Analysis of the Cramér-Rao Lower Bounds for unbiased parameter estimators of noisy damped sinusoids
Year: 2025
Type: article
Abstract: • Approximated expressions for the Cramér-Rao Lower Bounds (CRLBs) of the unbiased estimators of complex-valued noisy damped sinusoids are derived. • Derivation of simple CRLBs expressions when the observation duration is either enough smaller or enough greater than the signal time constant. • Constraints on the number of analyzed samples that allow the optimization of the tradeoff between estimation accuracy and processing effort are derived. • Accuracy verification of the derived expressions for the CRLBs. In this paper the Cramér-Rao Lower Bounds (CRLBs) for unbiased estimators of the parameters of complex-valued noisy damped sinusoid are comprehensively analyzed assuming that enough samples are acquired in an interval duration equal to the signal time constant. At first accurate, but simple, expressions for the CRLBs are derived. Then, even simpler expressions are obtained assuming that the observation duration is either enough smaller or enough greater than the signal time constant. Leveraging on the derived expression, constraints on the number of analyzed samples that allow the optimization of the tradeoff between estimation accuracy, estimation delay, and processing effort are derived. They can be useful to optimize measurement procedures aimed at estimating unknown signal parameters. The accuracies of the derived results are verified through computer calculations and the application of a state-of-the-art almost unbiased and statistically efficient algorithm.
Source: Measurement
Authors: Dario Petri, Daniel Belega
Institutions: University of Trento, Politehnica University of Timisoara
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $3,760
OpenAlex ID: W4416186435