基于三阶循环平稳度准则的盲源分离算法

3-order Cycle Cumulant DCS Criteria BSS Algorithm

通过研究循环平稳信号的特性和分析传统的基于二阶统计量的盲源分离算法,在二阶循环平稳度的基础上提出了三阶循环平稳度的概念,并推导出了利用三阶循环累积量平稳度作为分离准则的新盲源分离算法。本算法可以在复杂噪声的情况下有效的分离平稳信号和循环平稳信号。仿真结果表明该算法能够抑制混合信号中的强噪声,算法简单,实时性好。

The properties of cyclostationary signals and the traditional second order statistics BSS algorithms were exploited, and then the definition of the 3-order degree of eyclostationary was proposed based on the second order degree of cyclostationary. After deducting 3-order statistics separation criterion of the degree of cyclostationary and demonstrating its effect, a new BSS algorithm based on the 3-order cumulant was proposed. The simulation results show that the new algorithm can suppress strong noises mixed in the source signal effectively and can meet real-time demand, so it is an efficient and simple new algorithm.