Research on noise insensitive SVM based multi-class classifier

Kan Li; Yu Shu Liu

doi:10.1109/ICMLC.2004.1378593

Research on noise insensitive SVM based multi-class classifier

Kan Li^*
, Yu Shu Liu

^*Corresponding author for this work

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

A noise insensitive SVM multi-class classifier is proposed. The algorithm is used to analyze data characteristic in the high-dimension data set. Firstly a noise insensitive SVM two-class classifier is built to tackle the noise problem. On the basis of standard SVM, constraint distance is also considered to determine the optimal separating hyperplane. According to these, the noise insensitive SVM multi-class classifier is designed with edited SVM, confidence interval and one-against-one method.

Original language	English
Title of host publication	Proceedings of 2004 International Conference on Machine Learning and Cybernetics
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3234-3237
Number of pages	4
ISBN (Print)	0780384032, 9780780384033
DOIs	https://doi.org/10.1109/ICMLC.2004.1378593
Publication status	Published - 2004
Externally published	Yes
Event	3rd International Conference on Machine Learning and Cybernetics, ICMLC 2004 - Shanghai, China Duration: 26 Aug 2004 → 29 Aug 2004

Publication series

Name	Proceedings of 2004 International Conference on Machine Learning and Cybernetics
Volume	5

Conference

Conference	3rd International Conference on Machine Learning and Cybernetics, ICMLC 2004
Country/Territory	China
City	Shanghai
Period	26/08/04 → 29/08/04

Keywords

Constraint distance
Multi-class classifier
Noise
Support vector machine(SVM)

Access to Document

10.1109/ICMLC.2004.1378593

Cite this

Li, K., & Liu, Y. S. (2004). Research on noise insensitive SVM based multi-class classifier. In Proceedings of 2004 International Conference on Machine Learning and Cybernetics (pp. 3234-3237). (Proceedings of 2004 International Conference on Machine Learning and Cybernetics; Vol. 5). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMLC.2004.1378593

@inproceedings{31cd5cafeae34dd184d37ccb1045c324,

title = "Research on noise insensitive SVM based multi-class classifier",

abstract = "A noise insensitive SVM multi-class classifier is proposed. The algorithm is used to analyze data characteristic in the high-dimension data set. Firstly a noise insensitive SVM two-class classifier is built to tackle the noise problem. On the basis of standard SVM, constraint distance is also considered to determine the optimal separating hyperplane. According to these, the noise insensitive SVM multi-class classifier is designed with edited SVM, confidence interval and one-against-one method.",

keywords = "Constraint distance, Multi-class classifier, Noise, Support vector machine(SVM)",

author = "Kan Li and Liu, \{Yu Shu\}",

year = "2004",

doi = "10.1109/ICMLC.2004.1378593",

language = "English",

isbn = "0780384032",

series = "Proceedings of 2004 International Conference on Machine Learning and Cybernetics",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "3234--3237",

booktitle = "Proceedings of 2004 International Conference on Machine Learning and Cybernetics",

address = "United States",

note = "3rd International Conference on Machine Learning and Cybernetics, ICMLC 2004 ; Conference date: 26-08-2004 Through 29-08-2004",

}

Li, K & Liu, YS 2004, Research on noise insensitive SVM based multi-class classifier. in Proceedings of 2004 International Conference on Machine Learning and Cybernetics. Proceedings of 2004 International Conference on Machine Learning and Cybernetics, vol. 5, Institute of Electrical and Electronics Engineers Inc., pp. 3234-3237, 3rd International Conference on Machine Learning and Cybernetics, ICMLC 2004, Shanghai, China, 26/08/04. https://doi.org/10.1109/ICMLC.2004.1378593

Research on noise insensitive SVM based multi-class classifier. / Li, Kan; Liu, Yu Shu.
Proceedings of 2004 International Conference on Machine Learning and Cybernetics. Institute of Electrical and Electronics Engineers Inc., 2004. p. 3234-3237 (Proceedings of 2004 International Conference on Machine Learning and Cybernetics; Vol. 5).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Research on noise insensitive SVM based multi-class classifier

AU - Li, Kan

AU - Liu, Yu Shu

PY - 2004

Y1 - 2004

N2 - A noise insensitive SVM multi-class classifier is proposed. The algorithm is used to analyze data characteristic in the high-dimension data set. Firstly a noise insensitive SVM two-class classifier is built to tackle the noise problem. On the basis of standard SVM, constraint distance is also considered to determine the optimal separating hyperplane. According to these, the noise insensitive SVM multi-class classifier is designed with edited SVM, confidence interval and one-against-one method.

AB - A noise insensitive SVM multi-class classifier is proposed. The algorithm is used to analyze data characteristic in the high-dimension data set. Firstly a noise insensitive SVM two-class classifier is built to tackle the noise problem. On the basis of standard SVM, constraint distance is also considered to determine the optimal separating hyperplane. According to these, the noise insensitive SVM multi-class classifier is designed with edited SVM, confidence interval and one-against-one method.

KW - Constraint distance

KW - Multi-class classifier

KW - Noise

KW - Support vector machine(SVM)

UR - https://www.scopus.com/pages/publications/6344237344

U2 - 10.1109/ICMLC.2004.1378593

DO - 10.1109/ICMLC.2004.1378593

M3 - Conference contribution

AN - SCOPUS:6344237344

SN - 0780384032

SN - 9780780384033

T3 - Proceedings of 2004 International Conference on Machine Learning and Cybernetics

SP - 3234

EP - 3237

BT - Proceedings of 2004 International Conference on Machine Learning and Cybernetics

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd International Conference on Machine Learning and Cybernetics, ICMLC 2004

Y2 - 26 August 2004 through 29 August 2004

ER -

Research on noise insensitive SVM based multi-class classifier

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this