Recovering Sinusoids from Noisy Data Using Bayesian Inference with Simulated Annealing

[摘要] In this paper, we studied Bayesian analysis proposed by Bretthorst[6] for a general signal model equation and combined it with a simulated annealing (SA) algorithm to obtain a global maximum of a posterior probability density function (PDF) for frequencies. Thus, this analysis offers different approach to finding parameter values through a directed, but random, search of the parameter space. For this purpose, we developed a Mathematica code of this Bayesian approach together with SA and used it for recovering sinusoids from noisy data. Simulations results support its effectiveness.

[学科分类] 计算数学

[关键词] Bayesian Statistical Inference Simulated Annealing;Parameter Estimations;Power Spectral Density;Cramér-Rao lower bound