基于无先导卡尔曼滤波的卷积混沌信号的盲提取

Blind Extraction of Chaotic Signals from Convolutive Mixture Using Unscented Kalman Filter

从卷积混合的混沌信号中提取出所需的信号是一个挑战性课题.假设需要提取的混沌信号的映射已知,寻找提取向量的问题就可以转化为非线性系统的状态检测问题.为此,提出了一种基于无先导卡尔曼滤波的盲提取算法.仿真结果证明在无噪声或高信噪比情况下该算法的有效性.

Blind extraction of chaotic signals from a convolutive mixture is a challenging issue.Assuming that the dynamics of the chaotic signals to be extracted is known,the determination of the desired extracting vector is formulated as the problem of state estimation of nonlinear systems.In this paper,a blind extraction method is proposed,which is based on unscented Kalman filter（UKF）.Simulation results have confirmed the effectiveness of the proposed method under noiseless or high SNR＇s channels.