A novel parameter refinement approach to one class support vector machine

Trung Le, Dat Tran, Wanli Ma, Dharmendra Sharma

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

1 Citation (Scopus)

Abstract

One-Class Support Vector Machine employs a grid parameter selection process to discover the best parameters for a given data set. It is assumed that two separate trade-off parameters are assigned to normal and abnormal data samples, respectively. However, this assumption is not always true because data samples have different contributions to the construction of hypersphere or hyperplane decision boundary. In this paper, we introduce a new iterative learning process that is carried out right after the grid parameter selection process to refine the trade-off parameter value for each sample. In this learning process, a weight is assigned to each sample to represent the contribution of that sample and is iteratively refined. Experimental results performed on a number of data sets show a better performance for the proposed approach.

Original languageEnglish
Title of host publicationNeural Information Processing
Subtitle of host publication18th International Conference, ICONIP 2011, Shanghai, China, November 13-17, 2011, Proceedings, Part II
EditorsBao-Liang Lu, Liqing Zhang, James Kwok
Place of PublicationBerlin Germany
PublisherSpringer
Pages529-536
Number of pages8
ISBN (Print)9783642249570
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event18th International Conference on Neural Information Processing, ICONIP 2011 - Shanghai, China
Duration: 13 Nov 201117 Nov 2011

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume7063
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference18th International Conference on Neural Information Processing, ICONIP 2011
CountryChina
CityShanghai
Period13/11/1117/11/11

Keywords

  • machine learning
  • novelty detection
  • One class classification
  • support vector machine

Cite this

Le, T., Tran, D., Ma, W., & Sharma, D. (2011). A novel parameter refinement approach to one class support vector machine. In B-L. Lu, L. Zhang, & J. Kwok (Eds.), Neural Information Processing: 18th International Conference, ICONIP 2011, Shanghai, China, November 13-17, 2011, Proceedings, Part II (pp. 529-536). (Lecture Notes in Computer Science ; Vol. 7063 ). Berlin Germany: Springer. https://doi.org/10.1007/978-3-642-24958-7_61
Le, Trung ; Tran, Dat ; Ma, Wanli ; Sharma, Dharmendra. / A novel parameter refinement approach to one class support vector machine. Neural Information Processing: 18th International Conference, ICONIP 2011, Shanghai, China, November 13-17, 2011, Proceedings, Part II. editor / Bao-Liang Lu ; Liqing Zhang ; James Kwok. Berlin Germany : Springer, 2011. pp. 529-536 (Lecture Notes in Computer Science ).
@inproceedings{3ae90e5bc43b4f3eb3018a9ce9e2c55a,
title = "A novel parameter refinement approach to one class support vector machine",
abstract = "One-Class Support Vector Machine employs a grid parameter selection process to discover the best parameters for a given data set. It is assumed that two separate trade-off parameters are assigned to normal and abnormal data samples, respectively. However, this assumption is not always true because data samples have different contributions to the construction of hypersphere or hyperplane decision boundary. In this paper, we introduce a new iterative learning process that is carried out right after the grid parameter selection process to refine the trade-off parameter value for each sample. In this learning process, a weight is assigned to each sample to represent the contribution of that sample and is iteratively refined. Experimental results performed on a number of data sets show a better performance for the proposed approach.",
keywords = "machine learning, novelty detection, One class classification, support vector machine",
author = "Trung Le and Dat Tran and Wanli Ma and Dharmendra Sharma",
year = "2011",
doi = "10.1007/978-3-642-24958-7_61",
language = "English",
isbn = "9783642249570",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "529--536",
editor = "Lu, {Bao-Liang } and Liqing Zhang and Kwok, {James }",
booktitle = "Neural Information Processing",

}

Le, T, Tran, D, Ma, W & Sharma, D 2011, A novel parameter refinement approach to one class support vector machine. in B-L Lu, L Zhang & J Kwok (eds), Neural Information Processing: 18th International Conference, ICONIP 2011, Shanghai, China, November 13-17, 2011, Proceedings, Part II. Lecture Notes in Computer Science , vol. 7063 , Springer, Berlin Germany, pp. 529-536, 18th International Conference on Neural Information Processing, ICONIP 2011, Shanghai, China, 13/11/11. https://doi.org/10.1007/978-3-642-24958-7_61

A novel parameter refinement approach to one class support vector machine. / Le, Trung; Tran, Dat; Ma, Wanli; Sharma, Dharmendra.

Neural Information Processing: 18th International Conference, ICONIP 2011, Shanghai, China, November 13-17, 2011, Proceedings, Part II. ed. / Bao-Liang Lu; Liqing Zhang; James Kwok. Berlin Germany : Springer, 2011. p. 529-536 (Lecture Notes in Computer Science ; Vol. 7063 ).

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

TY - GEN

T1 - A novel parameter refinement approach to one class support vector machine

AU - Le, Trung

AU - Tran, Dat

AU - Ma, Wanli

AU - Sharma, Dharmendra

PY - 2011

Y1 - 2011

N2 - One-Class Support Vector Machine employs a grid parameter selection process to discover the best parameters for a given data set. It is assumed that two separate trade-off parameters are assigned to normal and abnormal data samples, respectively. However, this assumption is not always true because data samples have different contributions to the construction of hypersphere or hyperplane decision boundary. In this paper, we introduce a new iterative learning process that is carried out right after the grid parameter selection process to refine the trade-off parameter value for each sample. In this learning process, a weight is assigned to each sample to represent the contribution of that sample and is iteratively refined. Experimental results performed on a number of data sets show a better performance for the proposed approach.

AB - One-Class Support Vector Machine employs a grid parameter selection process to discover the best parameters for a given data set. It is assumed that two separate trade-off parameters are assigned to normal and abnormal data samples, respectively. However, this assumption is not always true because data samples have different contributions to the construction of hypersphere or hyperplane decision boundary. In this paper, we introduce a new iterative learning process that is carried out right after the grid parameter selection process to refine the trade-off parameter value for each sample. In this learning process, a weight is assigned to each sample to represent the contribution of that sample and is iteratively refined. Experimental results performed on a number of data sets show a better performance for the proposed approach.

KW - machine learning

KW - novelty detection

KW - One class classification

KW - support vector machine

UR - http://www.scopus.com/inward/record.url?scp=81855177383&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-24958-7_61

DO - 10.1007/978-3-642-24958-7_61

M3 - Conference Paper

AN - SCOPUS:81855177383

SN - 9783642249570

T3 - Lecture Notes in Computer Science

SP - 529

EP - 536

BT - Neural Information Processing

A2 - Lu, Bao-Liang

A2 - Zhang, Liqing

A2 - Kwok, James

PB - Springer

CY - Berlin Germany

ER -

Le T, Tran D, Ma W, Sharma D. A novel parameter refinement approach to one class support vector machine. In Lu B-L, Zhang L, Kwok J, editors, Neural Information Processing: 18th International Conference, ICONIP 2011, Shanghai, China, November 13-17, 2011, Proceedings, Part II. Berlin Germany: Springer. 2011. p. 529-536. (Lecture Notes in Computer Science ). https://doi.org/10.1007/978-3-642-24958-7_61