THRESHOLD ANALYSIS OF SVD-BASED ALGORITHMS.
Date of Original Version
The problem of analyzing the threshold effect of signal processing algorithms which use the singular-value decomposition (SVD) is addressed. The probability of obtaining an outlier is calculated and used to determine the threshold SNR at which the variance of parameter estimation errors depart from Cramer-Rao bound behavior. Simulation results using low rank approximation and linear prediction for frequency estimation verify the analysis. The same method of analysis can be applied to a broad class of parameter-estimation methods in which principal-component technique or low rank approximations to matrices are used.
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Tufts, D. W., A. C. Kot, and R. J. Vaccaro. "THRESHOLD ANALYSIS OF SVD-BASED ALGORITHMS.." ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings , (1988): 2416-2419. https://digitalcommons.uri.edu/ele_facpubs/1193