Cross-Dataset Variability Problem in EEG Decoding With Deep Learning

Cross-subject variability problems hinder practical usages of Brain-Computer Interfaces. Recently, deep learning has been introduced into the BCI community due to its better generalization and feature representation abilities. However, most studies currently only have validated deep learning models...

Full description

Saved in:
Bibliographic Details
Published inFrontiers in human neuroscience Vol. 14; p. 103
Main Authors Xu, Lichao, Xu, Minpeng, Ke, Yufeng, An, Xingwei, Liu, Shuang, Ming, Dong
Format Journal Article
LanguageEnglish
Published Switzerland Frontiers Research Foundation 21.04.2020
Frontiers Media S.A
Subjects
Algorithms
brain-computer interface
Classification
cross-dataset variability
cross-subject variability
Datasets
Deep learning
EEG
Eigenvalues
Electroencephalography
Geometry
Human Neuroscience
Interfaces
Internet
Machine learning
Medical imaging
Signal processing
transfer learning
deep learning
transfer learning
cross-subject variability
cross-dataset variability
EEG
brain-computer interface
Online AccessGet full text

Cover

More Information
Summary:Cross-subject variability problems hinder practical usages of Brain-Computer Interfaces. Recently, deep learning has been introduced into the BCI community due to its better generalization and feature representation abilities. However, most studies currently only have validated deep learning models for single datasets, and the generalization ability for other datasets still needs to be further verified. In this paper, we validated deep learning models for eight MI datasets and demonstrated that the cross-dataset variability problem weakened the generalization ability of models. To alleviate the impact of cross-dataset variability, we proposed an online pre-alignment strategy for aligning the EEG distributions of different subjects before training and inference processes. The results of this study show that deep learning models with online pre-alignment strategies could significantly improve the generalization ability across datasets without any additional calibration data.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Reviewed by: Ren Xu, Guger Technologies, Austria; Dongrui Wu, Huazhong University of Science and Technology, China; Sung Chan Jun, Gwangju Institute of Science and Technology, South Korea
This article was submitted to Brain-Computer Interfaces, a section of the journal Frontiers in Human Neuroscience
Edited by: Junhua Li, University of Essex, United Kingdom
These authors have contributed equally to this work
ISSN:1662-5161
1662-5161
DOI:10.3389/fnhum.2020.00103