A practical approach to Dynamic Bayesian Networks

A known impediment to the practical application of dynamic Bayesian networks (DBNs) by subject matter experts is the "knowledge acquisition problem". In this paper we present a series of novel concepts as an approach to make DBNs accessible. We provide a number of extensions and formalisms to DBNs to provide a framework for the development of a usable causal modelling language. We also address the issues of developing and populating models that can be computed using DBN techniques. Benefits of applying the preceding notions are that DBN creation becomes tenable and easily interpreted by a non-model builder.