Enhancing Event-Related Potentials Based on Maximum a Posteriori Estimation with a Spatial Correlation Prior

Hayato MAKI; Tomoki TODA; Sakriani SAKTI; Graham NEUBIG; Satoshi NAKAMURA

doi:10.1587/transinf.2015CBP0008

Enhancing Event-Related Potentials Based on Maximum a Posteriori Estimation with a Spatial Correlation Prior

Hayato MAKI, Tomoki TODA, Sakriani SAKTI, Graham NEUBIG, Satoshi NAKAMURA

Full Text Views

0

Share
Cite this

Summary :

In this paper a new method for noise removal from single-trial event-related potentials recorded with a multi-channel electroencephalogram is addressed. An observed signal is separated into multiple signals with a multi-channel Wiener filter whose coefficients are estimated based on parameter estimation of a probabilistic generative model that locally models the amplitude of each separated signal in the time-frequency domain. Effectiveness of using prior information about covariance matrices to estimate model parameters and frequency dependent covariance matrices were shown through an experiment with a simulated event-related potential data set.

Publication: IEICE TRANSACTIONS on Information Vol.E99-D No.6 pp.1437-1446

Publication Date: 2016/06/01

Publicized: 2016/04/01

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2015CBP0008

Type of Manuscript: Special Section PAPER (Special Section on Human Cognition and Behavioral Science and Technology)

Category

Authors

Hayato MAKI
  Nara Institute of Science and Technology
Tomoki TODA
  Nara Institute of Science and Technology,Nagoya University
Sakriani SAKTI
  Nara Institute of Science and Technology
Graham NEUBIG
  Nara Institute of Science and Technology
Satoshi NAKAMURA
  Nara Institute of Science and Technology

Keyword

electroencephalogram (EEG), event-related potential (ERP), generative model, independent component analysis (ICA), Wiener filter, noise removal, Wishart distribution, spatial correlation prior

Cite this

Copy

Hayato MAKI, Tomoki TODA, Sakriani SAKTI, Graham NEUBIG, Satoshi NAKAMURA, "Enhancing Event-Related Potentials Based on Maximum a Posteriori Estimation with a Spatial Correlation Prior" in IEICE TRANSACTIONS on Information, vol. E99-D, no. 6, pp. 1437-1446, June 2016, doi: 10.1587/transinf.2015CBP0008.
Abstract: In this paper a new method for noise removal from single-trial event-related potentials recorded with a multi-channel electroencephalogram is addressed. An observed signal is separated into multiple signals with a multi-channel Wiener filter whose coefficients are estimated based on parameter estimation of a probabilistic generative model that locally models the amplitude of each separated signal in the time-frequency domain. Effectiveness of using prior information about covariance matrices to estimate model parameters and frequency dependent covariance matrices were shown through an experiment with a simulated event-related potential data set.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2015CBP0008/_p

Copy

@ARTICLE{e99-d_6_1437,
author={Hayato MAKI, Tomoki TODA, Sakriani SAKTI, Graham NEUBIG, Satoshi NAKAMURA, },
journal={IEICE TRANSACTIONS on Information},
title={Enhancing Event-Related Potentials Based on Maximum a Posteriori Estimation with a Spatial Correlation Prior},
year={2016},
volume={E99-D},
number={6},
pages={1437-1446},
abstract={In this paper a new method for noise removal from single-trial event-related potentials recorded with a multi-channel electroencephalogram is addressed. An observed signal is separated into multiple signals with a multi-channel Wiener filter whose coefficients are estimated based on parameter estimation of a probabilistic generative model that locally models the amplitude of each separated signal in the time-frequency domain. Effectiveness of using prior information about covariance matrices to estimate model parameters and frequency dependent covariance matrices were shown through an experiment with a simulated event-related potential data set.},
keywords={},
doi={10.1587/transinf.2015CBP0008},
ISSN={1745-1361},
month={June},}

Copy

TY - JOUR
TI - Enhancing Event-Related Potentials Based on Maximum a Posteriori Estimation with a Spatial Correlation Prior
T2 - IEICE TRANSACTIONS on Information
SP - 1437
EP - 1446
AU - Hayato MAKI
AU - Tomoki TODA
AU - Sakriani SAKTI
AU - Graham NEUBIG
AU - Satoshi NAKAMURA
PY - 2016
DO - 10.1587/transinf.2015CBP0008
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2016
AB - In this paper a new method for noise removal from single-trial event-related potentials recorded with a multi-channel electroencephalogram is addressed. An observed signal is separated into multiple signals with a multi-channel Wiener filter whose coefficients are estimated based on parameter estimation of a probabilistic generative model that locally models the amplitude of each separated signal in the time-frequency domain. Effectiveness of using prior information about covariance matrices to estimate model parameters and frequency dependent covariance matrices were shown through an experiment with a simulated event-related potential data set.
ER -