Universidad Complutense de Madrid
E-Prints Complutense

Sensitivity to evidence in Gaussian Bayesian networks using mutual information

Impacto

Downloads

Downloads per month over past year

Gómez Villegas, Miguel A. and Main Yaque, Paloma and Viviani, Paola (2014) Sensitivity to evidence in Gaussian Bayesian networks using mutual information. Information sciences, 275 . pp. 115-126. ISSN 0020-0255

[img] PDF
Restringido a Repository staff only

592kB

Official URL: http://www.sciencedirect.com/science/article/pii/S0020025514001315


URLURL Type
http://www.sciencedirect.com/Publisher


Abstract

We introduce a methodology for sensitivity analysis of evidence variables in Gaussian Bayesian networks. Knowledge of the posterior probability distribution of the target variable in a Bayesian network, given a set of evidence, is desirable. However, this evidence is not always determined; in fact, additional information might be requested to improve the solution in terms of reducing uncertainty. In this study we develop a procedure, based on Shannon entropy and information theory measures, that allows us to prioritize information according to its utility in yielding a better result. Some examples illustrate the concepts and methods introduced.


Item Type:Article
Uncontrolled Keywords:Entropy; Evidence propagation; Gaussian Bayesian network; Mutual information; Sensitivity analysis
Subjects:Sciences > Mathematics > Mathematical statistics
ID Code:26447
Deposited On:29 Jul 2014 08:52
Last Modified:04 Mar 2016 14:49

Origin of downloads

Repository Staff Only: item control page