A Hybrid Transfer Learning Approach for Motor Imagery Classification in Brain-Computer Interface

Xuying Wang; Rui Yang; Mengjie Huang; Zhengni Yang; Zitong Wan

doi:10.1109/LifeTech52111.2021.9391933

A Hybrid Transfer Learning Approach for Motor Imagery Classification in Brain-Computer Interface

Xuying Wang, Rui Yang, Mengjie Huang^*, Zhengni Yang, Zitong Wan

^*Corresponding author for this work

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

9 Citations (Scopus)

Abstract

The classification of motor imagery (MI) signal is a representative problem in brain-computer interface (BCI) systems. Because one main application field of MI-based BCI is medical rehabilitation, it is often difficult to obtain a large amount of labeled data from the same subject. Moreover, there are huge individual differences among subjects, so the data from other subjects can not be directly used to train the classifier of the target subject. A transfer learning approach which based on data alignment and deep transfer learning is proposed to solve above problem, and the effectiveness of the proposed approach is verified by experiments based on open dataset.

Original language	English
Title of host publication	LifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	496-500
Number of pages	5
ISBN (Electronic)	9781665418751
DOIs	https://doi.org/10.1109/LifeTech52111.2021.9391933
Publication status	Published - 9 Mar 2021
Event	3rd IEEE Global Conference on Life Sciences and Technologies, LifeTech 2021 - Nara, Japan Duration: 9 Mar 2021 → 11 Mar 2021

Publication series

Name	LifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies

Conference

Conference	3rd IEEE Global Conference on Life Sciences and Technologies, LifeTech 2021
Country/Territory	Japan
City	Nara
Period	9/03/21 → 11/03/21

Keywords

Brain-computer interface
Convolutional neural network
Motor imagery
Transfer learning

Access to Document

10.1109/LifeTech52111.2021.9391933

Cite this

Wang, X., Yang, R., Huang, M., Yang, Z., & Wan, Z. (2021). A Hybrid Transfer Learning Approach for Motor Imagery Classification in Brain-Computer Interface. In LifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies (pp. 496-500). Article 9391933 (LifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/LifeTech52111.2021.9391933

Wang, Xuying ; Yang, Rui ; Huang, Mengjie et al. / A Hybrid Transfer Learning Approach for Motor Imagery Classification in Brain-Computer Interface. LifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 496-500 (LifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies).

@inproceedings{4d3f3ac94cf044e6b6d76691ac44fd91,

title = "A Hybrid Transfer Learning Approach for Motor Imagery Classification in Brain-Computer Interface",

abstract = "The classification of motor imagery (MI) signal is a representative problem in brain-computer interface (BCI) systems. Because one main application field of MI-based BCI is medical rehabilitation, it is often difficult to obtain a large amount of labeled data from the same subject. Moreover, there are huge individual differences among subjects, so the data from other subjects can not be directly used to train the classifier of the target subject. A transfer learning approach which based on data alignment and deep transfer learning is proposed to solve above problem, and the effectiveness of the proposed approach is verified by experiments based on open dataset.",

keywords = "Brain-computer interface, Convolutional neural network, Motor imagery, Transfer learning",

author = "Xuying Wang and Rui Yang and Mengjie Huang and Zhengni Yang and Zitong Wan",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 3rd IEEE Global Conference on Life Sciences and Technologies, LifeTech 2021 ; Conference date: 09-03-2021 Through 11-03-2021",

year = "2021",

month = mar,

day = "9",

doi = "10.1109/LifeTech52111.2021.9391933",

language = "English",

series = "LifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies",

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

pages = "496--500",

booktitle = "LifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies",

}

Wang, X, Yang, R , Huang, M, Yang, Z & Wan, Z 2021, A Hybrid Transfer Learning Approach for Motor Imagery Classification in Brain-Computer Interface. in LifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies., 9391933, LifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies, Institute of Electrical and Electronics Engineers Inc., pp. 496-500, 3rd IEEE Global Conference on Life Sciences and Technologies, LifeTech 2021, Nara, Japan, 9/03/21. https://doi.org/10.1109/LifeTech52111.2021.9391933

A Hybrid Transfer Learning Approach for Motor Imagery Classification in Brain-Computer Interface. / Wang, Xuying; Yang, Rui ; Huang, Mengjie et al.
LifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies. Institute of Electrical and Electronics Engineers Inc., 2021. p. 496-500 9391933 (LifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies).

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

TY - GEN

T1 - A Hybrid Transfer Learning Approach for Motor Imagery Classification in Brain-Computer Interface

AU - Wang, Xuying

AU - Yang, Rui

AU - Huang, Mengjie

AU - Yang, Zhengni

AU - Wan, Zitong

PY - 2021/3/9

Y1 - 2021/3/9

N2 - The classification of motor imagery (MI) signal is a representative problem in brain-computer interface (BCI) systems. Because one main application field of MI-based BCI is medical rehabilitation, it is often difficult to obtain a large amount of labeled data from the same subject. Moreover, there are huge individual differences among subjects, so the data from other subjects can not be directly used to train the classifier of the target subject. A transfer learning approach which based on data alignment and deep transfer learning is proposed to solve above problem, and the effectiveness of the proposed approach is verified by experiments based on open dataset.

AB - The classification of motor imagery (MI) signal is a representative problem in brain-computer interface (BCI) systems. Because one main application field of MI-based BCI is medical rehabilitation, it is often difficult to obtain a large amount of labeled data from the same subject. Moreover, there are huge individual differences among subjects, so the data from other subjects can not be directly used to train the classifier of the target subject. A transfer learning approach which based on data alignment and deep transfer learning is proposed to solve above problem, and the effectiveness of the proposed approach is verified by experiments based on open dataset.

KW - Brain-computer interface

KW - Convolutional neural network

KW - Motor imagery

KW - Transfer learning

UR - http://www.scopus.com/inward/record.url?scp=85104635503&partnerID=8YFLogxK

U2 - 10.1109/LifeTech52111.2021.9391933

DO - 10.1109/LifeTech52111.2021.9391933

M3 - Conference Proceeding

AN - SCOPUS:85104635503

T3 - LifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies

SP - 496

EP - 500

BT - LifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd IEEE Global Conference on Life Sciences and Technologies, LifeTech 2021

Y2 - 9 March 2021 through 11 March 2021

ER -

Wang X, Yang R , Huang M, Yang Z, Wan Z. A Hybrid Transfer Learning Approach for Motor Imagery Classification in Brain-Computer Interface. In LifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies. Institute of Electrical and Electronics Engineers Inc. 2021. p. 496-500. 9391933. (LifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies). doi: 10.1109/LifeTech52111.2021.9391933

A Hybrid Transfer Learning Approach for Motor Imagery Classification in Brain-Computer Interface

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this