基于遗传算法的超亚高斯混合信号盲分离  

Blind source separation algorithm based on genetic algorithm for mixed sub-Gaussian and super-Gaussian signal

作　　者：高兴龙[1] 崔琛[1] 

机构地区：[1]解放军电子工程学院信息工程系,安徽合肥230037

出　　处：《信息与电子工程》2011年第5期614-618,共5页information and electronic engineering

摘　　要：针对基于扩展信息最大化算法的盲源分离算法在分离超亚高斯混合信号时依赖于信号的峭度估计且对初始分离矩阵和步长较为敏感的问题,提出了一种基于遗传算法的盲源分离算法。该算法以分离信号之间的互信息作为代价函数,采用非多项式函数的逼近方法解决了互信息求解过程中涉及到的负熵的计算问题,用遗传算法代替梯度寻优算法最小化代价函数。仿真结果表明:在分离超亚高斯混合信号时,该算法计算简单,鲁棒性好,迭代100次时性能指数值达到0.025 5,分离性能优于基于扩展信息最大化算法的盲源分离算法。The blind source separation algorithm based on extended informax algorithm in separating the super-Gaussian and sub-Gaussian mixed-signals depends on the signals kurtosis estimates,and it is sensitive to the initial separation matrix and step size.To solve these problems,a new algorithm based on genetic algorithm was proposed.In order to calculate the mutual information between signals the non-linear polynomial was used to approximate the negative entropy.Genetic algorithm instead of the gradient optimization algorithm was used to minimize the mutual information between the separated signals.Simulations show that the proposed algorithm is simple,robust;the Performance Index（PI） value reaches 0.025 5 after 100 times of iteration;and the performance is superior to the Blind Source Separation（BSS） algorithm based on extended infomax algorithm.

关 键 词：盲源分离 遗传算法 互信息 负熵 超高斯 亚高斯 

分 类 号：TN911.72[电子电信—通信与信息系统]