Parameter Estimation of Hidden Diffusion Processes: Particle Filter vs. Modified Baum-Welch Algorithm

摘要

We propose a new method for the estimation of parameters of hidden diffusionprocesses. Based on parametrization of the transition matrix, the Baum-Welchalgorithm is improved. The algorithm is compared to the particle filter inapplication to the noisy periodic systems. It is shown that the modifiedBaum-Welch algorithm is capable of estimating the system parameters with betteraccuracy than particle filters.