Improving Spectral Resolution of a Stationary Signal Using Singular Value Decomposition

Abstract

A new approach to detecting Periodic Components with random phases of stationary time series corrupted by random component
is considered. The approach is based on usage of the new time series, which is the union of the principal singular
vectors of the data matrix of the original time series. The approach allows significant improvement of resolving capacity for all
existed method of pseudospectra estimation. The comparative examples, illustrated practical efficiency of the approach are
considered.