An Online Data Visualization Feedback Protocol for Motor Imagery-Based BCI Training
Brain–computer interface (BCI) has developed rapidly over the past two decades, mainly due to advancements in machine learning. Subjects must learn to modulate their brain activities to ensure a successful BCI. Feedback training is a practical approach to this learning process; however, the commonly...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2021-06-01
|
Series: | Frontiers in Human Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnhum.2021.625983/full |
id |
doaj-34ef61bfbf82441db5b965abde451d73 |
---|---|
record_format |
Article |
spelling |
doaj-34ef61bfbf82441db5b965abde451d732021-06-07T04:39:16ZengFrontiers Media S.A.Frontiers in Human Neuroscience1662-51612021-06-011510.3389/fnhum.2021.625983625983An Online Data Visualization Feedback Protocol for Motor Imagery-Based BCI TrainingXu Duan0Songyun Xie1Xinzhou Xie2Klaus Obermayer3Yujie Cui4Zhenzhen Wang5School of Electronics and Information, Northwestern Polytechnical University, Xi’an, ChinaSchool of Electronics and Information, Northwestern Polytechnical University, Xi’an, ChinaSchool of Electronics and Information, Northwestern Polytechnical University, Xi’an, ChinaFaculty of Electrical Engineering and Computer Science, Technical University Berlin, Berlin, GermanySchool of Electronics and Information, Northwestern Polytechnical University, Xi’an, ChinaSchool of Electronics and Information, Northwestern Polytechnical University, Xi’an, ChinaBrain–computer interface (BCI) has developed rapidly over the past two decades, mainly due to advancements in machine learning. Subjects must learn to modulate their brain activities to ensure a successful BCI. Feedback training is a practical approach to this learning process; however, the commonly used classifier-dependent approaches have inherent limitations such as the need for calibration and a lack of continuous feedback over long periods of time. This paper proposes an online data visualization feedback protocol that intuitively reflects the EEG distribution in Riemannian geometry in real time. Rather than learning a hyperplane, the Riemannian geometry formulation allows iterative learning of prototypical covariance matrices that are translated into visualized feedback through diffusion map process. Ten subjects were recruited for MI-BCI (motor imagery-BCI) training experiments. The subjects learned to modulate their sensorimotor rhythm to centralize the points within one category and to separate points belonging to different categories. The results show favorable overall training effects in terms of the class distinctiveness and EEG feature discriminancy over a 3-day training with 30% learners. A steadily increased class distinctiveness in the last three sessions suggests that the advanced training protocol is effective. The optimal frequency band was consistent during the 3-day training, and the difference between subjects with good or low MI-BCI performance could be clearly observed. We believe that the proposed feedback protocol has promising application prospect.https://www.frontiersin.org/articles/10.3389/fnhum.2021.625983/fullbrain–computer interfacemotor imagerytraining protocolfeedbackRiemannian geometry |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xu Duan Songyun Xie Xinzhou Xie Klaus Obermayer Yujie Cui Zhenzhen Wang |
spellingShingle |
Xu Duan Songyun Xie Xinzhou Xie Klaus Obermayer Yujie Cui Zhenzhen Wang An Online Data Visualization Feedback Protocol for Motor Imagery-Based BCI Training Frontiers in Human Neuroscience brain–computer interface motor imagery training protocol feedback Riemannian geometry |
author_facet |
Xu Duan Songyun Xie Xinzhou Xie Klaus Obermayer Yujie Cui Zhenzhen Wang |
author_sort |
Xu Duan |
title |
An Online Data Visualization Feedback Protocol for Motor Imagery-Based BCI Training |
title_short |
An Online Data Visualization Feedback Protocol for Motor Imagery-Based BCI Training |
title_full |
An Online Data Visualization Feedback Protocol for Motor Imagery-Based BCI Training |
title_fullStr |
An Online Data Visualization Feedback Protocol for Motor Imagery-Based BCI Training |
title_full_unstemmed |
An Online Data Visualization Feedback Protocol for Motor Imagery-Based BCI Training |
title_sort |
online data visualization feedback protocol for motor imagery-based bci training |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Human Neuroscience |
issn |
1662-5161 |
publishDate |
2021-06-01 |
description |
Brain–computer interface (BCI) has developed rapidly over the past two decades, mainly due to advancements in machine learning. Subjects must learn to modulate their brain activities to ensure a successful BCI. Feedback training is a practical approach to this learning process; however, the commonly used classifier-dependent approaches have inherent limitations such as the need for calibration and a lack of continuous feedback over long periods of time. This paper proposes an online data visualization feedback protocol that intuitively reflects the EEG distribution in Riemannian geometry in real time. Rather than learning a hyperplane, the Riemannian geometry formulation allows iterative learning of prototypical covariance matrices that are translated into visualized feedback through diffusion map process. Ten subjects were recruited for MI-BCI (motor imagery-BCI) training experiments. The subjects learned to modulate their sensorimotor rhythm to centralize the points within one category and to separate points belonging to different categories. The results show favorable overall training effects in terms of the class distinctiveness and EEG feature discriminancy over a 3-day training with 30% learners. A steadily increased class distinctiveness in the last three sessions suggests that the advanced training protocol is effective. The optimal frequency band was consistent during the 3-day training, and the difference between subjects with good or low MI-BCI performance could be clearly observed. We believe that the proposed feedback protocol has promising application prospect. |
topic |
brain–computer interface motor imagery training protocol feedback Riemannian geometry |
url |
https://www.frontiersin.org/articles/10.3389/fnhum.2021.625983/full |
work_keys_str_mv |
AT xuduan anonlinedatavisualizationfeedbackprotocolformotorimagerybasedbcitraining AT songyunxie anonlinedatavisualizationfeedbackprotocolformotorimagerybasedbcitraining AT xinzhouxie anonlinedatavisualizationfeedbackprotocolformotorimagerybasedbcitraining AT klausobermayer anonlinedatavisualizationfeedbackprotocolformotorimagerybasedbcitraining AT yujiecui anonlinedatavisualizationfeedbackprotocolformotorimagerybasedbcitraining AT zhenzhenwang anonlinedatavisualizationfeedbackprotocolformotorimagerybasedbcitraining AT xuduan onlinedatavisualizationfeedbackprotocolformotorimagerybasedbcitraining AT songyunxie onlinedatavisualizationfeedbackprotocolformotorimagerybasedbcitraining AT xinzhouxie onlinedatavisualizationfeedbackprotocolformotorimagerybasedbcitraining AT klausobermayer onlinedatavisualizationfeedbackprotocolformotorimagerybasedbcitraining AT yujiecui onlinedatavisualizationfeedbackprotocolformotorimagerybasedbcitraining AT zhenzhenwang onlinedatavisualizationfeedbackprotocolformotorimagerybasedbcitraining |
_version_ |
1721392960091717632 |