Compatible and incompatible abstractions in Bayesian networks

The graphical structure of a Bayesian network (BN) makes it a technology well-suited for developing decision support models from a combination of domain knowledge and data. The domain knowledge of experts is used to determine the graphical structure of the BN, corresponding to the relationships and between variables, and data is used for learning the strength of these relationships. However, the available data seldom match the variables in the structure that is elicited from experts, whose models may be quite detailed; consequently, the structure needs to be abstracted to match the data. Up to now, this abstraction has been informal, loosening the link between the final model and the experts' knowledge. In this paper, we propose a method for abstracting the BN structure by using four 'abstraction' operations: node removal, node merging, state-space collapsing and edge removal. Some of these steps introduce approximations, which can be identified from changes in the set of conditional independence (CI) assertions of a network.


Tool support for transformation from an OWL ontology to an HLA Object Model
ÖZDİKİŞ, Özer; DURAK, Umut; Oğuztüzün, Mehmet Halit S. (2010-03-15)
Designing simulation architectures based on domain models is a promising approach. Tools to support transformation of formalized domain models to design models are essential. Ontology languages offer a way of formally specifying the domain knowledge. We adopt a user-guided approach to model transformation, where the source is an OWL ontology and the target is an HLA Object Model, in particular, a federation object model (FOM). This paper presents a flexible transformation tool that enables the user to defin...
Bayesian Networks in Project Management
Yet, Barbaros (2017-01-01)
Bayesian networks (BNs) offer unique benefits for combining data and expert knowledge to model complex joint probability distributions. Recent advances in inference algorithms enabled efficient computation of BNs with both discrete and continuous variables that are also called hybrid BNs. Consequently, BNs have been widely used as risk assessment and decision support tools in various domains including project management. This article illustrates the use of BNs in different aspects of project management and ...
Comparison of hypermedia learning and traditional instruction on knowledge acquisition and retention
Yıldırım, Zahide; Aksu, M (2001-03-01)
A comparison was made of hypermedia learning environments and traditional instruction in terms of contribution to declarative, procedural, and conditional knowledge acquisition and retention in a specific subject area through a pretest-posttest control-group design. Thirty-nine 9th-grade biology students were assigned to experimental (hypermedia learning environment) and control (traditional instruction) groups through a matched-pair technique. Both groups were given pre-, post-, and retention tests. Postte...
Semi-Bayesian Inference of Time Series Chain Graphical Models in Biological Networks
Farnoudkia, Hajar; Purutçuoğlu Gazi, Vilda (null; 2018-09-20)
The construction of biological networks via time-course datasets can be performed both deterministic models such as ordinary differential equations and stochastic models such as diffusion approximation. Between these two branches, the former has wider application since more data can be available. In this study, we particularly deal with the probabilistic approaches for the steady-state or deterministic description of the biological systems when the systems are observed though time. Hence, we consider time s...
Near-instant link failure recovery in 5G wireless fog-based-fronthaul networks
Sulieman, Nabeel I.; Balevi, Eren; Gitlin, Richard D. (2018-05-23)
© 2018 IEEE.Rapid recovery from link failures was previously demonstrated via the synergistic combination of Diversity and Network Coding (DC-NC) for a wide variety of network architectures. In this paper, the DC-NC methodology is further enhanced to achieve near-instant recovery from multiple, simultaneous wireless link failures by modifying Triangular Network Coding (TNC) to create enhanced DC-NC (eDC-NC) that is applied to 5G wireless Fog computing based Radio Access Networks (F-RANs). In addition, an ex...
Citation Formats
B. Yet, “Compatible and incompatible abstractions in Bayesian networks,” KNOWLEDGE-BASED SYSTEMS, pp. 84–97, 2014, Accessed: 00, 2020. [Online]. Available: