Learning Bayesian networks is known to be highly sensitive to the chosen equivalent sample size (ESS) in the Bayesian Dirichlet equivalence uniform (BDeu). This sensitivity often engenders unstable or undesired results because the prior of BDeu does not represent ignorance of prior knowledge, but rather a user’s prior belief in the uniformity of the conditional distribution. This paper presents...

While inspections are a valuable tool for software quality assurance, inspection models are labour intensive, require knowledge of all errors in a software product, make questionable assumptions, and do not capture the experience of inspectors. In this paper we describe a novel inspection model based on Bayesian belief networks that overcomes many of these problems. We describe the problems whi...

Peter Sember and Ingrid Zukerman Department of Computer Science Monash University Oayton, VICfORIA 3168, AUSTRALIA netmail address: [email protected]@seismo.css.gov [email protected]@seismo.css.gov Bayesian Belief Networks have been largely overlooked by Expert Systems practitioners on the grounds that they do not correspond to the human inference mechanism. In this paper, we intro...

We consider the problem of computing mutual information between many pairs of variables in a Bayesian network. This task is relevant to a new class of Generalized Belief Propagation (GBP) algorithms that characterizes Iterative Belief Propagation (IBP) as a polytree approximation found by deleting edges in a Bayesian network. By computing, in the simplified network, the mutual information betwe...

background: high-risk unsafe behaviors (hrubs) have been known as the main cause of occupational accidents. considering the financial and societal costs of accidents and the limitations of available resources, there is an urgent need for managing unsafe behaviors at workplaces. the aim of the present study was to find strategies for decreasing the rate of hrubs using an integrated approach of s...

1 I n t r o d u c t i o n The Dempster-Shafer theory is quite popular in knowledge based applications. However, it's exponential computational complexity is a stumbling block. Several researchers worked on the problem of reducing the computational burden of the theory. The work in this direction was initiated by Barnett [1]. The approach of reducing the number of focal elements by certain appro...

Precision achieved by stochastic sampling al­ gorithms for Bayesian networks typically de­ teriorates in face of extremely unlikely ev­ idence. To address this problem, we pro­ pose the Evidence Pre-propagation Impor­ tance Sampling algorithm (EPIS-BN), an importance sampling algorithm that com­ putes an approximate importance function using two techniques: loopy belief propaga­ tion [19, 25] a...

Independence-based (IB) assignments to Bayesian belief networks were originally pro­ posed as abductive explanations. IB as­ signments assign fewer variables in abduc­ tive explanations than do schemes assign­ ing values to all evidentially supported vari­ ables. We use IB assignments to approxi­ mate marginal probabilities in Bayesian be­ lief networks. Recent work in belief up­ dating for Bay...

Graphical models have become common for representing probabilistic models in statistics and artificial intelligence. A Bayesian network is a graphical model which encodes a probability model as a directed graph in which nodes correspond to random variables, together with a set of conditional distributions of nodes given their parents. In most current applications of Bayesian networks, a fixed n...

The problem of profiling and filtering the Web content is important particularly for mobile applications where wireless network traffic and mobile terminal size are limited comparing to the Internet access from the PC. Bayesian networks are known to be good tool for learning user preferences in electronic commerce. However more sophisticated cases, when user preferences are changing according t...