An empirical suggestion for collaborative learning in motor imagery-based BCIs

Eun Song Kang; Bum Chae Kim; Heung Il Suk

doi:10.1109/IWW-BCI.2016.7457450

An empirical suggestion for collaborative learning in motor imagery-based BCIs

Eun Song Kang, Bum Chae Kim, Heung Il Suk

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

In modern Brain-Computer Interfaces (BCIs), it usually requires the so-called calibration session to adapt a BCI model, e.g., spatial filter and classifier, to a target subject before use, due to high intra- and inter-subject variability in brain signals. From a practical perspective, this is one of the main challenges that should be resolved, thus motivating to use information from other subjects via collaborative learning. In this study, we analyze the effects of utilizing data from other subjects and identify whether generic patterns, which are informative for general BCI, exist by conducting experiments on the BCI Competition IV-IIa dataset. Based on our two experiments of naïve inter-subject BCI and generic pattern-guided inter-subject BCI, we suggest utilizing 1) categorical information of training samples and 2) samples of generic patterns for generalization of a BCI model.

Original language	English
Title of host publication	4th International Winter Conference on Brain-Computer Interface, BCI 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781467378413
DOIs	https://doi.org/10.1109/IWW-BCI.2016.7457450
Publication status	Published - 2016 Apr 20
Event	4th International Winter Conference on Brain-Computer Interface, BCI 2016 - Gangwon Province, Korea, Republic of Duration: 2016 Feb 22 → 2016 Feb 24

Publication series

Name	4th International Winter Conference on Brain-Computer Interface, BCI 2016

Other

Other	4th International Winter Conference on Brain-Computer Interface, BCI 2016
Country/Territory	Korea, Republic of
City	Gangwon Province
Period	16/2/22 → 16/2/24

Bibliographical note

Funding Information:
This work was supported by Institute for Information and communications Technology Promotion (IITP) grant funded by the Korea government (MSIP) (No. B0101-15-0307, Basic Software Research in Human-level Lifelong Machine Learning (Machine Learning Center)).

Publisher Copyright:
© 2016 IEEE.

Copyright:
Copyright 2016 Elsevier B.V., All rights reserved.

Keywords

Brain-Computer Interface (BCI)
Calibration
Collaborative Filtering
Common Spatial Pattern
Zero-Training

ASJC Scopus subject areas

Human-Computer Interaction

Access to Document

10.1109/IWW-BCI.2016.7457450

Cite this

Kang, E. S., Kim, B. C., & Suk, H. I. (2016). An empirical suggestion for collaborative learning in motor imagery-based BCIs. In 4th International Winter Conference on Brain-Computer Interface, BCI 2016 Article 7457450 (4th International Winter Conference on Brain-Computer Interface, BCI 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IWW-BCI.2016.7457450

An empirical suggestion for collaborative learning in motor imagery-based BCIs. / Kang, Eun Song; Kim, Bum Chae; Suk, Heung Il.
4th International Winter Conference on Brain-Computer Interface, BCI 2016. Institute of Electrical and Electronics Engineers Inc., 2016. 7457450 (4th International Winter Conference on Brain-Computer Interface, BCI 2016).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kang, ES, Kim, BC & Suk, HI 2016, An empirical suggestion for collaborative learning in motor imagery-based BCIs. in 4th International Winter Conference on Brain-Computer Interface, BCI 2016., 7457450, 4th International Winter Conference on Brain-Computer Interface, BCI 2016, Institute of Electrical and Electronics Engineers Inc., 4th International Winter Conference on Brain-Computer Interface, BCI 2016, Gangwon Province, Korea, Republic of, 16/2/22. https://doi.org/10.1109/IWW-BCI.2016.7457450

