Graph Neural Network with Multilevel Feature Fusion for EEG based Brain-Computer Interface

Youngchul Kwak; Woo Jin Song; Seong Eun Kim

doi:10.1109/ICCE-Asia49877.2020.9276983

Graph Neural Network with Multilevel Feature Fusion for EEG based Brain-Computer Interface

Youngchul Kwak, Woo Jin Song, Seong Eun Kim

Dept. of Applied Artificial Intelligence

Pohang University of Science and Technology

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

4 Scopus citations

Abstract

The brain-computer interface (BCI) system provides information exchanges between neural signals containing the user's intention and device control signals. In this paper, we propose a graph neural network (GNN) with a multilevel feature fusion structure for high-performance BCI systems. Since the proposed structure can exploit both local and global neural information, the decoding accuracy greatly increases. Experimental results show that the original GNN outperforms conventional algorithms. Furthermore, the proposed multilevel feature fusion method dramatically enhances the performance of conventional GNN algorithms.

Original language	English
Title of host publication	2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728161648
DOIs	https://doi.org/10.1109/ICCE-Asia49877.2020.9276983
State	Published - 1 Nov 2020
Event	2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020 - Seoul, Korea, Republic of Duration: 1 Nov 2020 → 3 Nov 2020

Publication series

Name	2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020

Conference

Conference	2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020
Country/Territory	Korea, Republic of
City	Seoul
Period	1/11/20 → 3/11/20

Keywords

Brain-computer interface (BCI)
electroencephalogram (EEG)
graph neural network
motor imagery
multilevel feature fusion

Access to Document

10.1109/ICCE-Asia49877.2020.9276983

Cite this

Kwak, Y., Song, W. J., & Kim, S. E. (2020). Graph Neural Network with Multilevel Feature Fusion for EEG based Brain-Computer Interface. In 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020 Article 9276983 (2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE-Asia49877.2020.9276983

Kwak, Youngchul ; Song, Woo Jin ; Kim, Seong Eun. / Graph Neural Network with Multilevel Feature Fusion for EEG based Brain-Computer Interface. 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020. Institute of Electrical and Electronics Engineers Inc., 2020. (2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020).

@inproceedings{1cadc8330ce044cd9d580395517fc7d1,

title = "Graph Neural Network with Multilevel Feature Fusion for EEG based Brain-Computer Interface",

abstract = "The brain-computer interface (BCI) system provides information exchanges between neural signals containing the user's intention and device control signals. In this paper, we propose a graph neural network (GNN) with a multilevel feature fusion structure for high-performance BCI systems. Since the proposed structure can exploit both local and global neural information, the decoding accuracy greatly increases. Experimental results show that the original GNN outperforms conventional algorithms. Furthermore, the proposed multilevel feature fusion method dramatically enhances the performance of conventional GNN algorithms.",

keywords = "Brain-computer interface (BCI), electroencephalogram (EEG), graph neural network, motor imagery, multilevel feature fusion",

author = "Youngchul Kwak and Song, \{Woo Jin\} and Kim, \{Seong Eun\}",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020 ; Conference date: 01-11-2020 Through 03-11-2020",

year = "2020",

month = nov,

day = "1",

doi = "10.1109/ICCE-Asia49877.2020.9276983",

language = "English",

series = "2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020",

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

booktitle = "2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020",

}

Kwak, Y, Song, WJ & Kim, SE 2020, Graph Neural Network with Multilevel Feature Fusion for EEG based Brain-Computer Interface. in 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020., 9276983, 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020, Institute of Electrical and Electronics Engineers Inc., 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020, Seoul, Korea, Republic of, 1/11/20. https://doi.org/10.1109/ICCE-Asia49877.2020.9276983

Graph Neural Network with Multilevel Feature Fusion for EEG based Brain-Computer Interface. / Kwak, Youngchul; Song, Woo Jin; Kim, Seong Eun.
2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020. Institute of Electrical and Electronics Engineers Inc., 2020. 9276983 (2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020).

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

TY - GEN

T1 - Graph Neural Network with Multilevel Feature Fusion for EEG based Brain-Computer Interface

AU - Kwak, Youngchul

AU - Song, Woo Jin

AU - Kim, Seong Eun

PY - 2020/11/1

Y1 - 2020/11/1

N2 - The brain-computer interface (BCI) system provides information exchanges between neural signals containing the user's intention and device control signals. In this paper, we propose a graph neural network (GNN) with a multilevel feature fusion structure for high-performance BCI systems. Since the proposed structure can exploit both local and global neural information, the decoding accuracy greatly increases. Experimental results show that the original GNN outperforms conventional algorithms. Furthermore, the proposed multilevel feature fusion method dramatically enhances the performance of conventional GNN algorithms.

AB - The brain-computer interface (BCI) system provides information exchanges between neural signals containing the user's intention and device control signals. In this paper, we propose a graph neural network (GNN) with a multilevel feature fusion structure for high-performance BCI systems. Since the proposed structure can exploit both local and global neural information, the decoding accuracy greatly increases. Experimental results show that the original GNN outperforms conventional algorithms. Furthermore, the proposed multilevel feature fusion method dramatically enhances the performance of conventional GNN algorithms.

KW - Brain-computer interface (BCI)

KW - electroencephalogram (EEG)

KW - graph neural network

KW - motor imagery

KW - multilevel feature fusion

UR - http://www.scopus.com/inward/record.url?scp=85098868895&partnerID=8YFLogxK

U2 - 10.1109/ICCE-Asia49877.2020.9276983

DO - 10.1109/ICCE-Asia49877.2020.9276983

M3 - Conference contribution

AN - SCOPUS:85098868895

T3 - 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020

BT - 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020

Y2 - 1 November 2020 through 3 November 2020

ER -

Kwak Y, Song WJ, Kim SE. Graph Neural Network with Multilevel Feature Fusion for EEG based Brain-Computer Interface. In 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020. Institute of Electrical and Electronics Engineers Inc. 2020. 9276983. (2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020). doi: 10.1109/ICCE-Asia49877.2020.9276983

Graph Neural Network with Multilevel Feature Fusion for EEG based Brain-Computer Interface

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this