Multi-sphere support vector data description for brain-computer interface

Phuoc Nguyen; Dat Tran; Trung Le; Tuan Hoang; Dharmendra Sharma

doi:10.1109/CCE.2012.6315920

Multi-sphere support vector data description for brain-computer interface

Phuoc Nguyen, Dat Tran, Trung Le, Tuan Hoang, Dharmendra Sharma

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

7 Citations (Scopus)

Abstract

Support vector data description (SVDD) has been widely used in pattern classification, however it does not provide high performance in brain-computer interface (BCI) classification problems since brain signals are noisy and chaotic. Brain data have distinct distributions and hence a hyper-sphere in SVDD could not well describe the data. We propose in this paper a multi-sphere approach to SVDD to have a better description for the brain data. We also propose a fuzzy clustering approach to optimize SVDD parameters. Experiments on the brain data set III for motor imagery problem in BCI Competition II were conducted to compare performance of SVDD and multi-sphere SVDD.

Original language	English
Title of host publication	2012 Fourth International Conference on Communications and Electronics (ICCE)
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	318-321
Number of pages	4
ISBN (Print)	9781467324939
DOIs	https://doi.org/10.1109/CCE.2012.6315920
Publication status	Published - 2012
Externally published	Yes
Event	International Conference on Communications and Electronics (HUT-ICCE) 2012 - Hue, Vietnam Duration: 1 Aug 2012 → 3 Aug 2012 Conference number: 4th https://ieeexplore.ieee.org/xpl/conhome/6307954/proceeding (Proceedings)

Conference

Conference	International Conference on Communications and Electronics (HUT-ICCE) 2012
Abbreviated title	HUT-ICCE 2012
Country/Territory	Vietnam
City	Hue
Period	1/08/12 → 3/08/12
Internet address	https://ieeexplore.ieee.org/xpl/conhome/6307954/proceeding (Proceedings)

Access to Document

10.1109/CCE.2012.6315920

Cite this

@inproceedings{4011cd1a83ed4f6e82e01f27a8ac4498,

title = "Multi-sphere support vector data description for brain-computer interface",

abstract = "Support vector data description (SVDD) has been widely used in pattern classification, however it does not provide high performance in brain-computer interface (BCI) classification problems since brain signals are noisy and chaotic. Brain data have distinct distributions and hence a hyper-sphere in SVDD could not well describe the data. We propose in this paper a multi-sphere approach to SVDD to have a better description for the brain data. We also propose a fuzzy clustering approach to optimize SVDD parameters. Experiments on the brain data set III for motor imagery problem in BCI Competition II were conducted to compare performance of SVDD and multi-sphere SVDD.",

author = "Phuoc Nguyen and Dat Tran and Trung Le and Tuan Hoang and Dharmendra Sharma",

year = "2012",

doi = "10.1109/CCE.2012.6315920",

language = "English",

isbn = "9781467324939",

pages = "318--321",

booktitle = "2012 Fourth International Conference on Communications and Electronics (ICCE)",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "International Conference on Communications and Electronics (HUT-ICCE) 2012, HUT-ICCE 2012 ; Conference date: 01-08-2012 Through 03-08-2012",

url = "https://ieeexplore.ieee.org/xpl/conhome/6307954/proceeding",

}

Nguyen, P, Tran, D, Le, T, Hoang, T & Sharma, D 2012, Multi-sphere support vector data description for brain-computer interface. in 2012 Fourth International Conference on Communications and Electronics (ICCE)., 6315920, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 318-321, International Conference on Communications and Electronics (HUT-ICCE) 2012, Hue, Vietnam, 1/08/12. https://doi.org/10.1109/CCE.2012.6315920

Multi-sphere support vector data description for brain-computer interface. / Nguyen, Phuoc; Tran, Dat; Le, Trung et al.

2012 Fourth International Conference on Communications and Electronics (ICCE). Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2012. p. 318-321 6315920.

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

TY - GEN

T1 - Multi-sphere support vector data description for brain-computer interface

AU - Nguyen, Phuoc

AU - Tran, Dat

AU - Le, Trung

AU - Hoang, Tuan

AU - Sharma, Dharmendra

N1 - Conference code: 4th

PY - 2012

Y1 - 2012

N2 - Support vector data description (SVDD) has been widely used in pattern classification, however it does not provide high performance in brain-computer interface (BCI) classification problems since brain signals are noisy and chaotic. Brain data have distinct distributions and hence a hyper-sphere in SVDD could not well describe the data. We propose in this paper a multi-sphere approach to SVDD to have a better description for the brain data. We also propose a fuzzy clustering approach to optimize SVDD parameters. Experiments on the brain data set III for motor imagery problem in BCI Competition II were conducted to compare performance of SVDD and multi-sphere SVDD.

AB - Support vector data description (SVDD) has been widely used in pattern classification, however it does not provide high performance in brain-computer interface (BCI) classification problems since brain signals are noisy and chaotic. Brain data have distinct distributions and hence a hyper-sphere in SVDD could not well describe the data. We propose in this paper a multi-sphere approach to SVDD to have a better description for the brain data. We also propose a fuzzy clustering approach to optimize SVDD parameters. Experiments on the brain data set III for motor imagery problem in BCI Competition II were conducted to compare performance of SVDD and multi-sphere SVDD.

UR - http://www.scopus.com/inward/record.url?scp=84869156123&partnerID=8YFLogxK

U2 - 10.1109/CCE.2012.6315920

DO - 10.1109/CCE.2012.6315920

M3 - Conference Paper

AN - SCOPUS:84869156123

SN - 9781467324939

SP - 318

EP - 321

BT - 2012 Fourth International Conference on Communications and Electronics (ICCE)

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

T2 - International Conference on Communications and Electronics (HUT-ICCE) 2012

Y2 - 1 August 2012 through 3 August 2012

ER -

Multi-sphere support vector data description for brain-computer interface

Abstract

Conference

Access to Document

Other files and links

Cite this