{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T20:02:00Z","timestamp":1793822520022,"version":"4.6.1"},"reference-count":53,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T00:00:00Z","timestamp":1744848000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003661","name":"Korea Institute for Advancement of Technology","doi-asserted-by":"publisher","award":["RS-2024-00406796"],"award-info":[{"award-number":["RS-2024-00406796"]}],"id":[{"id":"10.13039\/501100003661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>The functional near-infrared spectroscopy-based brain-computer interface (fNIRS-BCI) systems recognize patterns in brain signals and generate control commands, thereby enabling individuals with motor disabilities to regain autonomy. In this study hand gripping data is acquired using fNIRS neuroimaging system, preprocessing is performed using nirsLAB and features extraction is performed using deep learning (DL) Algorithms. For feature extraction and classification stack and fft methods are proposed. Convolutional neural networks (CNN), long short-term memory (LSTM), and bidirectional long-short-term memory (Bi-LSTM) are employed to extract features. The stack method classifies these features using a stack model and the fft method enhances features by applying fast Fourier transformation which is followed by classification using a stack model. The proposed methods are applied to fNIRS signals from twenty participants engaged in a two-class hand-gripping motor activity. The classification performance of the proposed methods is compared with conventional CNN, LSTM, and Bi-LSTM algorithms and one another. The proposed fft and stack methods yield 90.11% and 87.00% classification accuracies respectively, which are significantly higher than those achieved by CNN (85.16%), LSTM (79.46%), and Bi-LSTM (81.88%) conventional algorithms. The results show that the proposed stack and fft methods can be effectively used for the classification of the two and three-class problems in fNIRS-BCI applications.<\/jats:p>","DOI":"10.1371\/journal.pone.0314447","type":"journal-article","created":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T17:35:05Z","timestamp":1744911305000},"page":"e0314447","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":7,"title":["Improved performance of fNIRS-BCI by stacking of deep learning-derived frequency domain features"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2403-7395","authenticated-orcid":true,"given":"Jamila","family":"Akhter","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2036-9601","authenticated-orcid":true,"given":"Hammad","family":"Nazeer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2680-6403","authenticated-orcid":true,"given":"Noman","family":"Naseer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4583-0624","authenticated-orcid":true,"given":"Rehan","family":"Naeem","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karam Dad","family":"Kallu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiye","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4316-0074","authenticated-orcid":true,"given":"Seong Young","family":"Ko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,4,17]]},"reference":[{"key":"pone.0314447.ref001","doi-asserted-by":"crossref","unstructured":"Bhuvaneshwari M, Kanaga EGM, Anitha J, Raimond K, George ST. A comprehensive review on deep learning techniques for a BCI-based communication system. Demystifying big data, machine learning, and deep learning for healthcare analytics. 2021. p. 131\u2013157. doi: 10.1016\/b978-0-12-821633-0.00013-1","DOI":"10.1016\/B978-0-12-821633-0.00013-1"},{"issue":"4","key":"pone.0314447.ref002","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/j.irbm.2021.07.001","article-title":"Brain-computer interface speller system for alternative communication: a review","volume":"43","author":"S Kundu","year":"2022","journal-title":"IRBM"},{"key":"pone.0314447.ref003","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1186\/1743-0003-5-10","article-title":"Human-machine interfaces based on EMG and EEG applied to robotic systems","volume":"5","author":"A Ferreira","year":"2008","journal-title":"J Neuroeng Rehabil"},{"issue":"24","key":"pone.0314447.ref004","doi-asserted-by":"crossref","first-page":"7309","DOI":"10.3390\/s20247309","article-title":"Developing a motor imagery-based real-time asynchronous hybrid bci controller for a lower-limb exoskeleton","volume":"20","author":"J