Contribution of learning CHARADE system of rules for the prevention of rail accidents

Issue title: CogInfoCom-Supported Approaches, Models and Solutions in Surface Transportation

Guest editors: Peter Baranyi, Attila Borsos, Salvatore Cafiso and Marian Tracz

Article type: Research Article

Authors: Hadj Mabrouk, Habib

Affiliations: IFSTTAR: French Institute of Science and Technology for Transport, Development and Networks, France | E-mail: [email protected]

Abstract: The modes of reasoning employed by the domain experts to analyze and assess the safety of railway transport and the very nature of knowledge about safety mean that a conventional computing solution is unsuitable and the utilization of artificial intelligence techniques would seem to be more appropriate. In artificial intelligence, we perceive two major independent research activities: the acquisition of knowledge which to better understand the transfer of expertise and the machine learning proposing the implementation of inductive, deductive, abductive techniques or by analogy to equip the system of learning abilities. This paper describes our contribution to improving the usual safety analysis methods used in the certification of railway transport systems in France. The methodology is based on the complementary and simultaneous use of knowledge acquisition and machine learning. The purpose is contributed to the generation of new accident scenarios that could help experts to conclude on the safe character of a new rail transport system.

Keywords: Knowledge acquisition, machine learning, expert system, railway, safety, accident scenarios

DOI: 10.3233/IDT-170304

Journal: Intelligent Decision Technologies, vol. 11, no. 4, pp. 477-485, 2017