Factoring Dynamic Bayesian Networks based on structural observability
- 1 December 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 244-250
Abstract
Dynamic Bayesian networks (DBNs) provide a systematic framework for robust online monitoring of dynamic systems. This paper presents an approach for increasing the efficiency of online estimation by partitioning a system DBN into a set of smaller factors, such that estimation algorithms can be applied to each factor independently. Our factoring scheme is based on the analysis of structural observability of the dynamic system. We establish the theoretical background for structural observability and derive an algorithm for generating the factors using structural observability analysis. We present experimental results to demonstrate the effectiveness of our factoring approach for accurate estimation of system behavior.Keywords
This publication has 5 references indexed in Scilit:
- A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian trackingIEEE Transactions on Signal Processing, 2002
- Sampling in Factored Dynamic Systems2001
- Diagnosis of continuous valued systems in transient operating regionsIEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 1999
- Bond-graph approach for structural analysis of MIMO linear systemsJournal of the Franklin Institute, 1991
- Structural controllability/observability of linear systems represented by bond graphsJournal of the Franklin Institute, 1989