An Analysis of Deep Learning Models in SSVEP-Based BCI: A Survey

The brain–computer interface (BCI), which provides a new way for humans to directly communicate with robots without the involvement of the peripheral nervous system, has recently attracted much attention. Among all the BCI paradigms, BCIs based on steady-state visual evoked potentials (SSVEPs) have...

Descripción completa

Detalles Bibliográficos
Autores principales: Xu, Dongcen, Tang, Fengzhen, Li, Yiping, Zhang, Qifeng, Feng, Xisheng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10046535/
https://www.ncbi.nlm.nih.gov/pubmed/36979293
http://dx.doi.org/10.3390/brainsci13030483
_version_ 1785013696939950080
author Xu, Dongcen
Tang, Fengzhen
Li, Yiping
Zhang, Qifeng
Feng, Xisheng
author_facet Xu, Dongcen
Tang, Fengzhen
Li, Yiping
Zhang, Qifeng
Feng, Xisheng
author_sort Xu, Dongcen
collection PubMed
description The brain–computer interface (BCI), which provides a new way for humans to directly communicate with robots without the involvement of the peripheral nervous system, has recently attracted much attention. Among all the BCI paradigms, BCIs based on steady-state visual evoked potentials (SSVEPs) have the highest information transfer rate (ITR) and the shortest training time. Meanwhile, deep learning has provided an effective and feasible solution for solving complex classification problems in many fields, and many researchers have started to apply deep learning to classify SSVEP signals. However, the designs of deep learning models vary drastically. There are many hyper-parameters that influence the performance of the model in an unpredictable way. This study surveyed 31 deep learning models (2011–2023) that were used to classify SSVEP signals and analyzed their design aspects including model input, model structure, performance measure, etc. Most of the studies that were surveyed in this paper were published in 2021 and 2022. This survey is an up-to-date design guide for researchers who are interested in using deep learning models to classify SSVEP signals.
format Online
Article
Text
id pubmed-10046535
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-100465352023-03-29 An Analysis of Deep Learning Models in SSVEP-Based BCI: A Survey Xu, Dongcen Tang, Fengzhen Li, Yiping Zhang, Qifeng Feng, Xisheng Brain Sci Review The brain–computer interface (BCI), which provides a new way for humans to directly communicate with robots without the involvement of the peripheral nervous system, has recently attracted much attention. Among all the BCI paradigms, BCIs based on steady-state visual evoked potentials (SSVEPs) have the highest information transfer rate (ITR) and the shortest training time. Meanwhile, deep learning has provided an effective and feasible solution for solving complex classification problems in many fields, and many researchers have started to apply deep learning to classify SSVEP signals. However, the designs of deep learning models vary drastically. There are many hyper-parameters that influence the performance of the model in an unpredictable way. This study surveyed 31 deep learning models (2011–2023) that were used to classify SSVEP signals and analyzed their design aspects including model input, model structure, performance measure, etc. Most of the studies that were surveyed in this paper were published in 2021 and 2022. This survey is an up-to-date design guide for researchers who are interested in using deep learning models to classify SSVEP signals. MDPI 2023-03-13 /pmc/articles/PMC10046535/ /pubmed/36979293 http://dx.doi.org/10.3390/brainsci13030483 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Review
Xu, Dongcen
Tang, Fengzhen
Li, Yiping
Zhang, Qifeng
Feng, Xisheng
An Analysis of Deep Learning Models in SSVEP-Based BCI: A Survey
title An Analysis of Deep Learning Models in SSVEP-Based BCI: A Survey
title_full An Analysis of Deep Learning Models in SSVEP-Based BCI: A Survey
title_fullStr An Analysis of Deep Learning Models in SSVEP-Based BCI: A Survey
title_full_unstemmed An Analysis of Deep Learning Models in SSVEP-Based BCI: A Survey
title_short An Analysis of Deep Learning Models in SSVEP-Based BCI: A Survey
title_sort analysis of deep learning models in ssvep-based bci: a survey
topic Review
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10046535/
https://www.ncbi.nlm.nih.gov/pubmed/36979293
http://dx.doi.org/10.3390/brainsci13030483
work_keys_str_mv AT xudongcen ananalysisofdeeplearningmodelsinssvepbasedbciasurvey
AT tangfengzhen ananalysisofdeeplearningmodelsinssvepbasedbciasurvey
AT liyiping ananalysisofdeeplearningmodelsinssvepbasedbciasurvey
AT zhangqifeng ananalysisofdeeplearningmodelsinssvepbasedbciasurvey
AT fengxisheng ananalysisofdeeplearningmodelsinssvepbasedbciasurvey
AT xudongcen analysisofdeeplearningmodelsinssvepbasedbciasurvey
AT tangfengzhen analysisofdeeplearningmodelsinssvepbasedbciasurvey
AT liyiping analysisofdeeplearningmodelsinssvepbasedbciasurvey
AT zhangqifeng analysisofdeeplearningmodelsinssvepbasedbciasurvey
AT fengxisheng analysisofdeeplearningmodelsinssvepbasedbciasurvey