Predictive-spectral-spatial preprocessing for a multiclass brain-computer interface

Damien Coyle; Abdul Satti; T. M. McGinnity

doi:10.1109/IJCNN.2010.5596756

Predictive-spectral-spatial preprocessing for a multiclass brain-computer interface

Damien Coyle, Abdul Satti, T. M. McGinnity

Ulster University

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

6 Citations (SciVal)

Abstract

Recent work has shown that combining prediction based preprocessing based on neural-time-series-prediction-preprocessing (NTSPP) along with spectral filtering (SF) and common-spatial patterns (CSP) can significantly improve the performance of a motor imagery based brain-computer interface (BCI) involving two classes. This paper illustrates how these performance improvements can be extended to a 4 class motor imagery BCI with between 2 and 22 channels. The results show that this combination of preprocessing techniques can significantly outperform any of methods operating independently and that NTSPP can reduce the number of electrodes required based on a comparison of results from 2, 3 and multichannel data.

Original language	English
Title of host publication	The 2010 International Joint Conference on Neural Networks (IJCNN)
Place of Publication	U. S. A.
Publisher	IEEE Computational Intelligence Society
Pages	3347-3364
Number of pages	18
ISBN (Electronic)	9781424469185
ISBN (Print)	9781424469161
DOIs	https://doi.org/10.1109/IJCNN.2010.5596756
Publication status	Published - 23 Jul 2010

Bibliographical note

the International Joint Conference on Neural Networks ; Conference date: 01-01-2010

Access to Document

10.1109/IJCNN.2010.5596756

Cite this

Predictive-spectral-spatial preprocessing for a multiclass brain-computer interface. / Coyle, Damien; Satti, Abdul; McGinnity, T. M.
The 2010 International Joint Conference on Neural Networks (IJCNN). U. S. A.: IEEE Computational Intelligence Society, 2010. p. 3347-3364.

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

@inproceedings{fedb9a6405b34a26b7d1dd4187f12d32,

title = "Predictive-spectral-spatial preprocessing for a multiclass brain-computer interface",

abstract = "Recent work has shown that combining prediction based preprocessing based on neural-time-series-prediction-preprocessing (NTSPP) along with spectral filtering (SF) and common-spatial patterns (CSP) can significantly improve the performance of a motor imagery based brain-computer interface (BCI) involving two classes. This paper illustrates how these performance improvements can be extended to a 4 class motor imagery BCI with between 2 and 22 channels. The results show that this combination of preprocessing techniques can significantly outperform any of methods operating independently and that NTSPP can reduce the number of electrodes required based on a comparison of results from 2, 3 and multichannel data.",

author = "Damien Coyle and Abdul Satti and McGinnity, {T. M.}",

note = "the International Joint Conference on Neural Networks ; Conference date: 01-01-2010",

year = "2010",

month = jul,

day = "23",

doi = "10.1109/IJCNN.2010.5596756",

language = "English",

isbn = "9781424469161",

pages = "3347--3364",

booktitle = "The 2010 International Joint Conference on Neural Networks (IJCNN)",

publisher = "IEEE Computational Intelligence Society",

}

TY - GEN

T1 - Predictive-spectral-spatial preprocessing for a multiclass brain-computer interface

AU - Coyle, Damien

AU - Satti, Abdul

AU - McGinnity, T. M.

N1 - the International Joint Conference on Neural Networks ; Conference date: 01-01-2010

PY - 2010/7/23

Y1 - 2010/7/23

N2 - Recent work has shown that combining prediction based preprocessing based on neural-time-series-prediction-preprocessing (NTSPP) along with spectral filtering (SF) and common-spatial patterns (CSP) can significantly improve the performance of a motor imagery based brain-computer interface (BCI) involving two classes. This paper illustrates how these performance improvements can be extended to a 4 class motor imagery BCI with between 2 and 22 channels. The results show that this combination of preprocessing techniques can significantly outperform any of methods operating independently and that NTSPP can reduce the number of electrodes required based on a comparison of results from 2, 3 and multichannel data.

AB - Recent work has shown that combining prediction based preprocessing based on neural-time-series-prediction-preprocessing (NTSPP) along with spectral filtering (SF) and common-spatial patterns (CSP) can significantly improve the performance of a motor imagery based brain-computer interface (BCI) involving two classes. This paper illustrates how these performance improvements can be extended to a 4 class motor imagery BCI with between 2 and 22 channels. The results show that this combination of preprocessing techniques can significantly outperform any of methods operating independently and that NTSPP can reduce the number of electrodes required based on a comparison of results from 2, 3 and multichannel data.

U2 - 10.1109/IJCNN.2010.5596756

DO - 10.1109/IJCNN.2010.5596756

M3 - Chapter in a published conference proceeding

SN - 9781424469161

SP - 3347

EP - 3364

BT - The 2010 International Joint Conference on Neural Networks (IJCNN)

PB - IEEE Computational Intelligence Society

CY - U. S. A.

ER -

Predictive-spectral-spatial preprocessing for a multiclass brain-computer interface

Abstract

Bibliographical note

Access to Document

Fingerprint

Cite this