摘要
提出了一种基于两步法的欠定盲源分离新算法。在混合矩阵估计阶段,采用基于势函数的聚类方法,在源信号恢复阶段,提出一种快速的稀疏信号重构算法,通过定义一个连续可微函数来近似l0范数,使得l0范数可解。该算法的特点是实现简单、速度快。仿真实验表明,与现有的采用快速l1范数最小化和OMP算法的欠定盲源分离方法相比,提出的算法在保证分离性能的前提下大幅度提高了算法的运行速度。
A new two-step algorithm for underdetermined source separation is proposed.Mixing matrix is estimated using clustering methods.Sources are estimated using a fast sparse reconstructed algorithm which defines a continuous and differential function so as to approximate l0-norm.The new algorithm runs fast and is easily implemented.It is experimentally shown that the proposed algorithm runs faster than other two underdetermined source separation algorithms using fast minimization l1-norm and OMP methods,while acquiring almost the same quality.
出处
《计算机工程与应用》
CSCD
2012年第12期112-115,共4页
Computer Engineering and Applications
关键词
欠定盲源分离
稀疏分量分析
两步法
l0范数
underdetermined blind source separation
sparse component analysis
two-step method
l0-norm