Bridge condition modelling and prediction using dynamic Bayesian belief networks

Bridge Condition Modelling and Prediction Using Dynamic Bayesian Belief Networks

Project Portfolio Risk Response Selection Using Bayesian Belief Networks

Risk identification, impact assessment, and response planning constitute three building blocks of project risk management. Correspondingly, three types of interactions could be envisioned between risks, between impacts of several risks on a portfolio component, and between several responses. While the interdependency of risks is a well-recognized issue, the other two types of interactions remai...

Modelling ecosystem services using Bayesian belief networks: Burggravenstroom case study

While being studied by scientists for decades, the term ecosystem services was only recently introduced to the general public. This introduction intended broad-scale recognition of ecosystems and their value for human wellbeing. Both quantitative and qualitative research on ecosystem services became emerging topics in scientific research. Ecosystem service prediction models were developed varyi...

The Information System for Bridge Networks Condition Monitoring and Prediction

This paper introduces an information system for estimating lifetime characteristics of elements of bridges and predicting the future conditions of networks of bridges. The Information System for Bridge Networks Condition Monitoring and Prediction was developed for the Roads and Traffic Authority of the state of New South Wales, Australia. The conceptual departure from the standard bridge manage...

Improved Reliability modelling using Bayesian Networks and dynamic discretisation

This paper shows how recent revolutionary Bayesian Network (BN) algorithms can be used to model very complex reliability problems in a simple unified way. The algorithms work for socalled hybrid BNs, which are BNs that can contain a mixture of both discrete and continuous variables. Such hybrid BNs enable us to model failure times and reliability together. The approach allows a compact represen...