Establishing Verification and Validation Objectives for Safety-Critical Bayesian Networks
Authors:
- Mark DouthwaiteMDMark Douthwaite
- Tim KellyTKTim Kelly
- 1 October 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 302-309
Abstract
The assurance of autonomous systems and the technologies that drive them is a major research challenge in the safety-critical systems engineering domain. The nature of many of these Machine Learning (ML) and Artificial Intelligence (AI) approaches raises a number of additional, technology-specific assurance concerns. One such approach is the Bayesian Network (BN) probabilistic modelling framework. Bayesian Networks and the family of modelling techniques they belong to form the basis of many AI applications. However, little research has been conducted into the assurance of BN-based systems for use in safety-critical applications. This paper explores some of the key distinctions between BN-based software-intensive systems and conventional software systems. It introduces a modelling framework that explicitly captures BN-based systemspecific considerations and facilitates both the communication of assurance concerns between safety practitioners and system stakeholders, and the subsequent safety analysis of the system itself. It demonstrates how this approach can be used to develop specific verification and validation objectives for a BN-based system in a medical application.Keywords
This publication has 28 references indexed in Scilit:
- Metrics for evaluating performance and uncertainty of Bayesian network modelsEcological Modelling, 2012
- Developing artificial neural networks for safety critical systemsNeural Computing and Applications, 2006
- Software architecture: introducing IEEE Standard 1471Computer, 2001
- Building large-scale Bayesian networksThe Knowledge Engineering Review, 2000
- Learning Bayesian networks: The combination of knowledge and statistical dataMachine Learning, 1995
- Bayesian networksCommunications of the ACM, 1995
- Applicability of modified condition/decision coverage to software testingSoftware Engineering Journal, 1994
- Evolving Bayesian classifiers for credit control—a comparison with other machine-learning methodsIMA Journal of Management Mathematics, 1993
- The ALARM Monitoring System – Intelligent Decision Making under UncertaintyAnesthesiology, 1989
- Why Expert Systems FailJournal of the Operational Research Society, 1985