Across-subject estimation of 3-back task performance using EEG signals

Jinsoo Kim; Min Ki Kim; Christian Wallraven; Sung Phil Kim

doi:10.1109/CIBCI.2014.7007785

Across-subject estimation of 3-back task performance using EEG signals

Jinsoo Kim, Min Ki Kim, Christian Wallraven, Sung Phil Kim

Department of Brain and Cognitive Engineering

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

Abstract

This study was aimed at estimating subjects' 3-back working memory task error rate using electroencephalogram (EEG) signals. Firstly, spatio-temporal band power features were selected based on statistical significance of across-subject correlation with the task error rate. Method-wise, ensemble network model was adopted where multiple artificial neural networks were trained independently and produced separate estimates to be later on aggregated to form a single estimated value. The task error rate of all subjects were estimated in a leave-one-out cross-validation scheme. While a simple linear method underperformed, the proposed model successfully obtained highly accurate estimates despite being restrained by very small sample size.

Original language	English
Title of host publication	IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIBCI 2014
Subtitle of host publication	2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	5-9
Number of pages	5
ISBN (Electronic)	9781479945443
DOIs	https://doi.org/10.1109/CIBCI.2014.7007785
Publication status	Published - 2015 Jan 12
Event	2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, CIBCI 2014 - Orlando, United States Duration: 2014 Dec 9 → 2014 Dec 12

Publication series

Name	IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIBCI 2014: 2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, Proceedings

Other

Other	2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, CIBCI 2014
Country/Territory	United States
City	Orlando
Period	14/12/9 → 14/12/12

Keywords

Artificial neural network
Committee of machines
EEG
N-back task
Network ensemble

ASJC Scopus subject areas

Computational Theory and Mathematics
Artificial Intelligence
Computer Science Applications

Access to Document

10.1109/CIBCI.2014.7007785

Cite this

Kim, J., Kim, M. K., Wallraven, C., & Kim, S. P. (2015). Across-subject estimation of 3-back task performance using EEG signals. In IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIBCI 2014: 2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, Proceedings (pp. 5-9). Article 7007785 (IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIBCI 2014: 2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CIBCI.2014.7007785

Across-subject estimation of 3-back task performance using EEG signals. / Kim, Jinsoo; Kim, Min Ki; Wallraven, Christian et al.
IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIBCI 2014: 2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. p. 5-9 7007785 (IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIBCI 2014: 2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, Proceedings).

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

Kim, J, Kim, MK, Wallraven, C & Kim, SP 2015, Across-subject estimation of 3-back task performance using EEG signals. in IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIBCI 2014: 2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, Proceedings., 7007785, IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIBCI 2014: 2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 5-9, 2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, CIBCI 2014, Orlando, United States, 14/12/9. https://doi.org/10.1109/CIBCI.2014.7007785

Kim J, Kim MK, Wallraven C, Kim SP. Across-subject estimation of 3-back task performance using EEG signals. In IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIBCI 2014: 2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2015. p. 5-9. 7007785. (IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIBCI 2014: 2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, Proceedings). doi: 10.1109/CIBCI.2014.7007785

Kim, Jinsoo ; Kim, Min Ki ; Wallraven, Christian et al. / Across-subject estimation of 3-back task performance using EEG signals. IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIBCI 2014: 2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 5-9 (IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIBCI 2014: 2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, Proceedings).

@inproceedings{69d2238263be4cc9b2d618d994fee85a,

title = "Across-subject estimation of 3-back task performance using EEG signals",

abstract = "This study was aimed at estimating subjects' 3-back working memory task error rate using electroencephalogram (EEG) signals. Firstly, spatio-temporal band power features were selected based on statistical significance of across-subject correlation with the task error rate. Method-wise, ensemble network model was adopted where multiple artificial neural networks were trained independently and produced separate estimates to be later on aggregated to form a single estimated value. The task error rate of all subjects were estimated in a leave-one-out cross-validation scheme. While a simple linear method underperformed, the proposed model successfully obtained highly accurate estimates despite being restrained by very small sample size.",

keywords = "Artificial neural network, Committee of machines, EEG, N-back task, Network ensemble",

author = "Jinsoo Kim and Kim, {Min Ki} and Christian Wallraven and Kim, {Sung Phil}",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, CIBCI 2014 ; Conference date: 09-12-2014 Through 12-12-2014",

year = "2015",

month = jan,

day = "12",

doi = "10.1109/CIBCI.2014.7007785",

language = "English",

series = "IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIBCI 2014: 2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, Proceedings",

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

pages = "5--9",

booktitle = "IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIBCI 2014",

}

TY - GEN

T1 - Across-subject estimation of 3-back task performance using EEG signals

AU - Kim, Jinsoo

AU - Kim, Min Ki

AU - Wallraven, Christian

AU - Kim, Sung Phil

PY - 2015/1/12

Y1 - 2015/1/12

N2 - This study was aimed at estimating subjects' 3-back working memory task error rate using electroencephalogram (EEG) signals. Firstly, spatio-temporal band power features were selected based on statistical significance of across-subject correlation with the task error rate. Method-wise, ensemble network model was adopted where multiple artificial neural networks were trained independently and produced separate estimates to be later on aggregated to form a single estimated value. The task error rate of all subjects were estimated in a leave-one-out cross-validation scheme. While a simple linear method underperformed, the proposed model successfully obtained highly accurate estimates despite being restrained by very small sample size.

AB - This study was aimed at estimating subjects' 3-back working memory task error rate using electroencephalogram (EEG) signals. Firstly, spatio-temporal band power features were selected based on statistical significance of across-subject correlation with the task error rate. Method-wise, ensemble network model was adopted where multiple artificial neural networks were trained independently and produced separate estimates to be later on aggregated to form a single estimated value. The task error rate of all subjects were estimated in a leave-one-out cross-validation scheme. While a simple linear method underperformed, the proposed model successfully obtained highly accurate estimates despite being restrained by very small sample size.

KW - Artificial neural network

KW - Committee of machines

KW - EEG

KW - N-back task

KW - Network ensemble

UR - http://www.scopus.com/inward/record.url?scp=84922979729&partnerID=8YFLogxK

U2 - 10.1109/CIBCI.2014.7007785

DO - 10.1109/CIBCI.2014.7007785

M3 - Conference contribution

AN - SCOPUS:84922979729

T3 - IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIBCI 2014: 2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, Proceedings

SP - 5

EP - 9

BT - IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIBCI 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces, CIBCI 2014

Y2 - 9 December 2014 through 12 December 2014

ER -

Across-subject estimation of 3-back task performance using EEG signals

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this