论文部分内容阅读
提出一种自稳定的双目的算法用以提取信号自相关矩阵的特征对.该算法可以通过仅仅改变一个符号实现主/次特征向量估计的转化,并且可以通过估计的特征向量的模值信息估计对应的特征值,从而实现特征对的提取.基于确定性离散时间方法对所提出的算法进行收敛性分析,并确定算法收敛的边界条件.与已有算法对比的仿真实验验证了所提出算法的收敛性能.
This paper proposes a self-stable binocular algorithm to extract the feature pairs of signal autocorrelation matrix.The algorithm can transform the primary / secondary eigenvector estimation by changing only one symbol, and can estimate the eigenvectors’ The corresponding eigenvalues are estimated to extract feature pairs.The convergence of the proposed algorithm is analyzed based on the deterministic discrete-time method and the boundary condition of the algorithm convergence is determined.Compared with the existing algorithms, the simulation results verify that the proposed algorithm Convergence performance.