基于差分进化算法实现非高斯噪声下盲信号分离

Blind Signals Separation of α Stable Distribution Based on Differential Evolution

简要介绍了稳定分布统计特性,推导了一种适用于α稳定分布噪声下盲信号分离的算法。该算法采用差分进化算法对目标函数自动寻优,求得分离矩阵,从而分离出信号。仿真结果表明:该算法分数低阶α稳定分布背景噪声条件下具有良好的分离效果。

In this paper,the statistic characteristic of stable distribution is investigated and a new algorithm is proposed for blind signals separation（BSS） of signals or noise with α stable distribution.By using differential evolution,the proposed algorithm finds the global optimal solution of objective function and obtains the separating matrix so that the signals are separated successfully.Simulation results indicate that the proposed method has better performance for the separate of signals or noise with α stable distribution.