Comparison of Dynamic Bayesian Network Tools

Abstract

In this paper we review and compare several state-of-the-art Dynamic Bayesian Network (DBN) software tools. Bayesian networks are probabilistic graphical representations used to build models from data and/or expert opinion. DBNs are extensions of Bayesian networks with temporal support to model systems with dynamic behavior. DBNs are utilized in a wide range of applications including robotics, data mining, speech recognition, digital forensics, protein sequencing, and bioinformatics. Existing DBN software tools differ in terms of features support, ease of use, documentation, users community, etc. We establish various metrics for selecting the proper software tools for creating and simulating DBNs, such as cost, licensing, GUI, built-in support for inference algorithms, structural learning, data types, etc. We provide a comprehensive evaluation and comparison of these tools for building DBNs based on the above set of user centered criteria.