A Hybrid EEG-fNIRS Brain-Computer Interface Based on Dynamic Functional Connectivity and Long Short-Term Memory

Peng Wang; Jing He; Wenli Lan; Hui Yang; Yue Leng; Ruimin Wang; Keiji Iramina; Sheng Ge

doi:10.1109/IAEAC50856.2021.9390839

A Hybrid EEG-fNIRS Brain-Computer Interface Based on Dynamic Functional Connectivity and Long Short-Term Memory

Peng Wang, Jing He, Wenli Lan, Hui Yang, Yue Leng, Ruimin Wang, Keiji Iramina, Sheng Ge

Intelligence Science

Research output: Contribution to journal › Conference article › peer-review

3 Citations (Scopus)

Abstract

In this study, we combined dynamic functional connectivity (dFC) and long short-term memory (LSTM) to obtain robust high classification accuracy on bimodal motor imagery signals. To characterize the information flow in brain cortical activity, we measured the variation of the functional interaction between different signal channels with dFC in the feature extraction stage. The variation measured by dFC was then decoded by LSTM for classification. In addition, we used the electroencephalograph (EEG) and functional near-infrared spectroscopy (fNIRS) bimodal signals acquired simultaneously to overcome the artifact susceptibility of EEG. The average classification accuracy of 20 subjects was 90.03%, significantly higher than the traditional common spatial pattern (CSP) method. The result demonstrates the effectiveness of our data processing model.

Original language	English
Article number	9390839
Pages (from-to)	2214-2219
Number of pages	6
Journal	IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)
DOIs	https://doi.org/10.1109/IAEAC50856.2021.9390839
Publication status	Published - 2021
Event	5th IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2021 - Chongqing, China Duration: Mar 12 2021 → Mar 14 2021

All Science Journal Classification (ASJC) codes

Control and Systems Engineering
Electrical and Electronic Engineering
Applied Mathematics
Artificial Intelligence
Computer Networks and Communications
Computer Science Applications
Information Systems
Computer Vision and Pattern Recognition

Access to Document

10.1109/IAEAC50856.2021.9390839

Cite this

@article{7790444d72434293b92448b326041cd4,

title = "A Hybrid EEG-fNIRS Brain-Computer Interface Based on Dynamic Functional Connectivity and Long Short-Term Memory",

abstract = "In this study, we combined dynamic functional connectivity (dFC) and long short-term memory (LSTM) to obtain robust high classification accuracy on bimodal motor imagery signals. To characterize the information flow in brain cortical activity, we measured the variation of the functional interaction between different signal channels with dFC in the feature extraction stage. The variation measured by dFC was then decoded by LSTM for classification. In addition, we used the electroencephalograph (EEG) and functional near-infrared spectroscopy (fNIRS) bimodal signals acquired simultaneously to overcome the artifact susceptibility of EEG. The average classification accuracy of 20 subjects was 90.03%, significantly higher than the traditional common spatial pattern (CSP) method. The result demonstrates the effectiveness of our data processing model.",

author = "Peng Wang and Jing He and Wenli Lan and Hui Yang and Yue Leng and Ruimin Wang and Keiji Iramina and Sheng Ge",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 5th IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2021 ; Conference date: 12-03-2021 Through 14-03-2021",

year = "2021",

doi = "10.1109/IAEAC50856.2021.9390839",

language = "English",

pages = "2214--2219",

journal = "IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)",

issn = "2689-6621",

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

}

TY - JOUR

T1 - A Hybrid EEG-fNIRS Brain-Computer Interface Based on Dynamic Functional Connectivity and Long Short-Term Memory

AU - Wang, Peng

AU - He, Jing

AU - Lan, Wenli

AU - Yang, Hui

AU - Leng, Yue

AU - Wang, Ruimin

AU - Iramina, Keiji

AU - Ge, Sheng

PY - 2021

Y1 - 2021

N2 - In this study, we combined dynamic functional connectivity (dFC) and long short-term memory (LSTM) to obtain robust high classification accuracy on bimodal motor imagery signals. To characterize the information flow in brain cortical activity, we measured the variation of the functional interaction between different signal channels with dFC in the feature extraction stage. The variation measured by dFC was then decoded by LSTM for classification. In addition, we used the electroencephalograph (EEG) and functional near-infrared spectroscopy (fNIRS) bimodal signals acquired simultaneously to overcome the artifact susceptibility of EEG. The average classification accuracy of 20 subjects was 90.03%, significantly higher than the traditional common spatial pattern (CSP) method. The result demonstrates the effectiveness of our data processing model.

AB - In this study, we combined dynamic functional connectivity (dFC) and long short-term memory (LSTM) to obtain robust high classification accuracy on bimodal motor imagery signals. To characterize the information flow in brain cortical activity, we measured the variation of the functional interaction between different signal channels with dFC in the feature extraction stage. The variation measured by dFC was then decoded by LSTM for classification. In addition, we used the electroencephalograph (EEG) and functional near-infrared spectroscopy (fNIRS) bimodal signals acquired simultaneously to overcome the artifact susceptibility of EEG. The average classification accuracy of 20 subjects was 90.03%, significantly higher than the traditional common spatial pattern (CSP) method. The result demonstrates the effectiveness of our data processing model.

UR - http://www.scopus.com/inward/record.url?scp=85104612979&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85104612979&partnerID=8YFLogxK

U2 - 10.1109/IAEAC50856.2021.9390839

DO - 10.1109/IAEAC50856.2021.9390839

M3 - Conference article

AN - SCOPUS:85104612979

SN - 2689-6621

SP - 2214

EP - 2219

JO - IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)

JF - IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)

M1 - 9390839

T2 - 5th IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2021

Y2 - 12 March 2021 through 14 March 2021

ER -

A Hybrid EEG-fNIRS Brain-Computer Interface Based on Dynamic Functional Connectivity and Long Short-Term Memory

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this