An innovative approach for real-time network traffic classification

Página do item simplificado
dc.creatorKlenilmar Lopes Dias
dc.creatorMateus Almeida Pongelupe
dc.creatorWalmir Matos Caminhas
dc.creatorLuciano de Errico
dc.date.accessioned2025-05-22T14:04:18Z
dc.date.accessioned2025-09-09T01:11:21Z
dc.date.available2025-05-22T14:04:18Z
dc.date.issued2019
dc.identifier.doihttps://doi.org/10.1016/j.comnet.2019.04.004
dc.identifier.issn1389-1286
dc.identifier.urihttps://hdl.handle.net/1843/82453
dc.languageeng
dc.publisherUniversidade Federal de Minas Gerais
dc.relation.ispartofComputer networks
dc.rightsAcesso Restrito
dc.subjectTelecomunicações
dc.subject.otherTraffic classification
dc.subject.otherNaive Bayes
dc.subject.otherMachine learning
dc.subject.otherVideo streaming
dc.titleAn innovative approach for real-time network traffic classification
dc.typeArtigo de periódico
local.citation.epage157
local.citation.spage143
local.citation.volume158
local.description.resumoThe growing demand for high-speed transmission rates in recent years attracted research in new mechanisms for network traffic characterization and classification. Their inadequate treatment degrades the performance of important operational schemes, such as Network Survivability, Traffic Engineering, Quality of Service (QoS), and Dynamic Access Control, among others. The most common methods for traffic classification are Deep Packet Inspection (DPI) and port based classification. However, those methods are becoming obsolete, as increasingly more traffic is being encrypted and applications are using dynamic ports or ports originally assigned to other popular applications. This paper presents a classification module for video streaming traffic, based on machine learning, as a solution for network schemes that require adequate real-time traffic treatment. The module adopts a new approach for the relaxation of the hypothesis of independence between the attributes of the Naive Bayes algorithm. The results show that the proposed module is a promising alternative to be applied in real-time scenarios.
local.publisher.countryBrasil
local.publisher.departmentENG - DEPARTAMENTO DE ENGENHARIA ELETRÔNICA
local.publisher.initialsUFMG
local.url.externahttps://www.sciencedirect.com/science/article/pii/S1389128618305541

Arquivos

Licença do pacote

Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
License.txt
Tamanho:
1.99 KB
Formato:
Plain Text
Descrição:
Baixar

Coleções

Artigo de Periódico

Logo UFMG