Title :
The calculation of features for non-stationary signals from moments of the singular value decomposition of Cohen-Posch (positive time-frequency) distributions
Author_Institution :
Naval Surface Warfare Center, Bremerton, WA, USA
Abstract :
This paper presents a new method for determining the principal features of a non-stationary time series process based on the singular value decomposition (SVD) of the Cohen-Posch (1985) positive time-frequency distribution. This new method uses density functions derived from the SVD singular vectors to generate moments that associate with the principal features of the non-stationary process. Since the SVD singular vectors are orthonormal, the vectors whose elements are composed of the squared-elements of the SVD vectors are discrete density functions. Moments generated from these density functions are the principal features of the non-stationary time series process
Keywords :
feature extraction; singular value decomposition; statistical analysis; time series; time-frequency analysis; Cohen-Posch positive time-frequency distribution; SVD; density functions; discrete density functions; feature extraction; moments; nonstationary signals; nonstationary time series process; orthonormal singular vectors; principal features; singular value decomposition; squared-elements; Density functional theory; Entropy; Kernel; Matrix decomposition; Signal analysis; Signal processing; Singular value decomposition; Spectrogram; Statistical analysis; Time frequency analysis;
Conference_Titel :
Time-Frequency and Time-Scale Analysis, 1998. Proceedings of the IEEE-SP International Symposium on
Conference_Location :
Pittsburgh, PA
Print_ISBN :
0-7803-5073-1
DOI :
10.1109/TFSA.1998.721497
