新的正交最小二乘方法

Novel orthogonal least squares algorithm

正交最小二乘是一种贪婪算法,采用逐步回归建模,每一步利用搜索算法找到最小化残差的一个回归项。将其拓展为每一步搜索多个最优的回归项,从而得到一种稀疏的回归方法,并将其应用于谐波分量提取中。仿真实验说明,新方法不仅能够较为精确地逐项估计出分量的参数,而且可以对分量个数进行有效的估计。

Orthogonal least squares（OLS） regression utilizes a greedy scheme to tune the parameters of each individual regressor term by term.To improve the performance of the greedy-scheme-based OLS algorithm,a tree structure search algorithm is constructed.At each regressor stage,this proposed OLS algorithm is realized by keeping multiple ＂best＂ regressors rather than using the ＂optimal＂one only.The new approach is used in harmonic retrieval.Numerical results show that this new scheme is capable of estimating not only the number of the harmonic components in the given signals but also the parameters of harmonic.