Discriminative FilterBank selection and EEG information fusion for brain computer interface

Kavitha P. Thomas; Cuntai Guan; Chiew Tong Lau; A. P. Vinod

doi:10.1109/ISCAS.2009.5118044

Discriminative FilterBank selection and EEG information fusion for brain computer interface

Kavitha P. Thomas, Cuntai Guan, Chiew Tong Lau, A. P. Vinod

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

16 Citations (Scopus)

Abstract

Brain Computer Interface (BCI) provides a direct communication pathway between a human and an external device. In this paper, we propose a new 'Discriminative FilterBank Common Spatial Pattern (DFBCSP)' algorithm to select the subject-specific filters automatically during training for a motor imagery based BCI. The subject-specific filters are selected using the fisher ratio values of filtered Electroencephalogram (EEG) signal. The channel 'C3' alone could give sufficient information to select the discriminative filterbank for the proposed system. We have also explored the possibility of boosting the system performance by including dynamic temporal features. Fusion of static and dynamic features in the proposed DFBCSP frame work gave an average test accuracy of 92.44%, which is significantly better than conventional filterbank based Common Spatial Pattern algorithms.

Original language	English
Title of host publication	2009 IEEE International Symposium on Circuits and Systems, ISCAS 2009
Pages	1469-1472
Number of pages	4
DOIs	https://doi.org/10.1109/ISCAS.2009.5118044
Publication status	Published - 2009
Externally published	Yes
Event	2009 IEEE International Symposium on Circuits and Systems, ISCAS 2009 - Taipei, Taiwan, Province of China Duration: 24 May 2009 → 27 May 2009

Publication series

Name	Proceedings - IEEE International Symposium on Circuits and Systems
ISSN (Print)	0271-4310

Conference

Conference	2009 IEEE International Symposium on Circuits and Systems, ISCAS 2009
Country/Territory	Taiwan, Province of China
City	Taipei
Period	24/05/09 → 27/05/09

Access to Document

10.1109/ISCAS.2009.5118044

Cite this

Thomas, K. P., Guan, C., Lau, C. T., & Vinod, A. P. (2009). Discriminative FilterBank selection and EEG information fusion for brain computer interface. In 2009 IEEE International Symposium on Circuits and Systems, ISCAS 2009 (pp. 1469-1472). Article 5118044 (Proceedings - IEEE International Symposium on Circuits and Systems). https://doi.org/10.1109/ISCAS.2009.5118044

@inproceedings{16f43a1bc156451081c73fa565481565,

title = "Discriminative FilterBank selection and EEG information fusion for brain computer interface",

abstract = "Brain Computer Interface (BCI) provides a direct communication pathway between a human and an external device. In this paper, we propose a new 'Discriminative FilterBank Common Spatial Pattern (DFBCSP)' algorithm to select the subject-specific filters automatically during training for a motor imagery based BCI. The subject-specific filters are selected using the fisher ratio values of filtered Electroencephalogram (EEG) signal. The channel 'C3' alone could give sufficient information to select the discriminative filterbank for the proposed system. We have also explored the possibility of boosting the system performance by including dynamic temporal features. Fusion of static and dynamic features in the proposed DFBCSP frame work gave an average test accuracy of 92.44\%, which is significantly better than conventional filterbank based Common Spatial Pattern algorithms.",

author = "Thomas, \{Kavitha P.\} and Cuntai Guan and Lau, \{Chiew Tong\} and Vinod, \{A. P.\}",

year = "2009",

doi = "10.1109/ISCAS.2009.5118044",

language = "English",

isbn = "9781424438280",

series = "Proceedings - IEEE International Symposium on Circuits and Systems",

pages = "1469--1472",

booktitle = "2009 IEEE International Symposium on Circuits and Systems, ISCAS 2009",

note = "2009 IEEE International Symposium on Circuits and Systems, ISCAS 2009 ; Conference date: 24-05-2009 Through 27-05-2009",

}

Thomas, KP, Guan, C, Lau, CT & Vinod, AP 2009, Discriminative FilterBank selection and EEG information fusion for brain computer interface. in 2009 IEEE International Symposium on Circuits and Systems, ISCAS 2009., 5118044, Proceedings - IEEE International Symposium on Circuits and Systems, pp. 1469-1472, 2009 IEEE International Symposium on Circuits and Systems, ISCAS 2009, Taipei, Taiwan, Province of China, 24/05/09. https://doi.org/10.1109/ISCAS.2009.5118044

Discriminative FilterBank selection and EEG information fusion for brain computer interface. / Thomas, Kavitha P.; Guan, Cuntai; Lau, Chiew Tong et al.
2009 IEEE International Symposium on Circuits and Systems, ISCAS 2009. 2009. p. 1469-1472 5118044 (Proceedings - IEEE International Symposium on Circuits and Systems).

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

TY - GEN

T1 - Discriminative FilterBank selection and EEG information fusion for brain computer interface

AU - Thomas, Kavitha P.

AU - Guan, Cuntai

AU - Lau, Chiew Tong

AU - Vinod, A. P.

PY - 2009

Y1 - 2009

N2 - Brain Computer Interface (BCI) provides a direct communication pathway between a human and an external device. In this paper, we propose a new 'Discriminative FilterBank Common Spatial Pattern (DFBCSP)' algorithm to select the subject-specific filters automatically during training for a motor imagery based BCI. The subject-specific filters are selected using the fisher ratio values of filtered Electroencephalogram (EEG) signal. The channel 'C3' alone could give sufficient information to select the discriminative filterbank for the proposed system. We have also explored the possibility of boosting the system performance by including dynamic temporal features. Fusion of static and dynamic features in the proposed DFBCSP frame work gave an average test accuracy of 92.44%, which is significantly better than conventional filterbank based Common Spatial Pattern algorithms.

AB - Brain Computer Interface (BCI) provides a direct communication pathway between a human and an external device. In this paper, we propose a new 'Discriminative FilterBank Common Spatial Pattern (DFBCSP)' algorithm to select the subject-specific filters automatically during training for a motor imagery based BCI. The subject-specific filters are selected using the fisher ratio values of filtered Electroencephalogram (EEG) signal. The channel 'C3' alone could give sufficient information to select the discriminative filterbank for the proposed system. We have also explored the possibility of boosting the system performance by including dynamic temporal features. Fusion of static and dynamic features in the proposed DFBCSP frame work gave an average test accuracy of 92.44%, which is significantly better than conventional filterbank based Common Spatial Pattern algorithms.

UR - http://www.scopus.com/inward/record.url?scp=70350156900&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.2009.5118044

DO - 10.1109/ISCAS.2009.5118044

M3 - Conference Paper published in a book

AN - SCOPUS:70350156900

SN - 9781424438280

T3 - Proceedings - IEEE International Symposium on Circuits and Systems

SP - 1469

EP - 1472

BT - 2009 IEEE International Symposium on Circuits and Systems, ISCAS 2009

T2 - 2009 IEEE International Symposium on Circuits and Systems, ISCAS 2009

Y2 - 24 May 2009 through 27 May 2009

ER -

Discriminative FilterBank selection and EEG information fusion for brain computer interface

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this