Parallel Support Vector Data Description

Dat TRAN, Xu HUANG, Wanli MA

Research output: A Conference proceeding or a Chapter in BookConference contribution

2 Citations (Scopus)
1 Downloads (Pure)

Abstract

This paper proposes an extension of Support Vector Data Description (SVDD) to provide a better data description. The extension is called Distant SVDD (DSVDD) that determines a smallest hypersphere enclosing all normal (positive) samples as seen in SVDD. In addition, DSVDD maximises the distance from centre of that hypersphere to the origin. When some abnormal (negative) samples are introduced, the DSVDD is extended to Parallel SVDD that also determines a smallest hypersphere for normal samples and at the same time determines a smallest hyperphere for abnormal samples and maximises the distance between centres of these two hyperspheres. Experimental results for classification show that the proposed extensions provide higher accuracy than the original SVDD.
Original languageEnglish
Title of host publicationInternational Work-Conference on Artificial Neural Networks:Advances in Computational Intelligence (IWANN 2013)
Subtitle of host publicationLecture Notes in Computer Science
EditorsIgnacio Rojas, Gonzalo Joya, Joan Gabestany
Place of PublicationBerlin
PublisherSpringer
Pages280-290
Number of pages11
Volume7902
ISBN (Electronic)9783642386794
ISBN (Print)9783642386787
DOIs
Publication statusPublished - 2013
Event12th International Work-Conference on Artificial Neural Networks, IWANN 2013 - Tenerife, Tenerife, Spain
Duration: 12 Jun 201314 Jun 2013

Conference

Conference12th International Work-Conference on Artificial Neural Networks, IWANN 2013
Abbreviated titleIWANN 2013
CountrySpain
CityTenerife
Period12/06/1314/06/13

Fingerprint

Data description

Cite this

TRAN, D., HUANG, X., & MA, W. (2013). Parallel Support Vector Data Description. In I. Rojas, G. Joya, & J. Gabestany (Eds.), International Work-Conference on Artificial Neural Networks:Advances in Computational Intelligence (IWANN 2013): Lecture Notes in Computer Science (Vol. 7902, pp. 280-290). Berlin: Springer. https://doi.org/10.1007/978-3-642-38679-4_27
TRAN, Dat ; HUANG, Xu ; MA, Wanli. / Parallel Support Vector Data Description. International Work-Conference on Artificial Neural Networks:Advances in Computational Intelligence (IWANN 2013): Lecture Notes in Computer Science. editor / Ignacio Rojas ; Gonzalo Joya ; Joan Gabestany. Vol. 7902 Berlin : Springer, 2013. pp. 280-290
@inproceedings{a87f9c4cf1454a5cb0647e5f6d231d14,
title = "Parallel Support Vector Data Description",
abstract = "This paper proposes an extension of Support Vector Data Description (SVDD) to provide a better data description. The extension is called Distant SVDD (DSVDD) that determines a smallest hypersphere enclosing all normal (positive) samples as seen in SVDD. In addition, DSVDD maximises the distance from centre of that hypersphere to the origin. When some abnormal (negative) samples are introduced, the DSVDD is extended to Parallel SVDD that also determines a smallest hypersphere for normal samples and at the same time determines a smallest hyperphere for abnormal samples and maximises the distance between centres of these two hyperspheres. Experimental results for classification show that the proposed extensions provide higher accuracy than the original SVDD.",
keywords = "Novelty detection, One-class classification, Spherically shaped boundary, Support vector data description, Support Vector Data Description",
author = "Dat TRAN and Xu HUANG and Wanli MA",
year = "2013",
doi = "10.1007/978-3-642-38679-4_27",
language = "English",
isbn = "9783642386787",
volume = "7902",
pages = "280--290",
editor = "Ignacio Rojas and Gonzalo Joya and Joan Gabestany",
booktitle = "International Work-Conference on Artificial Neural Networks:Advances in Computational Intelligence (IWANN 2013)",
publisher = "Springer",
address = "Netherlands",

}

TRAN, D, HUANG, X & MA, W 2013, Parallel Support Vector Data Description. in I Rojas, G Joya & J Gabestany (eds), International Work-Conference on Artificial Neural Networks:Advances in Computational Intelligence (IWANN 2013): Lecture Notes in Computer Science. vol. 7902, Springer, Berlin, pp. 280-290, 12th International Work-Conference on Artificial Neural Networks, IWANN 2013, Tenerife, Spain, 12/06/13. https://doi.org/10.1007/978-3-642-38679-4_27

Parallel Support Vector Data Description. / TRAN, Dat; HUANG, Xu; MA, Wanli.

International Work-Conference on Artificial Neural Networks:Advances in Computational Intelligence (IWANN 2013): Lecture Notes in Computer Science. ed. / Ignacio Rojas; Gonzalo Joya; Joan Gabestany. Vol. 7902 Berlin : Springer, 2013. p. 280-290.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Parallel Support Vector Data Description

AU - TRAN, Dat

AU - HUANG, Xu

AU - MA, Wanli

PY - 2013

Y1 - 2013

N2 - This paper proposes an extension of Support Vector Data Description (SVDD) to provide a better data description. The extension is called Distant SVDD (DSVDD) that determines a smallest hypersphere enclosing all normal (positive) samples as seen in SVDD. In addition, DSVDD maximises the distance from centre of that hypersphere to the origin. When some abnormal (negative) samples are introduced, the DSVDD is extended to Parallel SVDD that also determines a smallest hypersphere for normal samples and at the same time determines a smallest hyperphere for abnormal samples and maximises the distance between centres of these two hyperspheres. Experimental results for classification show that the proposed extensions provide higher accuracy than the original SVDD.

AB - This paper proposes an extension of Support Vector Data Description (SVDD) to provide a better data description. The extension is called Distant SVDD (DSVDD) that determines a smallest hypersphere enclosing all normal (positive) samples as seen in SVDD. In addition, DSVDD maximises the distance from centre of that hypersphere to the origin. When some abnormal (negative) samples are introduced, the DSVDD is extended to Parallel SVDD that also determines a smallest hypersphere for normal samples and at the same time determines a smallest hyperphere for abnormal samples and maximises the distance between centres of these two hyperspheres. Experimental results for classification show that the proposed extensions provide higher accuracy than the original SVDD.

KW - Novelty detection

KW - One-class classification

KW - Spherically shaped boundary

KW - Support vector data description

KW - Support Vector Data Description

U2 - 10.1007/978-3-642-38679-4_27

DO - 10.1007/978-3-642-38679-4_27

M3 - Conference contribution

SN - 9783642386787

VL - 7902

SP - 280

EP - 290

BT - International Work-Conference on Artificial Neural Networks:Advances in Computational Intelligence (IWANN 2013)

A2 - Rojas, Ignacio

A2 - Joya, Gonzalo

A2 - Gabestany, Joan

PB - Springer

CY - Berlin

ER -

TRAN D, HUANG X, MA W. Parallel Support Vector Data Description. In Rojas I, Joya G, Gabestany J, editors, International Work-Conference on Artificial Neural Networks:Advances in Computational Intelligence (IWANN 2013): Lecture Notes in Computer Science. Vol. 7902. Berlin: Springer. 2013. p. 280-290 https://doi.org/10.1007/978-3-642-38679-4_27