Performance of a Bayesian-Network-Model-Based BCI Using Single-Trial EEGs

Maiko SAKAMOTO; Hiromi YAMAGUCHI; Toshimasa YAMAZAKI; Ken-ichi KAMIJO; Takahiro YAMANOI

doi:10.1587/transinf.2015EDP7017

Performance of a Bayesian-Network-Model-Based BCI Using Single-Trial EEGs

Maiko SAKAMOTO, Hiromi YAMAGUCHI, Toshimasa YAMAZAKI, Ken-ichi KAMIJO, Takahiro YAMANOI

Full Text Views

0

Share
Cite this

Summary :

We have proposed a new Bayesian network model (BNM) framework for single-trial-EEG-based Brain-Computer Interface (BCI). The BNM was constructed in the following. In order to discriminate between left and right hands to be imaged from single-trial EEGs measured during the movement imagery tasks, the BNM has the following three steps: (1) independent component analysis (ICA) for each of the single-trial EEGs; (2) equivalent current dipole source localization (ECDL) for projections of each IC on the scalp surface; (3) BNM construction using the ECDL results. The BNMs were composed of nodes and edges which correspond to the brain sites where ECDs are located, and their connections, respectively. The connections were quantified as node activities by conditional probabilities calculated by probabilistic inference in each trial. The BNM-based BCI is compared with the common spatial pattern (CSP) method. For ten healthy subjects, there was no significant difference between the two methods. Our BNM might reflect each subject's strategy for task execution.

Publication: IEICE TRANSACTIONS on Information Vol.E98-D No.11 pp.1976-1981

Publication Date: 2015/11/01

Publicized: 2015/08/06

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2015EDP7017

Type of Manuscript: PAPER

Category: Biocybernetics, Neurocomputing

Authors

Maiko SAKAMOTO
  Hitachi Public System Service Co. Ltd.
Hiromi YAMAGUCHI
  NEC Corp.
Toshimasa YAMAZAKI
  Kyushu Institute of Technology
Ken-ichi KAMIJO
  NEC Corp.
Takahiro YAMANOI
  Hokkai Gakuen University

Keyword

BCI, Bayesian network, single-trial EEG, ICA, ECDL

Cite this

Copy

Maiko SAKAMOTO, Hiromi YAMAGUCHI, Toshimasa YAMAZAKI, Ken-ichi KAMIJO, Takahiro YAMANOI, "Performance of a Bayesian-Network-Model-Based BCI Using Single-Trial EEGs" in IEICE TRANSACTIONS on Information, vol. E98-D, no. 11, pp. 1976-1981, November 2015, doi: 10.1587/transinf.2015EDP7017.
Abstract: We have proposed a new Bayesian network model (BNM) framework for single-trial-EEG-based Brain-Computer Interface (BCI). The BNM was constructed in the following. In order to discriminate between left and right hands to be imaged from single-trial EEGs measured during the movement imagery tasks, the BNM has the following three steps: (1) independent component analysis (ICA) for each of the single-trial EEGs; (2) equivalent current dipole source localization (ECDL) for projections of each IC on the scalp surface; (3) BNM construction using the ECDL results. The BNMs were composed of nodes and edges which correspond to the brain sites where ECDs are located, and their connections, respectively. The connections were quantified as node activities by conditional probabilities calculated by probabilistic inference in each trial. The BNM-based BCI is compared with the common spatial pattern (CSP) method. For ten healthy subjects, there was no significant difference between the two methods. Our BNM might reflect each subject's strategy for task execution.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2015EDP7017/_p

Copy

@ARTICLE{e98-d_11_1976,
author={Maiko SAKAMOTO, Hiromi YAMAGUCHI, Toshimasa YAMAZAKI, Ken-ichi KAMIJO, Takahiro YAMANOI, },
journal={IEICE TRANSACTIONS on Information},
title={Performance of a Bayesian-Network-Model-Based BCI Using Single-Trial EEGs},
year={2015},
volume={E98-D},
number={11},
pages={1976-1981},
abstract={We have proposed a new Bayesian network model (BNM) framework for single-trial-EEG-based Brain-Computer Interface (BCI). The BNM was constructed in the following. In order to discriminate between left and right hands to be imaged from single-trial EEGs measured during the movement imagery tasks, the BNM has the following three steps: (1) independent component analysis (ICA) for each of the single-trial EEGs; (2) equivalent current dipole source localization (ECDL) for projections of each IC on the scalp surface; (3) BNM construction using the ECDL results. The BNMs were composed of nodes and edges which correspond to the brain sites where ECDs are located, and their connections, respectively. The connections were quantified as node activities by conditional probabilities calculated by probabilistic inference in each trial. The BNM-based BCI is compared with the common spatial pattern (CSP) method. For ten healthy subjects, there was no significant difference between the two methods. Our BNM might reflect each subject's strategy for task execution.},
keywords={},
doi={10.1587/transinf.2015EDP7017},
ISSN={1745-1361},
month={November},}

Copy

TY - JOUR
TI - Performance of a Bayesian-Network-Model-Based BCI Using Single-Trial EEGs
T2 - IEICE TRANSACTIONS on Information
SP - 1976
EP - 1981
AU - Maiko SAKAMOTO
AU - Hiromi YAMAGUCHI
AU - Toshimasa YAMAZAKI
AU - Ken-ichi KAMIJO
AU - Takahiro YAMANOI
PY - 2015
DO - 10.1587/transinf.2015EDP7017
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2015
AB - We have proposed a new Bayesian network model (BNM) framework for single-trial-EEG-based Brain-Computer Interface (BCI). The BNM was constructed in the following. In order to discriminate between left and right hands to be imaged from single-trial EEGs measured during the movement imagery tasks, the BNM has the following three steps: (1) independent component analysis (ICA) for each of the single-trial EEGs; (2) equivalent current dipole source localization (ECDL) for projections of each IC on the scalp surface; (3) BNM construction using the ECDL results. The BNMs were composed of nodes and edges which correspond to the brain sites where ECDs are located, and their connections, respectively. The connections were quantified as node activities by conditional probabilities calculated by probabilistic inference in each trial. The BNM-based BCI is compared with the common spatial pattern (CSP) method. For ten healthy subjects, there was no significant difference between the two methods. Our BNM might reflect each subject's strategy for task execution.
ER -