声后,利用最小二乘理论实现算法对未知系统的参数估计.仿真实验表明,该算法不仅有效地消除了一般算法对于噪声特性的限制,而且在低信噪比下仍能取得较为理想的辨识结果.

ICA-based Algorithm for Identification of Linear System with Additive Noisy Output

A novel noise subtraction method was proposed and investigated for estimating the parameters of a linear system with additive noisy output. This method treats the problem of system identification as the instantaneous mixing model defined in independent component analysis (ICA). Independent upon the statistics of the noise, the proposed method separates and subtracts the noise using some special characters of the mixing matrix, and then a following least-square approach is employed to estimate the parameters of the unknown system whose noise is canceled. Computer simulations utilizing a variety of additive noises indicate that the proposed method gives superior identification performance even at low SNR conditions.