Cargando…
Subject-Independent Functional Near-Infrared Spectroscopy-Based Brain–Computer Interfaces Based on Convolutional Neural Networks
Functional near-infrared spectroscopy (fNIRS) has attracted increasing attention in the field of brain–computer interfaces (BCIs) owing to their advantages such as non-invasiveness, user safety, affordability, and portability. However, fNIRS signals are highly subject-specific and have low test-rete...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7994252/ https://www.ncbi.nlm.nih.gov/pubmed/33776674 http://dx.doi.org/10.3389/fnhum.2021.646915 |
_version_ | 1783669715158171648 |
---|---|
author | Kwon, Jinuk Im, Chang-Hwan |
author_facet | Kwon, Jinuk Im, Chang-Hwan |
author_sort | Kwon, Jinuk |
collection | PubMed |
description | Functional near-infrared spectroscopy (fNIRS) has attracted increasing attention in the field of brain–computer interfaces (BCIs) owing to their advantages such as non-invasiveness, user safety, affordability, and portability. However, fNIRS signals are highly subject-specific and have low test-retest reliability. Therefore, individual calibration sessions need to be employed before each use of fNIRS-based BCI to achieve a sufficiently high performance for practical BCI applications. In this study, we propose a novel deep convolutional neural network (CNN)-based approach for implementing a subject-independent fNIRS-based BCI. A total of 18 participants performed the fNIRS-based BCI experiments, where the main goal of the experiments was to distinguish a mental arithmetic task from an idle state task. Leave-one-subject-out cross-validation was employed to evaluate the average classification accuracy of the proposed subject-independent fNIRS-based BCI. As a result, the average classification accuracy of the proposed method was reported to be 71.20 ± 8.74%, which was higher than the threshold accuracy for effective BCI communication (70%) as well as that obtained using conventional shrinkage linear discriminant analysis (65.74 ± 7.68%). To achieve a classification accuracy comparable to that of the proposed subject-independent fNIRS-based BCI, 24 training trials (of approximately 12 min) were necessary for the traditional subject-dependent fNIRS-based BCI. It is expected that our CNN-based approach would reduce the necessity of long-term individual calibration sessions, thereby enhancing the practicality of fNIRS-based BCIs significantly. |
format | Online Article Text |
id | pubmed-7994252 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-79942522021-03-27 Subject-Independent Functional Near-Infrared Spectroscopy-Based Brain–Computer Interfaces Based on Convolutional Neural Networks Kwon, Jinuk Im, Chang-Hwan Front Hum Neurosci Human Neuroscience Functional near-infrared spectroscopy (fNIRS) has attracted increasing attention in the field of brain–computer interfaces (BCIs) owing to their advantages such as non-invasiveness, user safety, affordability, and portability. However, fNIRS signals are highly subject-specific and have low test-retest reliability. Therefore, individual calibration sessions need to be employed before each use of fNIRS-based BCI to achieve a sufficiently high performance for practical BCI applications. In this study, we propose a novel deep convolutional neural network (CNN)-based approach for implementing a subject-independent fNIRS-based BCI. A total of 18 participants performed the fNIRS-based BCI experiments, where the main goal of the experiments was to distinguish a mental arithmetic task from an idle state task. Leave-one-subject-out cross-validation was employed to evaluate the average classification accuracy of the proposed subject-independent fNIRS-based BCI. As a result, the average classification accuracy of the proposed method was reported to be 71.20 ± 8.74%, which was higher than the threshold accuracy for effective BCI communication (70%) as well as that obtained using conventional shrinkage linear discriminant analysis (65.74 ± 7.68%). To achieve a classification accuracy comparable to that of the proposed subject-independent fNIRS-based BCI, 24 training trials (of approximately 12 min) were necessary for the traditional subject-dependent fNIRS-based BCI. It is expected that our CNN-based approach would reduce the necessity of long-term individual calibration sessions, thereby enhancing the practicality of fNIRS-based BCIs significantly. Frontiers Media S.A. 2021-03-12 /pmc/articles/PMC7994252/ /pubmed/33776674 http://dx.doi.org/10.3389/fnhum.2021.646915 Text en Copyright © 2021 Kwon and Im. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Human Neuroscience Kwon, Jinuk Im, Chang-Hwan Subject-Independent Functional Near-Infrared Spectroscopy-Based Brain–Computer Interfaces Based on Convolutional Neural Networks |
title | Subject-Independent Functional Near-Infrared Spectroscopy-Based Brain–Computer Interfaces Based on Convolutional Neural Networks |
title_full | Subject-Independent Functional Near-Infrared Spectroscopy-Based Brain–Computer Interfaces Based on Convolutional Neural Networks |
title_fullStr | Subject-Independent Functional Near-Infrared Spectroscopy-Based Brain–Computer Interfaces Based on Convolutional Neural Networks |
title_full_unstemmed | Subject-Independent Functional Near-Infrared Spectroscopy-Based Brain–Computer Interfaces Based on Convolutional Neural Networks |
title_short | Subject-Independent Functional Near-Infrared Spectroscopy-Based Brain–Computer Interfaces Based on Convolutional Neural Networks |
title_sort | subject-independent functional near-infrared spectroscopy-based brain–computer interfaces based on convolutional neural networks |
topic | Human Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7994252/ https://www.ncbi.nlm.nih.gov/pubmed/33776674 http://dx.doi.org/10.3389/fnhum.2021.646915 |
work_keys_str_mv | AT kwonjinuk subjectindependentfunctionalnearinfraredspectroscopybasedbraincomputerinterfacesbasedonconvolutionalneuralnetworks AT imchanghwan subjectindependentfunctionalnearinfraredspectroscopybasedbraincomputerinterfacesbasedonconvolutionalneuralnetworks |