基于广义特征值和核函数的非线性盲分离算法  

Algorithm for nonlinear blind source separation based on generalized eigenvalue decomposition and kernel feature space

作　　者：高鹰[1] 姚振坚[1] 李朝晖[1] 谢胜利[2] 

机构地区：[1]广州大学信息学院计算机科学与技术系,广东广州510006 [2]华南理工大学电子与信息学院,广东广州510641

出　　处：《系统工程与电子技术》2006年第10期1490-1493,共4页Systems Engineering and Electronics

基　　金：中国博士后科学基金(2003034062);广州市科技计划项目(2004J1-C0323);广州市市属高校科技计划项目(2055)基金资助课题

摘　　要：在给出了一种基于广义特征值分解的线性混合信号盲分离方法的基础上,结合核特征空间而给出了一种非线性混合信号盲分离算法。该算法首先将混合信号映射到高维核特征空间,同时构造该核特征空间的一组正交基。其次,通过这组正交基将高维核特征空间的信号映射到参数空间,从而把非线性混合信号盲分离问题转化为参数空间的线性混合信号盲分离问题。在参数空间中,应用基于广义特征值分解的线性混合信号盲分离方法对信号进行分离。该算法具有闭解形式,计算简单,收敛精度较高,稳定性好。仿真结果表明该算法是有效的,具有良好的分离性能。A linear blind source separation algorithm based on generalized eigenvalue decomposition is presented. Then a nonlinear blind source separation algorithm is proposed by extending the linear blind source separation algorithm to the nonlinear domain. The received mixing signals are first mapped to high-dimenslonal kernel feature space, and an orthonormal basis of the kernel feature space is constructed. Next, in the kernel feature space, the mixing signals are parameterized by the orthonormal basis. Finally, the linear blind source separation algorithm based on signal variability is applied to the parameterized mixing signals. The proposed algorithm has a closed-form solution and simple computation, and is characterized by high accuracy, and robustness. Simulation results illustrate the efficiency and good performance of the algorithm.

关 键 词：广义特征值分解 核特征空间 盲信号分离 非线性混舍 

分 类 号：TN911.72[电子电信—通信与信息系统]