Fuzzy-neuro risk assessment of distributed real-time systems through formal and object-oriented systems modelling

The purpose of this paper is to advocate and encourage the application of fuzzy-neuro algorithms in the risk assessment of Distributed Real-Time (DRT) systems, where object-oriented and formal techniques by means of UML-SDL models are used as knowledge (data) providers to the fuzzy-neuro analyser. The paper includes an introductory description of DRT systems and the presentation of the UML and SDL techniques as software modelling languages, along with their advantages and limitations. Next, a combination of UML and SDL for requirement and detailed design modelling is suggested to produce the proper knowledge bases to a risk analyser. An example of a fuzzy-neuro system is then utilised to illustrate how it can be trained to assess various kinds of risks by using the combined UML-SDL models as input and through deductive reasoning.

• Type: Conference
• Year: 2003
• Where: EUSFLAT
• Authors: Atoosa P.-J. Thunem
• Keywords: DRT Systems, EUSFLAT 2003, EUSFLAT 2007, Software Modelling Languages, UML-SDL Models