Frequency Estimation by Principal Component AR Spectral Estimation Method without Eigendecomposition
Document Type
Article
Date of Original Version
1-1-1988
Abstract
For accurate frequency estimation, principal component autoregressive spectral estimation methods have received considerable attention in the recent literature. Explicit computation of the eigendecomposition of the autocorrelation matrix is required to obtain the principal component solution. An alternative approach called the eigenvalue filtering method, which does not require explicit computation of the eigenvalues and the eigenvectors, is proposed in this paper. The proposed method applies a transformation to the autocorrelation matrix which has the effect of truncating the undesired eigenvalues so that the corresponding matrix function closely approximates the pseudoinverse. It is shown via computer simulation that compared to the forward-backward method, the proposed method enhances the threshold in SNR by about 6–8 dB. Further improvement is obtained by a simple subset selection method and a second eigenvalue filtering iteration. © 1988 IEEE
Publication Title, e.g., Journal
IEEE Transactions on Acoustics, Speech, and Signal Processing
Volume
36
Issue
1
Citation/Publisher Attribution
Kay, Steven M., and Arnab K. Shaw. "Frequency Estimation by Principal Component AR Spectral Estimation Method without Eigendecomposition." IEEE Transactions on Acoustics, Speech, and Signal Processing 36, 1 (1988): 95-101. doi: 10.1109/29.1492.