IEICE TRANSACTIONS on Information
Out-of-Sequence Traffic Classification Based on Improved Dynamic Time Warping
Summary :
Traffic classification has recently gained much attention in both academic and industrial research communities. Many machine learning methods have been proposed to tackle this problem and have shown good results. However, when applied to traffic with out-of-sequence packets, the accuracy of existing machine learning approaches decreases dramatically. We observe the main reason is that the out-of-sequence packets change the spatial representation of feature vectors, which means the property of linear mapping relation among features used in machine learning approaches cannot hold any more. To address this problem, this paper proposes an Improved Dynamic Time Warping (IDTW) method, which can align two feature vectors using non-linear alignment. Experimental results on two real traces show that IDTW achieves better classification accuracy in out-of-sequence traffic classification, in comparison to existing machine learning approaches.
- Publication
- IEICE TRANSACTIONS on Information Vol.E96-D No.11 pp.2354-2364
- Publication Date
- 2013/11/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E96.D.2354
- Type of Manuscript
- PAPER
- Category
- Information Network
Authors
Jinghua YAN
Beijing
Xiaochun YUN
Coordination Center of China
Hao LUO
Beijing
Zhigang WU
Beijing
Shuzhuang ZHANG
Beijing
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Jinghua YAN, Xiaochun YUN, Hao LUO, Zhigang WU, Shuzhuang ZHANG, "Out-of-Sequence Traffic Classification Based on Improved Dynamic Time Warping" in IEICE TRANSACTIONS on Information,
vol. E96-D, no. 11, pp. 2354-2364, November 2013, doi: 10.1587/transinf.E96.D.2354.
Abstract: Traffic classification has recently gained much attention in both academic and industrial research communities. Many machine learning methods have been proposed to tackle this problem and have shown good results. However, when applied to traffic with out-of-sequence packets, the accuracy of existing machine learning approaches decreases dramatically. We observe the main reason is that the out-of-sequence packets change the spatial representation of feature vectors, which means the property of linear mapping relation among features used in machine learning approaches cannot hold any more. To address this problem, this paper proposes an Improved Dynamic Time Warping (IDTW) method, which can align two feature vectors using non-linear alignment. Experimental results on two real traces show that IDTW achieves better classification accuracy in out-of-sequence traffic classification, in comparison to existing machine learning approaches.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E96.D.2354/_p
Copy
@ARTICLE{e96-d_11_2354,
author={Jinghua YAN, Xiaochun YUN, Hao LUO, Zhigang WU, Shuzhuang ZHANG, },
journal={IEICE TRANSACTIONS on Information},
title={Out-of-Sequence Traffic Classification Based on Improved Dynamic Time Warping},
year={2013},
volume={E96-D},
number={11},
pages={2354-2364},
abstract={Traffic classification has recently gained much attention in both academic and industrial research communities. Many machine learning methods have been proposed to tackle this problem and have shown good results. However, when applied to traffic with out-of-sequence packets, the accuracy of existing machine learning approaches decreases dramatically. We observe the main reason is that the out-of-sequence packets change the spatial representation of feature vectors, which means the property of linear mapping relation among features used in machine learning approaches cannot hold any more. To address this problem, this paper proposes an Improved Dynamic Time Warping (IDTW) method, which can align two feature vectors using non-linear alignment. Experimental results on two real traces show that IDTW achieves better classification accuracy in out-of-sequence traffic classification, in comparison to existing machine learning approaches.},
keywords={},
doi={10.1587/transinf.E96.D.2354},
ISSN={1745-1361},
month={November},}
Copy
TY - JOUR
TI - Out-of-Sequence Traffic Classification Based on Improved Dynamic Time Warping
T2 - IEICE TRANSACTIONS on Information
SP - 2354
EP - 2364
AU - Jinghua YAN
AU - Xiaochun YUN
AU - Hao LUO
AU - Zhigang WU
AU - Shuzhuang ZHANG
PY - 2013
DO - 10.1587/transinf.E96.D.2354
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2013
AB - Traffic classification has recently gained much attention in both academic and industrial research communities. Many machine learning methods have been proposed to tackle this problem and have shown good results. However, when applied to traffic with out-of-sequence packets, the accuracy of existing machine learning approaches decreases dramatically. We observe the main reason is that the out-of-sequence packets change the spatial representation of feature vectors, which means the property of linear mapping relation among features used in machine learning approaches cannot hold any more. To address this problem, this paper proposes an Improved Dynamic Time Warping (IDTW) method, which can align two feature vectors using non-linear alignment. Experimental results on two real traces show that IDTW achieves better classification accuracy in out-of-sequence traffic classification, in comparison to existing machine learning approaches.
ER -
English
