Parameter Estimation of Damped Sinusoidal Signal Based on Linear Prediction Method

This paper presents, a novel method for estimating the damping factor and frequency of real-valued damped Sinusoidal signals. The proposed approach models the damping factor and frequency using the coefficients of an autoregressive (AR) model, estimated through the Generalized Eigenvalue Problem (GEP) method. Evaluation results demonstrate the method’s superior performance, particularly in terms of Mean Squared Error (MSE) across a wide frequency range. Notably, at both low and high frequencies, the proposed method exhibits significantly lower MSE values, implying that proposed method consistently outperforms in overall reliability and robustness for damping factor and frequency estimation.