Choi","year":"2020","journal-title":"Sensors (Basel)"},{"issue":"23","key":"pone.0314447.ref005","doi-asserted-by":"crossref","first-page":"12253","DOI":"10.3390\/app122312253","article-title":"Review on BCI virtual rehabilitation and remote technology based on EEG for assistive devices","volume":"12","author":"AG Lazcano-Herrera","year":"2022","journal-title":"Appl Sci"},{"issue":"11","key":"pone.0314447.ref006","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1016\/j.tibtech.2010.08.002","article-title":"Neuroimaging-based approaches in the brain-computer interface","volume":"28","author":"B-K Min","year":"2010","journal-title":"Trends Biotechnol"},{"key":"pone.0314447.ref007","doi-asserted-by":"crossref","first-page":"2793211","DOI":"10.1155\/2023\/2793211","article-title":"Identifying thematics in a brain-computer interface research","volume":"2023","author":"H Alharbi","year":"2023","journal-title":"Comput Intell Neurosci"},{"key":"pone.0314447.ref008","doi-asserted-by":"crossref","unstructured":"Hassani K, Lee W-S. An experimental study on semi-invasive acupuncture-based EEG signal acquisition. In: The 3rd international winter conference on brain-computer interface. 2015. p. 1\u20134. doi: 10.1109\/iww-bci.2015.7073048","DOI":"10.1109\/IWW-BCI.2015.7073048"},{"key":"pone.0314447.ref009","doi-asserted-by":"crossref","first-page":"2042","DOI":"10.1109\/TNSRE.2022.3192543","article-title":"Minimally invasive local-skull electrophysiological modification with piezoelectric drill","volume":"30","author":"Y Sun","year":"2022","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"issue":"6","key":"pone.0314447.ref010","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1053\/j.semnuclmed.2013.06.003","article-title":"An overview of PET neuroimaging","volume":"43","author":"I Nasrallah","year":"2013","journal-title":"Semin Nucl Med"},{"key":"pone.0314447.ref011","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.aip.2017.05.004","article-title":"Functional near-infrared spectroscopy assessment of reward perception based on visual self-expression: Coloring, doodling, and free drawing","volume":"55","author":"G Kaimal","year":"2017","journal-title":"Arts Psychother"},{"key":"pone.0314447.ref012","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.neulet.2013.08.021","article-title":"Classification of functional near-infrared spectroscopy signals corresponding to the right- and left-wrist motor imagery for development of a brain-computer interface","volume":"553","author":"N Naseer","year":"2013","journal-title":"Neurosci Lett"},{"key":"pone.0314447.ref013","doi-asserted-by":"crossref","first-page":"613254","DOI":"10.3389\/fnhum.2020.613254","article-title":"Analysis of human gait using hybrid EEG-fNIRS-based BCI system: a review","volume":"14","author":"H Khan","year":"2021","journal-title":"Front Hum Neurosci"},{"key":"pone.0314447.ref014","doi-asserted-by":"crossref","first-page":"107641","DOI":"10.1016\/j.cmpb.2023.107641","article-title":"MBGA-Net: A multi-branch graph adaptive network for individualized motor imagery EEG classification","volume":"240","author":"W Ma","year":"2023","journal-title":"Comput Methods Programs Biomed"},{"issue":"4","key":"pone.0314447.ref015","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1002\/jmri.21049","article-title":"The Alzheimer\u2019s disease neuroimaging initiative (ADNI): MRI methods","volume":"27","author":"Jr Jack CR","year":"2008","journal-title":"J Magn Reson Imaging"},{"issue":"5","key":"pone.0314447.ref016","doi-asserted-by":"crossref","first-page":"1932","DOI":"10.3390\/s22051932","article-title":"Analyzing classification performance of fNIRS-BCI for gait rehabilitation using deep neural networks","volume":"22","author":"H Hamid","year":"2022","journal-title":"Sensors (Basel)"},{"issue":"5","key":"pone.0314447.ref017","doi-asserted-by":"crossref","first-page":"056025","DOI":"10.1088\/1741-2552\/abb417","article-title":"Enhancing classification accuracy of fNIRS-BCI using features acquired from vector-based phase analysis","volume":"17","author":"H Nazeer","year":"2020","journal-title":"J Neural Eng"},{"key":"pone.0314447.ref018","doi-asserted-by":"crossref","unstructured":"Jawad Khan M, Hong K-S, Naseer N, Bhutta MR. Drowsiness detection in dorsolateral-prefrontal cortex using fNIRS for a passive-BCI. In: 2015 15th international conference on control, automation and systems (ICCAS). 