An improvement of one-against-one method for multi-class support vector machine

Yang Liu; Rui Wang; Ying Sheng Zeng

doi:10.1109/ICMLC.2007.4370646

An improvement of one-against-one method for multi-class support vector machine

Yang Liu^*
, Rui Wang
, Ying Sheng Zeng

^*Corresponding author for this work

Department of Computer Science

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

21 Citations (Scopus)

Abstract

The support vector machine (SVM) has an excellent ability to solve binary classification problems. How to process multi-class problems with SVM is one of the present focuses. Among the existing multi-class SVM methods include one-against-one method, one-against-all method and some others. This paper presents an improved technique of one-against-one method that can largely reduce the number of the hyperplanes and speed up the predicting process. The experimental results show that the proposed method not only has promising accuracy and less training time, but also significantly improves the predicting speed in comparison with traditional one-against-one and one-against-all method.

Original language	English
Title of host publication	Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, ICMLC 2007
Publisher	IEEE
Pages	2915-2920
Number of pages	6
ISBN (Print)	142440973X, 9781424409730
DOIs	https://doi.org/10.1109/ICMLC.2007.4370646
Publication status	Published - 19 Aug 2007
Event	6th International Conference on Machine Learning and Cybernetics, ICMLC 2007 - Hong Kong, China Duration: 19 Aug 2007 → 22 Aug 2007

Publication series

Name	Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, ICMLC

Conference

Conference	6th International Conference on Machine Learning and Cybernetics, ICMLC 2007
Country/Territory	China
City	Hong Kong
Period	19/08/07 → 22/08/07

User-Defined Keywords

Multi-class problems
One-against-one method
Support vector machine (SVM)

Access to Document

10.1109/ICMLC.2007.4370646

Cite this

Liu, Y., Wang, R., & Zeng, Y. S. (2007). An improvement of one-against-one method for multi-class support vector machine. In Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, ICMLC 2007 (pp. 2915-2920). (Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, ICMLC). IEEE. https://doi.org/10.1109/ICMLC.2007.4370646

@inproceedings{ed9ecfb491bc42f5bb555b981795c0d6,

title = "An improvement of one-against-one method for multi-class support vector machine",

abstract = "The support vector machine (SVM) has an excellent ability to solve binary classification problems. How to process multi-class problems with SVM is one of the present focuses. Among the existing multi-class SVM methods include one-against-one method, one-against-all method and some others. This paper presents an improved technique of one-against-one method that can largely reduce the number of the hyperplanes and speed up the predicting process. The experimental results show that the proposed method not only has promising accuracy and less training time, but also significantly improves the predicting speed in comparison with traditional one-against-one and one-against-all method.",

keywords = "Multi-class problems, One-against-one method, Support vector machine (SVM)",

author = "Yang Liu and Rui Wang and Zeng, \{Ying Sheng\}",

note = "Publisher Copyright: {\textcopyright} 2007 IEEE.; 6th International Conference on Machine Learning and Cybernetics, ICMLC 2007 ; Conference date: 19-08-2007 Through 22-08-2007",

year = "2007",

month = aug,

day = "19",

doi = "10.1109/ICMLC.2007.4370646",

language = "English",

isbn = "142440973X",

series = "Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, ICMLC",

publisher = "IEEE",

pages = "2915--2920",

booktitle = "Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, ICMLC 2007",

address = "United States",

}

Liu, Y, Wang, R & Zeng, YS 2007, An improvement of one-against-one method for multi-class support vector machine. in Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, ICMLC 2007. Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, ICMLC, IEEE, pp. 2915-2920, 6th International Conference on Machine Learning and Cybernetics, ICMLC 2007, Hong Kong, China, 19/08/07. https://doi.org/10.1109/ICMLC.2007.4370646

An improvement of one-against-one method for multi-class support vector machine. / Liu, Yang; Wang, Rui; Zeng, Ying Sheng.
Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, ICMLC 2007. IEEE, 2007. p. 2915-2920 (Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, ICMLC).

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

TY - GEN

T1 - An improvement of one-against-one method for multi-class support vector machine

AU - Liu, Yang

AU - Wang, Rui

AU - Zeng, Ying Sheng

PY - 2007/8/19

Y1 - 2007/8/19

N2 - The support vector machine (SVM) has an excellent ability to solve binary classification problems. How to process multi-class problems with SVM is one of the present focuses. Among the existing multi-class SVM methods include one-against-one method, one-against-all method and some others. This paper presents an improved technique of one-against-one method that can largely reduce the number of the hyperplanes and speed up the predicting process. The experimental results show that the proposed method not only has promising accuracy and less training time, but also significantly improves the predicting speed in comparison with traditional one-against-one and one-against-all method.

AB - The support vector machine (SVM) has an excellent ability to solve binary classification problems. How to process multi-class problems with SVM is one of the present focuses. Among the existing multi-class SVM methods include one-against-one method, one-against-all method and some others. This paper presents an improved technique of one-against-one method that can largely reduce the number of the hyperplanes and speed up the predicting process. The experimental results show that the proposed method not only has promising accuracy and less training time, but also significantly improves the predicting speed in comparison with traditional one-against-one and one-against-all method.

KW - Multi-class problems

KW - One-against-one method

KW - Support vector machine (SVM)

UR - https://www.scopus.com/pages/publications/38049002505

U2 - 10.1109/ICMLC.2007.4370646

DO - 10.1109/ICMLC.2007.4370646

M3 - Conference proceeding

AN - SCOPUS:38049002505

SN - 142440973X

SN - 9781424409730

T3 - Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, ICMLC

SP - 2915

EP - 2920

BT - Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, ICMLC 2007

PB - IEEE

T2 - 6th International Conference on Machine Learning and Cybernetics, ICMLC 2007

Y2 - 19 August 2007 through 22 August 2007

ER -

An improvement of one-against-one method for multi-class support vector machine

Abstract

Publication series

Conference

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this