Enhancing unsupervised canonical correlation analysis-based frequency detection of SSVEPs by incorporating background EEG

Masaki Nakanishi, Yijun Wang, Yu Te Wang, Yasue Mitsukura, Tzyy Ping Jung

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

Steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) have potential to provide a fast communication channel between human brain and external devices. In SSVEP-based BCIs, Canonical Correlation Analysis (CCA) has been widely used to detect frequency-coded SSVEPs due to its high efficiency and robustness. However, the detectability of SSVEPs differs among frequencies due to a power-law distribution of the power spectra of spontaneous electroencephalogram (EEG) signals. This study proposed a new method based on the fact that changes of canonical correlation coefficients for SSVEPs and background EEG signals follow the same trend along frequency. The proposed method defined a normalized canonical correlation coefficient, the ratio of the canonical correlation coefficient for SSVEPs to the mean of the canonical correlation coefficients for background EEG signals, to enhance the frequency detection of SSVEPs. An SSVEP dataset from 13 subjects was used for comparing classification performance between the proposed method and the standard CCA method. Classification accuracy and simulated information transfer rates (ITR) suggest that, in an unsupervised way, the proposed method could considerably improve the frequency detection accuracy of SSVEPs with little computational effort.

Original languageEnglish
Title of host publication2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3053-3056
Number of pages4
ISBN (Print)9781424479290
DOIs
Publication statusPublished - 2014 Nov 2
Event2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014 - Chicago, United States
Duration: 2014 Aug 262014 Aug 30

Other

Other2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
CountryUnited States
CityChicago
Period14/8/2614/8/30

Fingerprint

Bioelectric potentials
Electroencephalography
Brain computer interface
Visual Evoked Potentials
Brain-Computer Interfaces
Power spectrum
Brain
Communication
Equipment and Supplies

ASJC Scopus subject areas

  • Health Informatics
  • Computer Science Applications
  • Biomedical Engineering

Cite this

Nakanishi, M., Wang, Y., Wang, Y. T., Mitsukura, Y., & Jung, T. P. (2014). Enhancing unsupervised canonical correlation analysis-based frequency detection of SSVEPs by incorporating background EEG. In 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014 (pp. 3053-3056). [6944267] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2014.6944267

Enhancing unsupervised canonical correlation analysis-based frequency detection of SSVEPs by incorporating background EEG. / Nakanishi, Masaki; Wang, Yijun; Wang, Yu Te; Mitsukura, Yasue; Jung, Tzyy Ping.

2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 3053-3056 6944267.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nakanishi, M, Wang, Y, Wang, YT, Mitsukura, Y & Jung, TP 2014, Enhancing unsupervised canonical correlation analysis-based frequency detection of SSVEPs by incorporating background EEG. in 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014., 6944267, Institute of Electrical and Electronics Engineers Inc., pp. 3053-3056, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014, Chicago, United States, 14/8/26. https://doi.org/10.1109/EMBC.2014.6944267
Nakanishi M, Wang Y, Wang YT, Mitsukura Y, Jung TP. Enhancing unsupervised canonical correlation analysis-based frequency detection of SSVEPs by incorporating background EEG. In 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 3053-3056. 6944267 https://doi.org/10.1109/EMBC.2014.6944267
Nakanishi, Masaki ; Wang, Yijun ; Wang, Yu Te ; Mitsukura, Yasue ; Jung, Tzyy Ping. / Enhancing unsupervised canonical correlation analysis-based frequency detection of SSVEPs by incorporating background EEG. 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 3053-3056
@inproceedings{a63f760a066d4130a8a957deaf833ed8,
title = "Enhancing unsupervised canonical correlation analysis-based frequency detection of SSVEPs by incorporating background EEG",
abstract = "Steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) have potential to provide a fast communication channel between human brain and external devices. In SSVEP-based BCIs, Canonical Correlation Analysis (CCA) has been widely used to detect frequency-coded SSVEPs due to its high efficiency and robustness. However, the detectability of SSVEPs differs among frequencies due to a power-law distribution of the power spectra of spontaneous electroencephalogram (EEG) signals. This study proposed a new method based on the fact that changes of canonical correlation coefficients for SSVEPs and background EEG signals follow the same trend along frequency. The proposed method defined a normalized canonical correlation coefficient, the ratio of the canonical correlation coefficient for SSVEPs to the mean of the canonical correlation coefficients for background EEG signals, to enhance the frequency detection of SSVEPs. An SSVEP dataset from 13 subjects was used for comparing classification performance between the proposed method and the standard CCA method. Classification accuracy and simulated information transfer rates (ITR) suggest that, in an unsupervised way, the proposed method could considerably improve the frequency detection accuracy of SSVEPs with little computational effort.",
author = "Masaki Nakanishi and Yijun Wang and Wang, {Yu Te} and Yasue Mitsukura and Jung, {Tzyy Ping}",
year = "2014",
month = "11",
day = "2",
doi = "10.1109/EMBC.2014.6944267",
language = "English",
isbn = "9781424479290",
pages = "3053--3056",
booktitle = "2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Enhancing unsupervised canonical correlation analysis-based frequency detection of SSVEPs by incorporating background EEG

