Evaluation of Hybrid Bayesian Networks using Analytical Density Representations
Abstract
In this article, a new mechanism is described for modeling and evaluatingHybrid Dynamic Bayesian networks. The approach uses Gaussian mixtures and Dirac mixtures asmessages to calculate marginal densities. As these densities are approximated by means of Gaussian mixtures, any desired precision is possible. The presented approach removes the restrictions of sample based evaluation ofBayesian networks since it uses an analytical approximation scheme forprobability densities which systematically minimizes the distance between theexact and the approximate density.
