Internet traffic classification using score level fusion of multiple classifier

Masatsugu Ichino, Hiroaki Maeda, Takeshi Yamashita, Kentaro Hoshi, Naohisa Komatsu, Kei Takeshita, Masayuki Tsujino, Motoi Iwashita, Hideaki Yoshino

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Internet traffic is continuously growing fast due to the rapid spread of the internet and the speed-up of the internet connection. Also, the applications provided on the internet have become more diversified. To support the QoS requirements for these internet applications, it would be better to measure the traffic volume according to the applications. Therefore, we are engaged in the application classification method, which is an offline technique for identifying the applications in units of flow. In some application classification methods, the applications of the target flows are analyzed according to their statistics on traffic metric, or features. We focus on these feature based classification methods, since the methods have the advantage that the port number and the packet payload need not be checked for classification. In the field of the machine learning, the classification methods that consist of multiple classifiers have been discussed. This is why the classification methods are improved in performance. However, the conventional feature based classification methods consists of single classifier. Also, the design of multiple classifiers has hardly been discussed. The design includes the way of combining some classifiers. Here, we introduce the fusion of multiple classifiers and propose applying the score level fusion using feature vectors to concatenate each classifier score to classify the flow into applications.

Original languageEnglish
Title of host publicationProceedings - 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010
Pages105-110
Number of pages6
DOIs
Publication statusPublished - 2010
Event9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010 - Yamagata
Duration: 2010 Aug 182010 Aug 20

Other

Other9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010
CityYamagata
Period10/8/1810/8/20

Fingerprint

Classifiers
Fusion reactions
Internet
Learning systems
Quality of service
Statistics

Keywords

  • Application classification
  • Internet traffic
  • Multiple classifier
  • Score level fusion

ASJC Scopus subject areas

  • Information Systems

Cite this

Ichino, M., Maeda, H., Yamashita, T., Hoshi, K., Komatsu, N., Takeshita, K., ... Yoshino, H. (2010). Internet traffic classification using score level fusion of multiple classifier. In Proceedings - 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010 (pp. 105-110). [5593127] https://doi.org/10.1109/ICIS.2010.48

Internet traffic classification using score level fusion of multiple classifier. / Ichino, Masatsugu; Maeda, Hiroaki; Yamashita, Takeshi; Hoshi, Kentaro; Komatsu, Naohisa; Takeshita, Kei; Tsujino, Masayuki; Iwashita, Motoi; Yoshino, Hideaki.

Proceedings - 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010. 2010. p. 105-110 5593127.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ichino, M, Maeda, H, Yamashita, T, Hoshi, K, Komatsu, N, Takeshita, K, Tsujino, M, Iwashita, M & Yoshino, H 2010, Internet traffic classification using score level fusion of multiple classifier. in Proceedings - 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010., 5593127, pp. 105-110, 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010, Yamagata, 10/8/18. https://doi.org/10.1109/ICIS.2010.48
Ichino M, Maeda H, Yamashita T, Hoshi K, Komatsu N, Takeshita K et al. Internet traffic classification using score level fusion of multiple classifier. In Proceedings - 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010. 2010. p. 105-110. 5593127 https://doi.org/10.1109/ICIS.2010.48
Ichino, Masatsugu ; Maeda, Hiroaki ; Yamashita, Takeshi ; Hoshi, Kentaro ; Komatsu, Naohisa ; Takeshita, Kei ; Tsujino, Masayuki ; Iwashita, Motoi ; Yoshino, Hideaki. / Internet traffic classification using score level fusion of multiple classifier. Proceedings - 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010. 2010. pp. 105-110
@inproceedings{585737d181f84eaeb2cc140df41c5cd0,
title = "Internet traffic classification using score level fusion of multiple classifier",
abstract = "Internet traffic is continuously growing fast due to the rapid spread of the internet and the speed-up of the internet connection. Also, the applications provided on the internet have become more diversified. To support the QoS requirements for these internet applications, it would be better to measure the traffic volume according to the applications. Therefore, we are engaged in the application classification method, which is an offline technique for identifying the applications in units of flow. In some application classification methods, the applications of the target flows are analyzed according to their statistics on traffic metric, or features. We focus on these feature based classification methods, since the methods have the advantage that the port number and the packet payload need not be checked for classification. In the field of the machine learning, the classification methods that consist of multiple classifiers have been discussed. This is why the classification methods are improved in performance. However, the conventional feature based classification methods consists of single classifier. Also, the design of multiple classifiers has hardly been discussed. The design includes the way of combining some classifiers. Here, we introduce the fusion of multiple classifiers and propose applying the score level fusion using feature vectors to concatenate each classifier score to classify the flow into applications.",
keywords = "Application classification, Internet traffic, Multiple classifier, Score level fusion",
author = "Masatsugu Ichino and Hiroaki Maeda and Takeshi Yamashita and Kentaro Hoshi and Naohisa Komatsu and Kei Takeshita and Masayuki Tsujino and Motoi Iwashita and Hideaki Yoshino",
year = "2010",
doi = "10.1109/ICIS.2010.48",
language = "English",
isbn = "9780769541471",
pages = "105--110",
booktitle = "Proceedings - 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010",

