Analyzing Classification Performance of fNIRS-BCI for Gait Rehabilitation Using Deep Neural Networks
This research presents a brain-computer interface (BCI) framework for brain signal classification using deep learning (DL) and machine learning (ML) approaches on functional near-infrared spectroscopy (fNIRS) signals. fNIRS signals of motor execution for walking and rest tasks are acquired from the...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-03-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/5/1932 |
_version_ | 1797473708918439936 |
---|---|
author | Huma Hamid Noman Naseer Hammad Nazeer Muhammad Jawad Khan Rayyan Azam Khan Umar Shahbaz Khan |
author_facet | Huma Hamid Noman Naseer Hammad Nazeer Muhammad Jawad Khan Rayyan Azam Khan Umar Shahbaz Khan |
author_sort | Huma Hamid |
collection | DOAJ |
description | This research presents a brain-computer interface (BCI) framework for brain signal classification using deep learning (DL) and machine learning (ML) approaches on functional near-infrared spectroscopy (fNIRS) signals. fNIRS signals of motor execution for walking and rest tasks are acquired from the primary motor cortex in the brain’s left hemisphere for nine subjects. DL algorithms, including convolutional neural networks (CNNs), long short-term memory (LSTM), and bidirectional LSTM (Bi-LSTM) are used to achieve average classification accuracies of 88.50%, 84.24%, and 85.13%, respectively. For comparison purposes, three conventional ML algorithms, support vector machine (SVM), k-nearest neighbor (k-NN), and linear discriminant analysis (LDA) are also used for classification, resulting in average classification accuracies of 73.91%, 74.24%, and 65.85%, respectively. This study successfully demonstrates that the enhanced performance of fNIRS-BCI can be achieved in terms of classification accuracy using DL approaches compared to conventional ML approaches. Furthermore, the control commands generated by these classifiers can be used to initiate and stop the gait cycle of the lower limb exoskeleton for gait rehabilitation. |
first_indexed | 2024-03-09T20:21:14Z |
format | Article |
id | doaj.art-4ab0fcbba6294882994befa189c1382c |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T20:21:14Z |
publishDate | 2022-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-4ab0fcbba6294882994befa189c1382c2023-11-23T23:48:31ZengMDPI AGSensors1424-82202022-03-01225193210.3390/s22051932Analyzing Classification Performance of fNIRS-BCI for Gait Rehabilitation Using Deep Neural NetworksHuma Hamid0Noman Naseer1Hammad Nazeer2Muhammad Jawad Khan3Rayyan Azam Khan4Umar Shahbaz Khan5Department of Mechatronics and Biomedical Engineering, Air University, Islamabad 44000, PakistanDepartment of Mechatronics and Biomedical Engineering, Air University, Islamabad 44000, PakistanDepartment of Mechatronics and Biomedical Engineering, Air University, Islamabad 44000, PakistanSchool of Mechanical and Manufacturing Engineering, National University of Science and Technology, Islamabad 44000, PakistanDepartment of Mechanical Engineering, University of Saskatchewan, Saskatoon, SK S7N 5A9, CanadaDepartment of Mechatronics Engineering, National University of Sciences and Technology, Islamabad 44000, PakistanThis research presents a brain-computer interface (BCI) framework for brain signal classification using deep learning (DL) and machine learning (ML) approaches on functional near-infrared spectroscopy (fNIRS) signals. fNIRS signals of motor execution for walking and rest tasks are acquired from the primary motor cortex in the brain’s left hemisphere for nine subjects. DL algorithms, including convolutional neural networks (CNNs), long short-term memory (LSTM), and bidirectional LSTM (Bi-LSTM) are used to achieve average classification accuracies of 88.50%, 84.24%, and 85.13%, respectively. For comparison purposes, three conventional ML algorithms, support vector machine (SVM), k-nearest neighbor (k-NN), and linear discriminant analysis (LDA) are also used for classification, resulting in average classification accuracies of 73.91%, 74.24%, and 65.85%, respectively. This study successfully demonstrates that the enhanced performance of fNIRS-BCI can be achieved in terms of classification accuracy using DL approaches compared to conventional ML approaches. Furthermore, the control commands generated by these classifiers can be used to initiate and stop the gait cycle of the lower limb exoskeleton for gait rehabilitation.https://www.mdpi.com/1424-8220/22/5/1932functional near-infrared spectroscopybrain-computer interfaceconvolutional neural networklong short-term memoryneurorehabilitation |
spellingShingle | Huma Hamid Noman Naseer Hammad Nazeer Muhammad Jawad Khan Rayyan Azam Khan Umar Shahbaz Khan Analyzing Classification Performance of fNIRS-BCI for Gait Rehabilitation Using Deep Neural Networks Sensors functional near-infrared spectroscopy brain-computer interface convolutional neural network long short-term memory neurorehabilitation |
title | Analyzing Classification Performance of fNIRS-BCI for Gait Rehabilitation Using Deep Neural Networks |
title_full | Analyzing Classification Performance of fNIRS-BCI for Gait Rehabilitation Using Deep Neural Networks |
title_fullStr | Analyzing Classification Performance of fNIRS-BCI for Gait Rehabilitation Using Deep Neural Networks |
title_full_unstemmed | Analyzing Classification Performance of fNIRS-BCI for Gait Rehabilitation Using Deep Neural Networks |
title_short | Analyzing Classification Performance of fNIRS-BCI for Gait Rehabilitation Using Deep Neural Networks |
title_sort | analyzing classification performance of fnirs bci for gait rehabilitation using deep neural networks |
topic | functional near-infrared spectroscopy brain-computer interface convolutional neural network long short-term memory neurorehabilitation |
url | https://www.mdpi.com/1424-8220/22/5/1932 |
work_keys_str_mv | AT humahamid analyzingclassificationperformanceoffnirsbciforgaitrehabilitationusingdeepneuralnetworks AT nomannaseer analyzingclassificationperformanceoffnirsbciforgaitrehabilitationusingdeepneuralnetworks AT hammadnazeer analyzingclassificationperformanceoffnirsbciforgaitrehabilitationusingdeepneuralnetworks AT muhammadjawadkhan analyzingclassificationperformanceoffnirsbciforgaitrehabilitationusingdeepneuralnetworks AT rayyanazamkhan analyzingclassificationperformanceoffnirsbciforgaitrehabilitationusingdeepneuralnetworks AT umarshahbazkhan analyzingclassificationperformanceoffnirsbciforgaitrehabilitationusingdeepneuralnetworks |