An open toolbox for the reduction, inference computation and sensitivity analysis of Credal Networks. (January 2018)

• Record Type: Journal Article
• Authors: Tolo, Silvia; Patelli, Edoardo; Beer, Michael
• Is Part Of: Advances in engineering software. Volume 115(2018)
• Page Start: 126
• Page End: 148
• Publication Date: 2018-01
• Subjects: Credal Networks -- Bayesian Networks -- Decision making -- System reliability; Computer-aided engineering -- Periodicals; Engineering -- Computer programs -- Periodicals; Engineering -- Software -- Periodicals; Periodicals; 620.0028553
• DOI: 10.1016/j.advengsoft.2017.09.003
• Languages: English
• ISSNs: 0965-9978

Abstract

Highlights: A computational toolbox for the implementation and analysis of Credal Networks is proposed. The toolbox incorporates novel methods for the reduction of Credal Networks to equivalent Bayesian Networks including interval probabilities. Novel methods for the computation of exact and approximate inference on the reduced models are integrated in the toolbox. The computational toolbox includes novel methods for the computation of sensitivity analysis and parameter tuning on the reduced models. Abstract: Bayesian Networks are a flexible and intuitive tool associated with a robust mathematical background. They have attracted increasing interest in a large variety of applications in different fields. In spite of this, inference in traditional Bayesian Networks is generally limited to only discrete variables or to probabilistic distributions (adopting approximate inference algorithms) that cannot fully capture the epistemic imprecision of the data available. In order to overcome these limitations, Credal Networks have been proposed to integrate Bayesian Networks with imprecise probabilities which, adopting non-probabilistic or hybrid models, allow to fully represent the information available and its uncertainty. Here, a novel computational tool, implemented in the general purpose software OpenCossan, is proposed. The tool provides the reduction of Credal Networks through the use of structural reliability methods, in order to limit the cost associated with the inference computation without impoverishing the quality of the information initially introduced. Novel algorithms for the inference computation of networks involving probability bounds are provided. In addition, a novel sensitivity approach is proposed and implemented into the Toolbox in order to identify the maximum tolerable uncertainty associated with the inputs.