Bayesian Parameter Estimation of Sinusoids with Simulated Annealing


ÜSTÜNDAĞ D., Cevri M.

8th WSEAS International Conference on Signal Processing, Conputational Geometry and Artificial Vision, Rhodes, Greece, 20 - 22 August 2008, pp.106-112 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • City: Rhodes
  • Country: Greece
  • Page Numbers: pp.106-112
  • Istanbul University Affiliated: No

Abstract

In this paper, we consider Bayesian analysis proposed by Bretthorst for estimating parameters from noisy data and combined it with a simulated annealing algorithm to obtain a global maximum of the posterior probability density of 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 and used it for estimating parameters of sinusoids corrupted by random noise. The simulations results support the effectiveness of the method.