name
Malykhina Maria Petrovna
Scholastic degree
•
Academic rank
professor
Honorary rank
—
Organization, job position
• Kuban State Technological University
Research interests
Web site url
—
—
Current rating (overall rating of articles)
0
TOP5 co-authors
Articles count: 6
Сформировать список работ, опубликованных в Научном журнале КубГАУ
-
Description
This article is devoted to the problem of network attacks recognition, which is essential for providing network security. A research of neural network efficiency has been held. Such metaeuristic algorithms as genetic algorithm, gray wolf algorithm and firefly algorithm have been applied for the neural network learning. The algorithms’ fundamentals have been described. Multilayer perseptrone with sigmoid activation function has been selected for the task of network attack presence check. Various configurations of the neural network have been tested in order to find the optimal number of layers and neurons per layer, which ensure the least error. Learning has been performed by minimization of the average squared error between the network’s output and its target value with the help of the listed algorithms. Genetic algorithm requires accurate parameter picking in case of any network’s architecture alteration. Moreover, it is not as fast as firefly and gray wolf algorithms. Gray wolf algorithm appears to be the most effective one. However, it loses its efficiency if the number of layers is increased. Firefly algorithm proves to be the most universal one. Although it is less effective than gray wolf algorithm, it provides the most exact output even if the network’s structure is changed
-
Description
The article discusses the ways of working of an intelligent system based on hybridization of several technologies of intelligent computations. A model of the hybrid system is represented. The effectiveness of the proposed approach has been proved
-
INTELLIGENT SYSTEM FOR DATABASE DESIGN OF EFFECTIVE STRUCTURES
DescriptionThe article deals with the automated system that will allow users to make the structure of the existing database efficiently by sequential normalization with the use of explanatory system
-
Description
Selection of borders on images through color difference is reviewed in this article. The existing approaches are considered, the problems are set. We also show the reasons of shifting to other approaches
-
ANALYSIS OF PATTERN RECOGNITION WITH NEURAL NETWORK METHOD
DescriptionThe article deals with a set of basic patterns of technical analysis and reviews their recognition techniques using neural network methods. The existing approaches to the problem have been set. The reasons of relevance of the described technique have been shown
-
Description
In the article we have considered the analysis of the dependence of RGB components for segmentation of objects on images