Parts | Days | Selection | Search | Downloads | Help
DY: Dynamik und Statistische Physik
DY 21: Brownian motion
DY 21.4: Talk
Tuesday, March 25, 2003, 10:45–11:00, G\"OR/229
From hidden Markov Models to hidden diffusion processes — •Abdelhadi Benabdallah and Günter Radons — TU Chemnitz, Institut für Physik , D-09107 Chemnitz, Germany
The Expectation-Maximization (EM) algorithm, is an iterative procedure for maximum likelihood parameter estimation from data sets with missing or hidden variables. It has been applied successfully to the hidden Markov models. We present a analytical estimation of the diffusion and the drift term associated to the Hidden diffusion problem in a one-dimensional periodic potential. Numerical calculations confirm our estimations.