Bridging the BCI illiteracy gap: a subject-to-subject semantic style transfer for EEG-based motor imagery classification

Brain-computer interfaces (BCIs) facilitate direct interaction between the human brain and computers, enabling individuals to control external devices through cognitive processes. Despite its potential, the problem of BCI illiteracy remains one of the major challenges due to inter-subject EEG variab...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in Human Neuroscience Vol. 17; p. 1194751
Main Authors: Kim, Da-Hyun, Shin, Dong-Hee, Kam, Tae-Eui
Format: Journal Article
Language:English
Published: Switzerland Frontiers Media SA 15.05.2023
Frontiers Research Foundation
Frontiers Media S.A
Subjects:
Adaptation
BCI illiteracy
Brain research
brain-computer interface
Classification
Cognitive ability
Computers
convolutional neural network
Discriminant analysis
EEG
electroencephalogram
Electroencephalography
Human Neuroscience
Illiteracy
Machine learning
Mental task performance
motor imagery
Neural networks
Neurosciences. Biological psychiatry. Neuropsychiatry
RC321-571
style transfer
motor imagery
style transfer
brain-computer interface
convolutional neural network
electroencephalogram
BCI illiteracy
ISSN:1662-5161, 1662-5161
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Brain-computer interfaces (BCIs) facilitate direct interaction between the human brain and computers, enabling individuals to control external devices through cognitive processes. Despite its potential, the problem of BCI illiteracy remains one of the major challenges due to inter-subject EEG variability, which hinders many users from effectively utilizing BCI systems. In this study, we propose a subject-to-subject semantic style transfer network (SSSTN) at the feature-level to address the BCI illiteracy problem in electroencephalogram (EEG)-based motor imagery (MI) classification tasks. Our approach uses the continuous wavelet transform method to convert high-dimensional EEG data into images as input data. The SSSTN 1) trains a classifier for each subject, 2) transfers the distribution of class discrimination styles from the source subject (the best-performing subject for the classifier, i.e., BCI expert) to each subject of the target domain (the remaining subjects except the source subject, specifically BCI illiterates) through the proposed style loss, and applies a modified content loss to preserve the class-relevant semantic information of the target domain, and 3) finally merges the classifier predictions of both source and target subject using an ensemble technique. We evaluate the proposed method on the BCI Competition IV-2a and IV-2b datasets and demonstrate improved classification performance over existing methods, especially for BCI illiterate users. The ablation experiments and t-SNE visualizations further highlight the effectiveness of the proposed method in achieving meaningful feature-level semantic style transfer.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Edited by: Jiahui Pan, South China Normal University, China
Reviewed by: Fangzhou Xu, Qilu University of Technology, China; Yong Peng, Hangzhou Dianzi University, China; Xin Deng, Chongqing University of Posts and Telecommunications, China
ISSN:1662-5161
1662-5161
DOI:10.3389/fnhum.2023.1194751