A Hybrid Approach for the Prevention of Railway Accidents Based on Artificial Intelligence

  • Habib Hadj-MabroukEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 866)


The modes of reasoning which are used in the context of safety analysis 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. Our research has involved three specific aspects of artificial intelligence: knowledge acquisition, machine learning and knowledge based systems (KBS). Development of the knowledge base in a KBS requires the use of knowledge acquisition techniques in order to collect, structure and formalizes knowledge. It has not been possible with knowledge acquisition to extract effectively some types of expert knowledge. Therefore, the use of knowledge acquisition in combination with machine learning appears to be a very promising solution. This paper presents the result of these two research activities which are involved in the methodology of safety analysis of guided rail transport systems.


Rail transport Safety Accident scenarios Knowledge acquisition Machine learning Expert system 


  1. 1.
    Gaines, B.R.: Knowledge acquisition: past, present, and future. Int. J. Hum.–Comput. Stud. (2012).
  2. 2.
    Aussenac, G., Gandon, F.: From the knowledge acquisition bottleneck to the knowledge acquisition overflow: a brief French history of knowledge acquisition. Int. J. Hum.-Comput. Stud. 71(2), 157–165 (2013)Google Scholar
  3. 3.
    Kodratoff, Y.: Leçons d’apprentissage symbolique automatique. Cepadues éd., Toulouse, France (1986)Google Scholar
  4. 4.
    Ganascia, J-G.: Agape et Charade: deux mécanismes d’apprentissage symbolique appliqués à la construction de bases de connaissances. Thèse d’État, Université Paris- sud, France (1987)Google Scholar
  5. 5.
    Ganascia, J.-G.: Logical induction, machine learning and human creativity. In: Switching Codes. University of Chicago Press (2011). ISBN 978022603830Google Scholar
  6. 6.
    Michalski, R-S., Wojtusiak, J.: Reasoning with missing, not-applicable and irrelevant meta-values in concept learning and pattern discovery. J. Intell. Inf. Syst. 39(1), 141–166 (2012). SpringerGoogle Scholar
  7. 7.
    Hadj-Mabrouk, H.: Contribution of learning Charade system of rules for the prevention of rail accidents. J. Intell. Decis. Technol. 11(4), 477–485 (2017). Scholar
  8. 8.
    Hadj-Mabrouk, H.: CLASCA: learning system for classification and capitalization of accident Scenarios of Railway. Int. J. Eng. Res. Appl. 6(8), 91–98 (2016). ISSN: 2248-9622Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.French Institute of Science and Technology for Transport, Development and NetworksMarne la ValléeFrance

Personalised recommendations