Exploring Effects of Mental Stress with Data Augmentation and Classification Using fNIRS

Accurately identifying and discriminating between different brain states is a major emphasis of functional brain imaging research. Various machine learning techniques play an important role in this regard. However, when working with a small number of study participants, the lack of sufficient data a...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Khan, Malik Nasir Afzal (author)
مؤلفون آخرون: Zahour, Nada (author), Tariq, Usman (author), Masri, Ghinwa (author), Almadani, Ismat F. (author), Al-Nashah, Hasan (author)
التنسيق: article
منشور في: 2025
الموضوعات:
الوصول للمادة أونلاين:https://hdl.handle.net/11073/26085
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513432915542016
author Khan, Malik Nasir Afzal
author2 Zahour, Nada
Tariq, Usman
Masri, Ghinwa
Almadani, Ismat F.
Al-Nashah, Hasan
author2_role author
author
author
author
author
author_facet Khan, Malik Nasir Afzal
Zahour, Nada
Tariq, Usman
Masri, Ghinwa
Almadani, Ismat F.
Al-Nashah, Hasan
author_role author
dc.creator.none.fl_str_mv Khan, Malik Nasir Afzal
Zahour, Nada
Tariq, Usman
Masri, Ghinwa
Almadani, Ismat F.
Al-Nashah, Hasan
dc.date.none.fl_str_mv 2025-06-02T08:55:12Z
2025-06-02T08:55:12Z
2025-01
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv Khan, M.N.A.; Zahour, N.; Tariq, U.; Masri, G.; Almadani, I.F.; Al-Nashah, H. Exploring Effects of Mental Stress with Data Augmentation and Classification Using fNIRS. Sensors 2025, 25, 428. https://doi.org/10.3390/s25020428
1424-8220
https://hdl.handle.net/11073/26085
10.3390/s25020428
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv MDPI
dc.relation.none.fl_str_mv https://doi.org/10.3390/s25020428
dc.subject.none.fl_str_mv Functional near-infrared spectroscopy (fNIRS)
Hemodynamic response
Deep convolutional generative adversarial network (DCGAN)
Feed-forward neural network
Linear support vector machines
Decision tree
Restricted Boltzmann machine
Convolutional neural networks
Classification
Binaural beats
dc.title.none.fl_str_mv Exploring Effects of Mental Stress with Data Augmentation and Classification Using fNIRS
dc.type.none.fl_str_mv Peer-Reviewed
Published version
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description Accurately identifying and discriminating between different brain states is a major emphasis of functional brain imaging research. Various machine learning techniques play an important role in this regard. However, when working with a small number of study participants, the lack of sufficient data and achieving meaningful classification results remain a challenge. In this study, we employ a classification strategy to explore stress and its impact on spatial activation patterns and brain connectivity caused by the Stroop color–word task (SCWT). To improve our results and increase our dataset, we use data augmentation with a deep convolutional generative adversarial network (DCGAN). The study is carried out at two separate times of day (morning and evening) and involves 21 healthy participants. Additionally, we introduce binaural beats (BBs) stimulation to investigate its potential for stress reduction. The morning session includes a control phase with 10 SCWT trials, whereas the afternoon session is divided into three phases: stress, mitigation (with 16 Hz BB stimulation), and post-mitigation, each with 10 SCWT trials. For a comprehensive evaluation, the acquired fNIRS data are classified using a variety of machine-learning approaches. Linear discriminant analysis (LDA) showed a maximum accuracy of 60%, whereas non-augmented data classified by a convolutional neural network (CNN) provided the highest classification accuracy of 73%. Notably, after augmenting the data with DCGAN, the classification accuracy increases dramatically to 96%. In the time series data, statistically significant differences were noticed in the data before and after BB stimulation, which showed an improvement in the brain state, in line with the classification results. These findings illustrate the ability to detect changes in brain states with high accuracy using fNIRS, underline the need for larger datasets, and demonstrate that data augmentation can significantly help when data are scarce in the case of brain signals.
