Performance enhancement of a brain-computer interface using high-density multi-distance NIRS

Abstract This study investigated the effectiveness of using a high-density multi-distance source-detector (SD) separations in near-infrared spectroscopy (NIRS), for enhancing the performance of a functional NIRS (fNIRS)-based brain-computer interface (BCI). The NIRS system that was used for the expe...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Jaeyoung Shin, Jinuk Kwon, Jongkwan Choi, Chang-Hwan Im
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2017
Materias:
R
Q
Acceso en línea:https://doaj.org/article/5f0b0849e741491cbe931733ac017b88
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:5f0b0849e741491cbe931733ac017b88
record_format dspace
spelling oai:doaj.org-article:5f0b0849e741491cbe931733ac017b882021-12-02T15:04:58ZPerformance enhancement of a brain-computer interface using high-density multi-distance NIRS10.1038/s41598-017-16639-02045-2322https://doaj.org/article/5f0b0849e741491cbe931733ac017b882017-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-16639-0https://doaj.org/toc/2045-2322Abstract This study investigated the effectiveness of using a high-density multi-distance source-detector (SD) separations in near-infrared spectroscopy (NIRS), for enhancing the performance of a functional NIRS (fNIRS)-based brain-computer interface (BCI). The NIRS system that was used for the experiment was capable of measuring signals from four SD separations: 15, 21.2, 30, and 33.5 mm, and this allowed the measurement of hemodynamic response alterations at various depths. Fifteen participants were asked to perform mental arithmetic and word chain tasks, to induce task-related hemodynamic response variations, or they were asked to stay relaxed to acquire a baseline signal. To evaluate the degree of BCI performance enhancement by high-density channel configuration, the classification accuracy obtained using a typical low-density lattice SD arrangement, was compared to that obtained using the high-density SD arrangement, while maintaining the SD separation at 30 mm. The analysis results demonstrated that the use of a high-density channel configuration did not result in a noticeable enhancement of classification accuracy. However, the combination of hemodynamic variations, measured by two multi-distance SD separations, resulted in the significant enhancement of overall classification accuracy. The results of this study indicated that the use of high-density multi-distance SD separations can likely provide a new method for enhancing the performance of an fNIRS-BCI.Jaeyoung ShinJinuk KwonJongkwan ChoiChang-Hwan ImNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-10 (2017)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Jaeyoung Shin
Jinuk Kwon
Jongkwan Choi
Chang-Hwan Im
Performance enhancement of a brain-computer interface using high-density multi-distance NIRS
description Abstract This study investigated the effectiveness of using a high-density multi-distance source-detector (SD) separations in near-infrared spectroscopy (NIRS), for enhancing the performance of a functional NIRS (fNIRS)-based brain-computer interface (BCI). The NIRS system that was used for the experiment was capable of measuring signals from four SD separations: 15, 21.2, 30, and 33.5 mm, and this allowed the measurement of hemodynamic response alterations at various depths. Fifteen participants were asked to perform mental arithmetic and word chain tasks, to induce task-related hemodynamic response variations, or they were asked to stay relaxed to acquire a baseline signal. To evaluate the degree of BCI performance enhancement by high-density channel configuration, the classification accuracy obtained using a typical low-density lattice SD arrangement, was compared to that obtained using the high-density SD arrangement, while maintaining the SD separation at 30 mm. The analysis results demonstrated that the use of a high-density channel configuration did not result in a noticeable enhancement of classification accuracy. However, the combination of hemodynamic variations, measured by two multi-distance SD separations, resulted in the significant enhancement of overall classification accuracy. The results of this study indicated that the use of high-density multi-distance SD separations can likely provide a new method for enhancing the performance of an fNIRS-BCI.
format article
author Jaeyoung Shin
Jinuk Kwon
Jongkwan Choi
Chang-Hwan Im
author_facet Jaeyoung Shin
Jinuk Kwon
Jongkwan Choi
Chang-Hwan Im
author_sort Jaeyoung Shin
title Performance enhancement of a brain-computer interface using high-density multi-distance NIRS
title_short Performance enhancement of a brain-computer interface using high-density multi-distance NIRS
title_full Performance enhancement of a brain-computer interface using high-density multi-distance NIRS
title_fullStr Performance enhancement of a brain-computer interface using high-density multi-distance NIRS
title_full_unstemmed Performance enhancement of a brain-computer interface using high-density multi-distance NIRS
title_sort performance enhancement of a brain-computer interface using high-density multi-distance nirs
publisher Nature Portfolio
publishDate 2017
url https://doaj.org/article/5f0b0849e741491cbe931733ac017b88
work_keys_str_mv AT jaeyoungshin performanceenhancementofabraincomputerinterfaceusinghighdensitymultidistancenirs
AT jinukkwon performanceenhancementofabraincomputerinterfaceusinghighdensitymultidistancenirs
AT jongkwanchoi performanceenhancementofabraincomputerinterfaceusinghighdensitymultidistancenirs
AT changhwanim performanceenhancementofabraincomputerinterfaceusinghighdensitymultidistancenirs
_version_ 1718388958630510592