Discrete Event System in Applied Sciences and AI- Recurrent Neural Networks

Abstract

A system with an occurrence is a DES (discrete event system) with discrete conditions, which means that its condition evolution is solely dependent on discrete, contradictory events [1]. A methodology for simulating various sys- tems that may be split into several logically independent processes that move through time on their own is defined as discrete event simulation (DES). Each event has a logical timing and occurs on a specific process (a timestamp). This event’s output can be sent to one or more other processes. A new set of oc- currences that should be handled at a future meaningful time may be created because of the outcome’s content. Typically, f(x) in a CVDS represents the an- swer to the setup of equations p(y)=a(p(y), b(y), y). When an event happens, a(y) is a piece-wise uniform function because the condition of a discrete event system changes from one discrete value to another. Condition that monitoring problem for a certain kind of neural network is solved using Markovian jump- ing parameters, which is the subject of this paper. The modes of the neural net- work models can switch between each other within a Markov chain and have a finite number of modes. In a discrete-time M.C, the events occur at specific time periods, denoted as {0, 1, 2, 3, . . . , k}. This allows us to construct a stochas- tic sequence {X1, X2, X3, . . . }, where the defining characteristic is its Markov property. P [Xp + 1 =Xp + 1|Xp = Xp, Xp − 1 = Xp − 1, ..., X0 = x0] =P [X − k + 1 = Xp + 1|Xp = Xp ] (1.1)