Applying support vector machine to P2P traffic identification with smooth processing

Yang Liu; Rui Wang; Heyun Huang; Yingsheng Zeng; Hangen He

doi:10.1109/ICOSP.2006.345921

Applying support vector machine to P2P traffic identification with smooth processing

Yang Liu^*
, Rui Wang
, Heyun Huang
, Yingsheng Zeng
, Hangen He

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

5 Citations (Scopus)

Abstract

Since the emergence of peer-to-peer (P2P) networking in the last 90s, P2P traffic, being a significant portion of the network traffic today, has constituted a highly desirable class for identification. How to improve the accuracy of the P2P traffic identification efficiently is still a challenging problem. The support vector machine (SVM) is a powerful learning mechanism and has shown remarkable success in many applications. In this paper, we propose a new approach for P2P traffic identification, which uses the support vector machine and a new technology called smooth processing. The experiments of identifying P2P traffic show that the generalization performance and the accuracy of identification are improved significantly compared to that of the traditional methods.

Original language	English
Title of host publication	8th International Conference on Signal Processing, ICSP 2006
Publisher	IEEE
Number of pages	4
Volume	4
ISBN (Print)	0780397371, 9780780397378
DOIs	https://doi.org/10.1109/ICOSP.2006.345921
Publication status	Published - 16 Nov 2006
Event	8th International Conference on Signal Processing, ICSP 2006 - Guilin, China Duration: 16 Nov 2006 → 20 Nov 2006

Publication series

Name	International Conference on Signal Processing Proceedings, ICSP

Conference

Conference	8th International Conference on Signal Processing, ICSP 2006
Country/Territory	China
City	Guilin
Period	16/11/06 → 20/11/06

Access to Document

10.1109/ICOSP.2006.345921

Cite this

@inproceedings{3cb007b48efc4753b3a665a61c29ccb0,

title = "Applying support vector machine to P2P traffic identification with smooth processing",

abstract = "Since the emergence of peer-to-peer (P2P) networking in the last 90s, P2P traffic, being a significant portion of the network traffic today, has constituted a highly desirable class for identification. How to improve the accuracy of the P2P traffic identification efficiently is still a challenging problem. The support vector machine (SVM) is a powerful learning mechanism and has shown remarkable success in many applications. In this paper, we propose a new approach for P2P traffic identification, which uses the support vector machine and a new technology called smooth processing. The experiments of identifying P2P traffic show that the generalization performance and the accuracy of identification are improved significantly compared to that of the traditional methods.",

author = "Yang Liu and Rui Wang and Heyun Huang and Yingsheng Zeng and Hangen He",

note = "Publisher Copyright: {\textcopyright} 2006 IEEE; 8th International Conference on Signal Processing, ICSP 2006 ; Conference date: 16-11-2006 Through 20-11-2006",

year = "2006",

month = nov,

day = "16",

doi = "10.1109/ICOSP.2006.345921",

language = "English",

isbn = "0780397371",

volume = "4",

series = "International Conference on Signal Processing Proceedings, ICSP",

publisher = "IEEE",

booktitle = "8th International Conference on Signal Processing, ICSP 2006",

address = "United States",

}

Liu, Y, Wang, R, Huang, H, Zeng, Y & He, H 2006, Applying support vector machine to P2P traffic identification with smooth processing. in 8th International Conference on Signal Processing, ICSP 2006. vol. 4, International Conference on Signal Processing Proceedings, ICSP, IEEE, 8th International Conference on Signal Processing, ICSP 2006, Guilin, China, 16/11/06. https://doi.org/10.1109/ICOSP.2006.345921

Applying support vector machine to P2P traffic identification with smooth processing. / Liu, Yang; Wang, Rui; Huang, Heyun et al.
8th International Conference on Signal Processing, ICSP 2006. Vol. 4 IEEE, 2006. (International Conference on Signal Processing Proceedings, ICSP).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Applying support vector machine to P2P traffic identification with smooth processing

AU - Liu, Yang

AU - Wang, Rui

AU - Huang, Heyun

AU - Zeng, Yingsheng

AU - He, Hangen

PY - 2006/11/16

Y1 - 2006/11/16

N2 - Since the emergence of peer-to-peer (P2P) networking in the last 90s, P2P traffic, being a significant portion of the network traffic today, has constituted a highly desirable class for identification. How to improve the accuracy of the P2P traffic identification efficiently is still a challenging problem. The support vector machine (SVM) is a powerful learning mechanism and has shown remarkable success in many applications. In this paper, we propose a new approach for P2P traffic identification, which uses the support vector machine and a new technology called smooth processing. The experiments of identifying P2P traffic show that the generalization performance and the accuracy of identification are improved significantly compared to that of the traditional methods.

AB - Since the emergence of peer-to-peer (P2P) networking in the last 90s, P2P traffic, being a significant portion of the network traffic today, has constituted a highly desirable class for identification. How to improve the accuracy of the P2P traffic identification efficiently is still a challenging problem. The support vector machine (SVM) is a powerful learning mechanism and has shown remarkable success in many applications. In this paper, we propose a new approach for P2P traffic identification, which uses the support vector machine and a new technology called smooth processing. The experiments of identifying P2P traffic show that the generalization performance and the accuracy of identification are improved significantly compared to that of the traditional methods.

UR - https://www.scopus.com/pages/publications/34249299420

U2 - 10.1109/ICOSP.2006.345921

DO - 10.1109/ICOSP.2006.345921

M3 - Conference proceeding

AN - SCOPUS:34249299420

SN - 0780397371

SN - 9780780397378

VL - 4

T3 - International Conference on Signal Processing Proceedings, ICSP

BT - 8th International Conference on Signal Processing, ICSP 2006

PB - IEEE

T2 - 8th International Conference on Signal Processing, ICSP 2006

Y2 - 16 November 2006 through 20 November 2006

ER -

Applying support vector machine to P2P traffic identification with smooth processing

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this