@inproceedings{5c8033912e034759983ee23a219c2d82,

title = "An empirical suggestion for collaborative learning in motor imagery-based BCIs",

abstract = "In modern Brain-Computer Interfaces (BCIs), it usually requires the so-called calibration session to adapt a BCI model, e.g., spatial filter and classifier, to a target subject before use, due to high intra- and inter-subject variability in brain signals. From a practical perspective, this is one of the main challenges that should be resolved, thus motivating to use information from other subjects via collaborative learning. In this study, we analyze the effects of utilizing data from other subjects and identify whether generic patterns, which are informative for general BCI, exist by conducting experiments on the BCI Competition IV-IIa dataset. Based on our two experiments of na{\"i}ve inter-subject BCI and generic pattern-guided inter-subject BCI, we suggest utilizing 1) categorical information of training samples and 2) samples of generic patterns for generalization of a BCI model.",

keywords = "Brain-Computer Interface (BCI), Calibration, Collaborative Filtering, Common Spatial Pattern, Zero-Training",

author = "Kang, {Eun Song} and Kim, {Bum Chae} and Suk, {Heung Il}",

note = "Funding Information: This work was supported by Institute for Information and communications Technology Promotion (IITP) grant funded by the Korea government (MSIP) (No. B0101-15-0307, Basic Software Research in Human-level Lifelong Machine Learning (Machine Learning Center)). Publisher Copyright: {\textcopyright} 2016 IEEE. Copyright: Copyright 2016 Elsevier B.V., All rights reserved.; 4th International Winter Conference on Brain-Computer Interface, BCI 2016 ; Conference date: 22-02-2016 Through 24-02-2016",

year = "2016",

month = apr,

day = "20",

doi = "10.1109/IWW-BCI.2016.7457450",

language = "English",

series = "4th International Winter Conference on Brain-Computer Interface, BCI 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "4th International Winter Conference on Brain-Computer Interface, BCI 2016",

}

TY - GEN

T1 - An empirical suggestion for collaborative learning in motor imagery-based BCIs

AU - Kang, Eun Song

AU - Kim, Bum Chae

AU - Suk, Heung Il

N1 - Funding Information: This work was supported by Institute for Information and communications Technology Promotion (IITP) grant funded by the Korea government (MSIP) (No. B0101-15-0307, Basic Software Research in Human-level Lifelong Machine Learning (Machine Learning Center)). Publisher Copyright: © 2016 IEEE. Copyright: Copyright 2016 Elsevier B.V., All rights reserved.

PY - 2016/4/20

Y1 - 2016/4/20

N2 - In modern Brain-Computer Interfaces (BCIs), it usually requires the so-called calibration session to adapt a BCI model, e.g., spatial filter and classifier, to a target subject before use, due to high intra- and inter-subject variability in brain signals. From a practical perspective, this is one of the main challenges that should be resolved, thus motivating to use information from other subjects via collaborative learning. In this study, we analyze the effects of utilizing data from other subjects and identify whether generic patterns, which are informative for general BCI, exist by conducting experiments on the BCI Competition IV-IIa dataset. Based on our two experiments of naïve inter-subject BCI and generic pattern-guided inter-subject BCI, we suggest utilizing 1) categorical information of training samples and 2) samples of generic patterns for generalization of a BCI model.

AB - In modern Brain-Computer Interfaces (BCIs), it usually requires the so-called calibration session to adapt a BCI model, e.g., spatial filter and classifier, to a target subject before use, due to high intra- and inter-subject variability in brain signals. From a practical perspective, this is one of the main challenges that should be resolved, thus motivating to use information from other subjects via collaborative learning. In this study, we analyze the effects of utilizing data from other subjects and identify whether generic patterns, which are informative for general BCI, exist by conducting experiments on the BCI Competition IV-IIa dataset. Based on our two experiments of naïve inter-subject BCI and generic pattern-guided inter-subject BCI, we suggest utilizing 1) categorical information of training samples and 2) samples of generic patterns for generalization of a BCI model.

KW - Brain-Computer Interface (BCI)

KW - Calibration

KW - Collaborative Filtering

KW - Common Spatial Pattern

KW - Zero-Training

UR - http://www.scopus.com/inward/record.url?scp=84969222331&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84969222331&partnerID=8YFLogxK

U2 - 10.1109/IWW-BCI.2016.7457450

DO - 10.1109/IWW-BCI.2016.7457450

M3 - Conference contribution

AN - SCOPUS:84969222331

T3 - 4th International Winter Conference on Brain-Computer Interface, BCI 2016

BT - 4th International Winter Conference on Brain-Computer Interface, BCI 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 4th International Winter Conference on Brain-Computer Interface, BCI 2016

Y2 - 22 February 2016 through 24 February 2016

ER -

An empirical suggestion for collaborative learning in motor imagery-based BCIs

Abstract

Publication series

Other

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this