}

TY - GEN

T1 - Internet traffic classification using score level fusion of multiple classifier

AU - Ichino, Masatsugu

AU - Maeda, Hiroaki

AU - Yamashita, Takeshi

AU - Hoshi, Kentaro

AU - Komatsu, Naohisa

AU - Takeshita, Kei

AU - Tsujino, Masayuki

AU - Iwashita, Motoi

AU - Yoshino, Hideaki

PY - 2010

Y1 - 2010

N2 - Internet traffic is continuously growing fast due to the rapid spread of the internet and the speed-up of the internet connection. Also, the applications provided on the internet have become more diversified. To support the QoS requirements for these internet applications, it would be better to measure the traffic volume according to the applications. Therefore, we are engaged in the application classification method, which is an offline technique for identifying the applications in units of flow. In some application classification methods, the applications of the target flows are analyzed according to their statistics on traffic metric, or features. We focus on these feature based classification methods, since the methods have the advantage that the port number and the packet payload need not be checked for classification. In the field of the machine learning, the classification methods that consist of multiple classifiers have been discussed. This is why the classification methods are improved in performance. However, the conventional feature based classification methods consists of single classifier. Also, the design of multiple classifiers has hardly been discussed. The design includes the way of combining some classifiers. Here, we introduce the fusion of multiple classifiers and propose applying the score level fusion using feature vectors to concatenate each classifier score to classify the flow into applications.

AB - Internet traffic is continuously growing fast due to the rapid spread of the internet and the speed-up of the internet connection. Also, the applications provided on the internet have become more diversified. To support the QoS requirements for these internet applications, it would be better to measure the traffic volume according to the applications. Therefore, we are engaged in the application classification method, which is an offline technique for identifying the applications in units of flow. In some application classification methods, the applications of the target flows are analyzed according to their statistics on traffic metric, or features. We focus on these feature based classification methods, since the methods have the advantage that the port number and the packet payload need not be checked for classification. In the field of the machine learning, the classification methods that consist of multiple classifiers have been discussed. This is why the classification methods are improved in performance. However, the conventional feature based classification methods consists of single classifier. Also, the design of multiple classifiers has hardly been discussed. The design includes the way of combining some classifiers. Here, we introduce the fusion of multiple classifiers and propose applying the score level fusion using feature vectors to concatenate each classifier score to classify the flow into applications.

KW - Application classification

KW - Internet traffic

KW - Multiple classifier

KW - Score level fusion

UR - http://www.scopus.com/inward/record.url?scp=78649258064&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649258064&partnerID=8YFLogxK

U2 - 10.1109/ICIS.2010.48

DO - 10.1109/ICIS.2010.48

M3 - Conference contribution

SN - 9780769541471

SP - 105

EP - 110

BT - Proceedings - 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010

ER -