Home // ICDS 2013, The Seventh International Conference on Digital Society // View article

Predicting the Quality Level of a VoIP Communication through Intelligent Learning Techniques

Authors:
Demóstenes Zegarra Rodríguez
Renata Lopes Rosa
Graça Bressan

Keywords: QoS; VoIP; Machine Learning; Decision Tree; EModel; PESQ.

Abstract:
This paper presents a method for determining the quality of a VoIP communication using intelligent learning techniques. The proposed solution uses historical values of network parameters and communication quality in order to train the intelligent learning algorithms. After that, these algorithms are able to find the quality of the VoIP communication based on network parameters of an specific period of time. The intelligent learning algorithms take as input a baseline file that contains some values of network parameters and voice coding, associating an index quality for each scenario according to the ITU-T Recommendation G.107. The tests were performed in an emulated network environment, totally isolated and controlled with real traffic of voice and realistic IP network parameters. The quality ratings obtained for the learning algorithms in all scenarios were corroborated with the results of the algorithm of ITU-T Recommendation P.862. The results show the reliability of the three learning algorithms used on the tests: Decision Trees (J.48), Neural Networks (Multilayer Perceptron) and Bayesian Networks (Naives). The highest value of reliability in determining the quality of the VoIP communications was 0.98 with the use of Decision Trees Algorithm. These results demonstrate the validity of the method proposed.

Pages: 42 to 47

Copyright: Copyright (c) IARIA, 2013

Publication date: February 24, 2013

Published in: conference

ISSN: 2308-3956

ISBN: 978-1-61208-249-3

Location: Nice, France

Dates: from February 24, 2013 to March 1, 2013