基于遗传算法的盲源分离算法

针对现有盲源分离算法的性能依赖于对比函数选择的现象,提出了一种基于遗传算法的盲源分离算法,该算法直接从信号的样本序列中估计出信号的概率分布,解决了信号间互信息的求解问题.通过遗传算法最小化信号的互信息,实现了对线性混叠信号的分离.对模拟信号的分离结果表明,该算法可以成功地分离混叠信号,同时与快速独立分量分析算法相比,该算法的性能对源信号的概率密度性质没有依赖,因而对亚高斯和超高斯信号的混合信号表现出更加优异的分离能力.

New Blind Source Separation Method Based on Genetic Algorithm

The performance of existing blind source separation methods is highly affected by the non-linear contrast functions that are selected according to the distribution of original signals, and the separation results are not always ideal, especially for the mixture of super-Gaussian signal and sub-Gaussian signal. To solve this problem, a new blind source separation method based on genetic algorithm is proposed, where the probability of separated signals is estimated directly from their samples, so the mutual entropy can be easily evaluated, and genetic algorithm is applied to find the separation matrix to minimize the mutual entropy. The simulated results show that the proposed method is superior to FastICA in separating the mixture of super-Gaussian signal and sub-Gaussian signal.