Neuro-DEVS, an hybrid environment to describe complex systems

Several methodologies has been developed to specify complex systems formally [1] [2] [3] [4] [5]. Among those formalisms stands the DEVS formalism and Artificial Neu-ral Networks. Although no direct comparisons are possible between the two techniques, both can provide good results when they are applied to the same problem. DEVS formalism is a set-theoretic formalism. It allows the definition of discrete events models in a hierarchical and modular manner with well defined interfaces [6], thus DEVS paradigm is well adapted to create an object oriented modelling and simulation (OOMS) environment such as DevsJava [7], DevsSim++[3] [8]. Also based on this paradigm we developed an OOMS (object oriented modelling and simulation approach).[9] The originality of our approach stands in two points : • the use of three types of hierarchies (abstraction [10], description [11] and time [12]); • the use of Object Oriented Programming concepts in order to implement and simulate the studied system. This approach has been successfully implemented in the OOMS java set of tools developed in the University of Cor-sica, JDEVS [13]. The integration of those concepts allow the automatic generation of a simulator from the model as defined in the DEVS formalism [11].