论文部分内容阅读
次成分分析是信号处理领域一门重要的工具.然而,到目前为止能够进行多个次成分提取的算法并不多见,一些现存算法还存在很多限制条件.针对这些问题,采用加权矩阵的方法将M?ller算法扩展为多个次成分提取算法.该算法对于输入信号的特征值没有要求,而且在不需要模值限制措施的情况下,仍然具有很好的收敛性.仿真结果表明,该算法可并行提取多个次成分,而且收敛速度优于一些现有算法.
Sub-component analysis is an important tool in the field of signal processing.However, algorithms that can extract multiple sub-components so far are rare and some of the existing algorithms still have many limitations.To solve these problems, a weighted matrix method The M l ller algorithm is extended to a number of sub-component extraction algorithms, the algorithm has no requirements for the eigenvalues of the input signal, and it still has good convergence without the need of modulo limitation. The simulation results show that The algorithm can extract multiple sub-components in parallel, and the convergence speed is better than some existing algorithms.