format article
id aus_972b29ef278fbbd1e3299a9ef96f2034
identifier_str_mv Khan, M.N.A.; Zahour, N.; Tariq, U.; Masri, G.; Almadani, I.F.; Al-Nashah, H. Exploring Effects of Mental Stress with Data Augmentation and Classification Using fNIRS. Sensors 2025, 25, 428. https://doi.org/10.3390/s25020428
1424-8220
10.3390/s25020428
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/26085
publishDate 2025
publisher.none.fl_str_mv MDPI
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Exploring Effects of Mental Stress with Data Augmentation and Classification Using fNIRSKhan, Malik Nasir AfzalZahour, NadaTariq, UsmanMasri, GhinwaAlmadani, Ismat F.Al-Nashah, HasanFunctional near-infrared spectroscopy (fNIRS)Hemodynamic responseDeep convolutional generative adversarial network (DCGAN)Feed-forward neural networkLinear support vector machinesDecision treeRestricted Boltzmann machineConvolutional neural networksClassificationBinaural beatsAccurately identifying and discriminating between different brain states is a major emphasis of functional brain imaging research. Various machine learning techniques play an important role in this regard. However, when working with a small number of study participants, the lack of sufficient data and achieving meaningful classification results remain a challenge. In this study, we employ a classification strategy to explore stress and its impact on spatial activation patterns and brain connectivity caused by the Stroop color–word task (SCWT). To improve our results and increase our dataset, we use data augmentation with a deep convolutional generative adversarial network (DCGAN). The study is carried out at two separate times of day (morning and evening) and involves 21 healthy participants. Additionally, we introduce binaural beats (BBs) stimulation to investigate its potential for stress reduction. The morning session includes a control phase with 10 SCWT trials, whereas the afternoon session is divided into three phases: stress, mitigation (with 16 Hz BB stimulation), and post-mitigation, each with 10 SCWT trials. For a comprehensive evaluation, the acquired fNIRS data are classified using a variety of machine-learning approaches. Linear discriminant analysis (LDA) showed a maximum accuracy of 60%, whereas non-augmented data classified by a convolutional neural network (CNN) provided the highest classification accuracy of 73%. Notably, after augmenting the data with DCGAN, the classification accuracy increases dramatically to 96%. In the time series data, statistically significant differences were noticed in the data before and after BB stimulation, which showed an improvement in the brain state, in line with the classification results. These findings illustrate the ability to detect changes in brain states with high accuracy using fNIRS, underline the need for larger datasets, and demonstrate that data augmentation can significantly help when data are scarce in the case of brain signals.American University of SharjahCollege of EngineeringDepartment of Electrical EngineeringMDPI2025-06-02T08:55:12Z2025-06-02T08:55:12Z2025-01Peer-ReviewedPublished versioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfKhan, M.N.A.; Zahour, N.; Tariq, U.; Masri, G.; Almadani, I.F.; Al-Nashah, H. Exploring Effects of Mental Stress with Data Augmentation and Classification Using fNIRS. Sensors 2025, 25, 428. https://doi.org/10.3390/s250204281424-8220https://hdl.handle.net/11073/2608510.3390/s25020428en_UShttps://doi.org/10.3390/s25020428oai:repository.aus.edu:11073/260852025-06-02T11:53:34Z
spellingShingle Exploring Effects of Mental Stress with Data Augmentation and Classification Using fNIRS
Khan, Malik Nasir Afzal
Functional near-infrared spectroscopy (fNIRS)
Hemodynamic response
Deep convolutional generative adversarial network (DCGAN)
Feed-forward neural network
Linear support vector machines
Decision tree
Restricted Boltzmann machine
Convolutional neural networks
Classification
Binaural beats
status_str publishedVersion
title Exploring Effects of Mental Stress with Data Augmentation and Classification Using fNIRS
title_full Exploring Effects of Mental Stress with Data Augmentation and Classification Using fNIRS
title_fullStr Exploring Effects of Mental Stress with Data Augmentation and Classification Using fNIRS
title_full_unstemmed Exploring Effects of Mental Stress with Data Augmentation and Classification Using fNIRS
title_short Exploring Effects of Mental Stress with Data Augmentation and Classification Using fNIRS
title_sort Exploring Effects of Mental Stress with Data Augmentation and Classification Using fNIRS
topic Functional near-infrared spectroscopy (fNIRS)
Hemodynamic response
Deep convolutional generative adversarial network (DCGAN)
Feed-forward neural network
Linear support vector machines
Decision tree
Restricted Boltzmann machine
Convolutional neural networks
Classification
Binaural beats
url https://hdl.handle.net/11073/26085