Performance Evaluation of Local Area Network based on Support Vector Machine

DOI

10.2991/icmmct-16.2016.384How to use a DOI?

Keywords

IP performance evaluation; support vector machine; k-fold cross validation; local area network

Abstract

This work presents an IP performance evaluation method, based on the Support Vector Machine (SVM). In this work, eight network parameters are collected: CPU utilization of switchboard, utilization of memory, network link-off, delay, delay jitter, bandwidth, bit rate of transmission and bit rate of reception. The performance of the local area network is classified into three grades: excellent, good and failed. In this work, the collected network parameters are processed using SVM classifier. The average classification accuracy is achieved using k-fold cross validation method. The experiment results indicate that the classification accuracy of the proposed method is over 90%. This proposed evaluation system could be applied to a real-time network performance evaluation application effectively.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Qi Liu
AU  - Yin Liu
AU  - Yiyong Lin
AU  - Ling He
AU  - Yunzhi Huang
PY  - 2016/03
DA  - 2016/03
TI  - Performance Evaluation of Local Area Network based on Support Vector Machine
BT  - Proceedings of the 2016 4th International Conference on Machinery, Materials and Computing Technology
PB  - Atlantis Press
SP  - 1927
EP  - 1930
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmmct-16.2016.384
DO  - 10.2991/icmmct-16.2016.384
ID  - Liu2016/03
ER  -