AU - Nakanishi, Masaki

AU - Wang, Yijun

AU - Wang, Yu Te

AU - Mitsukura, Yasue

AU - Jung, Tzyy Ping

PY - 2014/11/2

Y1 - 2014/11/2

N2 - Steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) have potential to provide a fast communication channel between human brain and external devices. In SSVEP-based BCIs, Canonical Correlation Analysis (CCA) has been widely used to detect frequency-coded SSVEPs due to its high efficiency and robustness. However, the detectability of SSVEPs differs among frequencies due to a power-law distribution of the power spectra of spontaneous electroencephalogram (EEG) signals. This study proposed a new method based on the fact that changes of canonical correlation coefficients for SSVEPs and background EEG signals follow the same trend along frequency. The proposed method defined a normalized canonical correlation coefficient, the ratio of the canonical correlation coefficient for SSVEPs to the mean of the canonical correlation coefficients for background EEG signals, to enhance the frequency detection of SSVEPs. An SSVEP dataset from 13 subjects was used for comparing classification performance between the proposed method and the standard CCA method. Classification accuracy and simulated information transfer rates (ITR) suggest that, in an unsupervised way, the proposed method could considerably improve the frequency detection accuracy of SSVEPs with little computational effort.

AB - Steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) have potential to provide a fast communication channel between human brain and external devices. In SSVEP-based BCIs, Canonical Correlation Analysis (CCA) has been widely used to detect frequency-coded SSVEPs due to its high efficiency and robustness. However, the detectability of SSVEPs differs among frequencies due to a power-law distribution of the power spectra of spontaneous electroencephalogram (EEG) signals. This study proposed a new method based on the fact that changes of canonical correlation coefficients for SSVEPs and background EEG signals follow the same trend along frequency. The proposed method defined a normalized canonical correlation coefficient, the ratio of the canonical correlation coefficient for SSVEPs to the mean of the canonical correlation coefficients for background EEG signals, to enhance the frequency detection of SSVEPs. An SSVEP dataset from 13 subjects was used for comparing classification performance between the proposed method and the standard CCA method. Classification accuracy and simulated information transfer rates (ITR) suggest that, in an unsupervised way, the proposed method could considerably improve the frequency detection accuracy of SSVEPs with little computational effort.

UR - http://www.scopus.com/inward/record.url?scp=84929493229&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929493229&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2014.6944267

DO - 10.1109/EMBC.2014.6944267

M3 - Conference contribution

C2 - 25570635

AN - SCOPUS:84929493229

SN - 9781424479290

SP - 3053

EP - 3056

BT - 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -