Browsing by Author "Lanevych, Vladyslav"

Now showing 1 - 1 of 1

Intelligent Computer Network for Railway Transport Using Neuro-Fuzzy Means for Determining the Optimal Route
(Sworld & D.A. Tsenov Academy of Economics, Svishtov, Bulgaria, 2025) Pakhomova, Victoria M.; Lanevych, Vladyslav
ENG: At the present stage, the information and telecommunications system of railway transport uses local networks of the following technologies: Ethernet; Fast Ethernet; Gigabit Ethernet, as well as the OSPF routing protocol, when used in real time, a problem arises due to constant changes in the volume of transmitted data, and for its solution, it is possible to consider the use of a neurofuzzy tool, which confirms the relevance of the topic. As a mathematical apparatus for solving the problem of determining the optimal route, a neural fuzzy network of the configuration «12-24-144-144-1» was taken, where 12 is the number of input neurons (delays on routers); 24 is the number of hidden neurons taking into account the terms; 144 is the number of hidden neurons according to the number of rules; 1 is the number of resulting neurons (total delay on routers along the route). Using the Fuzzy Logic Toolbox package of the MatLAB environment, a Sugeno ANFIS algorithm (with a Gaussian membership function for hidden neurons) was created, on which the mean square error and the number of learning epochs were studied using various learning optimization methods (Backpropagation, Hybrid) on samples of different lengths. It was determined that the accuracy of the created neurofuzzy tool is 80% for the considered fragment of the railway transport information and telecommunications system; a general scheme of an intelligent computer network based on ANFIS was proposed.