Title: Accuracy evaluation of supervised machine learning classification models for wireless network traffic

Authors: Elans Grabs; Ernests Petersons; Dmitry Efrosinin; Aleksandrs Ipatovs; Janis Kluga; Valentin Sturm

Addresses: Telecommunications Institute, Riga Technical University, Azenes St., LV-1048, Riga, Latvia ' Telecommunications Institute, Riga Technical University, Azenes St., LV-1048, Riga, Latvia ' Institut für Stochastik, Johannes Kepler Universität, Altenberger Straße 69, 4040, Linz, Austria ' Telecommunications Institute, Riga Technical University, Azenes St., LV-1048, Riga, Latvia ' Telecommunications Institute, Riga Technical University, Azenes St., LV-1048, Riga, Latvia ' Institut für Stochastik, Johannes Kepler Universität, Altenberger Straße 69, 4040, Linz, Austria

Abstract: The article contains results of training and testing machine learning models with captured network traffic data. The main goal is to perform classification of video traffic in computer networks. Multiple performance metrics have been evaluated for commonly used classic supervised machine learning algorithms, as well as more advanced convolutional neural network model (for comparison). The article describes in detail the experimental setup, traffic pre-processing procedure, features extraction with different traffic window length and model parameters for training/testing. The article provides some experimental results in the form of tables and 3D surface plots. The conclusion of the article summarises the main findings and outlines the future study directions.

Keywords: accuracy; classification models; features extraction; network traffic; performance metrics; statistical parameters; supervised machine learning; traffic intensity; window length; wireless networks; convolutional neural network; CNN.

DOI: 10.1504/IJCNDS.2022.126222

International Journal of Communication Networks and Distributed Systems, 2022 Vol.28 No.6, pp.655 - 678

Received: 09 Jul 2021
Accepted: 19 Oct 2021
Published online: 17 Oct 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article