This paper proposes a new algorithm of blind source separation (BSS). The algorithm can overcome the difficulty known as 'the sensors are less than the source signals' and works effectively when the sensors ar...
详细信息
This paper proposes a new algorithm of blind source separation (BSS). The algorithm can overcome the difficulty known as 'the sensors are less than the source signals' and works effectively when the sensors are less. Then, the paper discusses the nonlinear functions used in the new algorithm. A uniform nonlinear function is proposed and some criterion are given to choose its parameters. Finally, some simulations are presented to show the effectness of the algorithm and the correctness of the criterion.
基于泰勒级数展开的近似函数法在求解非线性函数的中误差时需要进行复杂的导数计算,已有的Monte Carlo法虽然可以避免导数运算,但在模拟次数的选择上不具有客观性,且无法直接控制模拟结果。因此,将Stein两阶段法融入非线性函数的协方差传播理论中,并与Monte Carlo方法结合,设计了一套非线性函数协方差传播的Stein Monte Carlo算法流程。将该方法用于二维多项式函数和GNSS基线向量的协方差传播计算中,实验结果验证了其有效性,为非线性模型协方差传播的计算提供了一种新思路。
暂无评论