Open AccessIdentification of the local area network using machine learning
Author(s) -
Ilya Vasilievich Voronin,
A. I. Gazin,
Vladimir Sergeyevich Ziyautdinov,
T. A. Zolotareva,
Dmitry Mikhailovich Skudnev,
O. V. Selishchev
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1399/3/033046
Subject(s) - computer science , identification (biology) , cluster analysis , machine learning , artificial neural network , artificial intelligence , process (computing) , local area network , data mining , set (abstract data type) , network packet , computer network , botany , biology , programming language , operating system
This article discusses the use of a network traffic analyzer based on a neural network to detect and resolve problems that occur in local area networks. Several packet capture approaches have been investigated that affect the speed and accuracy of network traffic analysis. Various methods for classifying network traffic are given, special attention is paid to the machine learning method. The main advantages and disadvantages of various teaching methods have been identified. The process and basic steps of clustering the training set are described. As a result of the study, a method was identified for creating a high-quality system that allows identifying the state of a local area network.