Improved dilation CapsuleNet for motor imagery and mental arithmetic classification based on fNIRS

Purpose This study aimed to improve the accuracy of brain-computer interface (BCI) systems based on motor imagery (MI) and mental arithmetic (MA) by utilizing functional near-infrared spectroscopy (fNIRS) and an improved dilation CapsuleNet (ID-CapsuleNet) model.Methods The study focused on the char...

Full description

Saved in:
Bibliographic Details
Main Authors: Yu Li, Tao Xu, Junhua Li, Feng Wan, Hongtao Wang
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:Brain-Apparatus Communication
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/27706710.2024.2335886
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850063321219203072
author Yu Li
Tao Xu
Junhua Li
Feng Wan
Hongtao Wang
author_facet Yu Li
Tao Xu
Junhua Li
Feng Wan
Hongtao Wang
author_sort Yu Li
collection DOAJ
description Purpose This study aimed to improve the accuracy of brain-computer interface (BCI) systems based on motor imagery (MI) and mental arithmetic (MA) by utilizing functional near-infrared spectroscopy (fNIRS) and an improved dilation CapsuleNet (ID-CapsuleNet) model.Methods The study focused on the characteristics of fNIRS and employed large-kernel dilation convolution to extract hemodynamic features from fNIRS data. Inspired by CapsuleNet’s success in image classification, an ID-CapsuleNet model was designed, combining large-kernel dilation convolution and CapsuleNet. Four publicly available datasets (A, B, C, and D) were utilized for evaluating the proposed model. Datasets A and B were MA type, while datasets C and D were MI type. Ablation experiments were conducted to assess the usefulness of large-kernel convolution, dynamic routing, and dilation convolution.Results The average accuracies for each dataset were 95.01%, 76.88%, 74.03%, and 80.29% respectively. Cross-subject average accuracies were 88.72%, 75.80%, 75.78%, and 80.34%. Ablation experiments confirmed the importance of large-kernel convolution, dynamic routing, and dilation convolution in the ID-CapsuleNet model.Conclusion The developed ID-CapsuleNet model demonstrated promising potential for enhancing the performance of BCI systems based on MI and MA. The findings contribute to the advancement of BCI technology, offering improved assistive tools for disabled individuals.
format Article
id doaj-art-769ceb174d74437ba8d4e6ff4cac6bc8
institution DOAJ
issn 2770-6710
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series Brain-Apparatus Communication
spelling doaj-art-769ceb174d74437ba8d4e6ff4cac6bc82025-08-20T02:49:39ZengTaylor & Francis GroupBrain-Apparatus Communication2770-67102024-12-013110.1080/27706710.2024.2335886Improved dilation CapsuleNet for motor imagery and mental arithmetic classification based on fNIRSYu Li0Tao Xu1Junhua Li2Feng Wan3Hongtao Wang4Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen, ChinaFaculty of Intelligent Manufacturing, Wuyi University, Jiangmen, ChinaFaculty of Intelligent Manufacturing, Wuyi University, Jiangmen, ChinaDepartment of Electrical and Computer Engineering, Faculty of Science and Engineering, University of Macau, Macau, ChinaFaculty of Intelligent Manufacturing, Wuyi University, Jiangmen, ChinaPurpose This study aimed to improve the accuracy of brain-computer interface (BCI) systems based on motor imagery (MI) and mental arithmetic (MA) by utilizing functional near-infrared spectroscopy (fNIRS) and an improved dilation CapsuleNet (ID-CapsuleNet) model.Methods The study focused on the characteristics of fNIRS and employed large-kernel dilation convolution to extract hemodynamic features from fNIRS data. Inspired by CapsuleNet’s success in image classification, an ID-CapsuleNet model was designed, combining large-kernel dilation convolution and CapsuleNet. Four publicly available datasets (A, B, C, and D) were utilized for evaluating the proposed model. Datasets A and B were MA type, while datasets C and D were MI type. Ablation experiments were conducted to assess the usefulness of large-kernel convolution, dynamic routing, and dilation convolution.Results The average accuracies for each dataset were 95.01%, 76.88%, 74.03%, and 80.29% respectively. Cross-subject average accuracies were 88.72%, 75.80%, 75.78%, and 80.34%. Ablation experiments confirmed the importance of large-kernel convolution, dynamic routing, and dilation convolution in the ID-CapsuleNet model.Conclusion The developed ID-CapsuleNet model demonstrated promising potential for enhancing the performance of BCI systems based on MI and MA. The findings contribute to the advancement of BCI technology, offering improved assistive tools for disabled individuals.https://www.tandfonline.com/doi/10.1080/27706710.2024.2335886Brain-computer interfacemotor imagerymental arithmeticfNIRSCapsuleNetdilation convolution
spellingShingle Yu Li
Tao Xu
Junhua Li
Feng Wan
Hongtao Wang
Improved dilation CapsuleNet for motor imagery and mental arithmetic classification based on fNIRS
Brain-Apparatus Communication
Brain-computer interface
motor imagery
mental arithmetic
fNIRS
CapsuleNet
dilation convolution
title Improved dilation CapsuleNet for motor imagery and mental arithmetic classification based on fNIRS
title_full Improved dilation CapsuleNet for motor imagery and mental arithmetic classification based on fNIRS
title_fullStr Improved dilation CapsuleNet for motor imagery and mental arithmetic classification based on fNIRS
title_full_unstemmed Improved dilation CapsuleNet for motor imagery and mental arithmetic classification based on fNIRS
title_short Improved dilation CapsuleNet for motor imagery and mental arithmetic classification based on fNIRS
title_sort improved dilation capsulenet for motor imagery and mental arithmetic classification based on fnirs
topic Brain-computer interface
motor imagery
mental arithmetic
fNIRS
CapsuleNet
dilation convolution
url https://www.tandfonline.com/doi/10.1080/27706710.2024.2335886
work_keys_str_mv AT yuli improveddilationcapsulenetformotorimageryandmentalarithmeticclassificationbasedonfnirs
AT taoxu improveddilationcapsulenetformotorimageryandmentalarithmeticclassificationbasedonfnirs
AT junhuali improveddilationcapsulenetformotorimageryandmentalarithmeticclassificationbasedonfnirs
AT fengwan improveddilationcapsulenetformotorimageryandmentalarithmeticclassificationbasedonfnirs
AT hongtaowang improveddilationcapsulenetformotorimageryandmentalarithmeticclassificationbasedonfnirs