Home > Research > Publications & Outputs > Internet traffic classification using energy ti...

Links

Text available via DOI:

View graph of relations

Internet traffic classification using energy time-frequency distributions

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Internet traffic classification using energy time-frequency distributions. / Marnerides, Angelos; Pezaros, Dimitrios; Kim, Hyun-chul et al.
2013 IEEE International Conference on Communications (ICC). IEEE, 2013. p. 2513-2518.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Marnerides, A, Pezaros, D, Kim, H & Hutchison, D 2013, Internet traffic classification using energy time-frequency distributions. in 2013 IEEE International Conference on Communications (ICC). IEEE, pp. 2513-2518, IEEE ICC, Budapest, Bahamas, 9/06/13. https://doi.org/10.1109/ICC.2013.6654911

APA

Marnerides, A., Pezaros, D., Kim, H., & Hutchison, D. (2013). Internet traffic classification using energy time-frequency distributions. In 2013 IEEE International Conference on Communications (ICC) (pp. 2513-2518). IEEE. https://doi.org/10.1109/ICC.2013.6654911

Vancouver

Marnerides A, Pezaros D, Kim H, Hutchison D. Internet traffic classification using energy time-frequency distributions. In 2013 IEEE International Conference on Communications (ICC). IEEE. 2013. p. 2513-2518 doi: 10.1109/ICC.2013.6654911

Author

Marnerides, Angelos ; Pezaros, Dimitrios ; Kim, Hyun-chul et al. / Internet traffic classification using energy time-frequency distributions. 2013 IEEE International Conference on Communications (ICC). IEEE, 2013. pp. 2513-2518

Bibtex

@inproceedings{736864a0dabe4c219d85156460382e2e,
title = "Internet traffic classification using energy time-frequency distributions",
abstract = "We present a fundamentally new approach to classify application flows based on the mapping of aggregate transport-layer volume information onto the Time-Frequency (TF) plane. We initially show that the volume persona (i.e. counts of packets and bytes) of traffic flows at the transport layer exhibits highly non-stationary characteristics, hence rendering many typical classification methods inapplicable. By virtue of this constraint, we present a novel application classification method based on the Cohen energy TF distributions for such highly non-stationary signals. We have used the R{\'e}nyi information to measure the distinct complexity of any given application signal, and to subsequently construct a robust training model for every application protocol within our scheme. The effectiveness of our approach is demonstrated using real backbone and edge link network traces captured in US and Japan. Our results show that for the majority of applications, aggregate volume-based classification can reach up to 96% accuracy, while considering significantly less features in comparison with existing approaches.",
author = "Angelos Marnerides and Dimitrios Pezaros and Hyun-chul Kim and David Hutchison",
year = "2013",
month = jun,
day = "9",
doi = "10.1109/ICC.2013.6654911",
language = "English",
isbn = "9781467331203",
pages = "2513--2518",
booktitle = "2013 IEEE International Conference on Communications (ICC)",
publisher = "IEEE",
note = "IEEE ICC ; Conference date: 09-06-2013 Through 13-06-2013",

}

RIS

TY - GEN

T1 - Internet traffic classification using energy time-frequency distributions

AU - Marnerides, Angelos

AU - Pezaros, Dimitrios

AU - Kim, Hyun-chul

AU - Hutchison, David

PY - 2013/6/9

Y1 - 2013/6/9

N2 - We present a fundamentally new approach to classify application flows based on the mapping of aggregate transport-layer volume information onto the Time-Frequency (TF) plane. We initially show that the volume persona (i.e. counts of packets and bytes) of traffic flows at the transport layer exhibits highly non-stationary characteristics, hence rendering many typical classification methods inapplicable. By virtue of this constraint, we present a novel application classification method based on the Cohen energy TF distributions for such highly non-stationary signals. We have used the Rényi information to measure the distinct complexity of any given application signal, and to subsequently construct a robust training model for every application protocol within our scheme. The effectiveness of our approach is demonstrated using real backbone and edge link network traces captured in US and Japan. Our results show that for the majority of applications, aggregate volume-based classification can reach up to 96% accuracy, while considering significantly less features in comparison with existing approaches.

AB - We present a fundamentally new approach to classify application flows based on the mapping of aggregate transport-layer volume information onto the Time-Frequency (TF) plane. We initially show that the volume persona (i.e. counts of packets and bytes) of traffic flows at the transport layer exhibits highly non-stationary characteristics, hence rendering many typical classification methods inapplicable. By virtue of this constraint, we present a novel application classification method based on the Cohen energy TF distributions for such highly non-stationary signals. We have used the Rényi information to measure the distinct complexity of any given application signal, and to subsequently construct a robust training model for every application protocol within our scheme. The effectiveness of our approach is demonstrated using real backbone and edge link network traces captured in US and Japan. Our results show that for the majority of applications, aggregate volume-based classification can reach up to 96% accuracy, while considering significantly less features in comparison with existing approaches.

U2 - 10.1109/ICC.2013.6654911

DO - 10.1109/ICC.2013.6654911

M3 - Conference contribution/Paper

SN - 9781467331203

SP - 2513

EP - 2518

BT - 2013 IEEE International Conference on Communications (ICC)

PB - IEEE

T2 - IEEE ICC

Y2 - 9 June 2013 through 13 June 2013

ER -