基于粒子滤波的混沌信号盲分离  

Blind Separation Based on Particle Filtering for Chaotic Signal

作　　者：徐茂格[1] 宋耀良[1] 刘力维[2] 

机构地区：[1]南京理工大学电子工程与光电技术学院,南京210094 [2]南京理工大学理学院,南京210094

出　　处：《电子与信息学报》2007年第12期2836-2839,共4页Journal of Electronics & Information Technology

摘　　要：该文首先建立了混沌信号盲分离问题的状态空间模型,进而通过引入Rao-Blackwellisaion策略和加扰动的方法,提出了一种基于粒子滤波的在线盲分离算法。在此基础上,为了降低分离后信号中的残留噪声,提出了新颖的延迟估计方法,很好地解决了传统的延迟加权(delay-weight)方法中信号源之间的相互干扰问题。A state space model for chaotic signal blind separation is first suggested, and then combined the Rao-Blackwellisaion （RB） strategy and incorporated roughening noise method, a particle filtering based online blind separation algorithm is proposed. To further decrease the residual noise in the online recovered signals, a novel delay estimation method which can effectively reduce the cross influence of source signals compared to the traditional delay-weight method is proposed.

关 键 词：混沌信号:盲分离 粒子滤波 

分 类 号：TN911.7[电子电信—通信与信息系统]