2015. p. 1811\u20131816. doi: 10.1109\/iccas.2015.7364653","DOI":"10.1109\/ICCAS.2015.7364653"},{"key":"pone.0314447.ref019","doi-asserted-by":"crossref","first-page":"109262","DOI":"10.1016\/j.jneumeth.2021.109262","article-title":"Correcting physiological noise in whole-head functional near-infrared spectroscopy","volume":"360","author":"F Zhang","year":"2021","journal-title":"J Neurosci Methods"},{"key":"pone.0314447.ref020","doi-asserted-by":"crossref","first-page":"104110","DOI":"10.1016\/j.bspc.2022.104110","article-title":"fNIRS: Non-stationary preprocessing methods","volume":"79","author":"D Patashov","year":"2023","journal-title":"Biomed Signal Process Control"},{"key":"pone.0314447.ref021","first-page":"467061","article-title":"Impact of global normalization in FMRI acupuncture studies","volume":"2012","author":"J Sun","year":"2012","journal-title":"Evid Based Complement Alternat Med"},{"issue":"5","key":"pone.0314447.ref022","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1089\/brain.2011.0018","article-title":"Empirical evaluations of slice-timing, smoothing, and normalization effects in seed-based, resting-state functional magnetic resonance imaging analyses","volume":"1","author":"CW Wu","year":"2011","journal-title":"Brain Connect"},{"issue":"1","key":"pone.0314447.ref023","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/j.ijpsycho.2008.12.018","article-title":"Mining EEG-fMRI using independent component analysis","volume":"73","author":"T Eichele","year":"2009","journal-title":"Int J Psychophysiol"},{"issue":"23","key":"pone.0314447.ref024","doi-asserted-by":"crossref","first-page":"6995","DOI":"10.3390\/s20236995","article-title":"Enhancing classification performance of fNIRS-BCI by identifying cortically active channels using the z-score method","volume":"20","author":"H Nazeer","year":"2020","journal-title":"Sensors (Basel)"},{"key":"pone.0314447.ref025","doi-asserted-by":"crossref","first-page":"985","DOI":"10.1016\/j.neuroimage.2013.04.126","article-title":"Self-regulation of human brain activity using simultaneous real-time fMRI and EEG neurofeedback","volume":"85","author":"V Zotev","year":"2014","journal-title":"Neuroimage"},{"issue":"3","key":"pone.0314447.ref026","doi-asserted-by":"crossref","first-page":"1214","DOI":"10.1016\/j.neuroimage.2004.03.027","article-title":"Validating the independent components of neuroimaging time series via clustering and visualization","volume":"22","author":"J Himberg","year":"2004","journal-title":"Neuroimage"},{"key":"pone.0314447.ref027","doi-asserted-by":"crossref","unstructured":"Khalil MA, Ramirez M, Can J, George K. Implementation of machine learning in BCI based lie detection. In: 2022 IEEE World AI IoT congress (AIIoT). 2022. p. 213\u2013217. doi: 10.1109\/aiiot54504.2022.9817162","DOI":"10.1109\/AIIoT54504.2022.9817162"},{"issue":"8","key":"pone.0314447.ref028","doi-asserted-by":"crossref","first-page":"3051","DOI":"10.3390\/s22083051","article-title":"Improved cognitive vigilance assessment after artifact reduction with wavelet independent component analysis","volume":"22","author":"N Abu Farha","year":"2022","journal-title":"Sensors (Basel)"},{"key":"pone.0314447.ref029","doi-asserted-by":"crossref","first-page":"107944","DOI":"10.1016\/j.cmpb.2023.107944","article-title":"Fractal Dimension as a discriminative feature for high accuracy classification in motor imagery EEG-based brain-computer interface","volume":"244","author":"S Moaveninejad","year":"2024","journal-title":"Comput Methods Programs Biomed"},{"issue":"1","key":"pone.0314447.ref030","doi-asserted-by":"crossref","first-page":"317","DOI":"10.3390\/app12010317","article-title":"Att-BiL-SL: attention-based Bi-LSTM and sequential LSTM for describing video in the textual formation","volume":"12","author":"S Ahmed","year":"2021","journal-title":"Appl Sci"},{"issue":"6","key":"pone.0314447.ref031","doi-asserted-by":"crossref","first-page":"2559","DOI":"10.1109\/JBHI.2022.3140531","article-title":"Transformer model for functional near-infrared spectroscopy classification","volume":"26","author":"Z Wang","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"key":"pone.0314447.ref032","doi-asserted-by":"crossref","article-title":"Improved estimation of hemodynamic response in fNIRS using protocol constraint and wavelet transform decomposition based adaptive algorithm","author":"S Jahani","DOI":"10.1101\/2020.04.25.062000"},{"key":"pone.0314447.ref033","doi-asserted-by":"crossref","first-page":"569508","DOI":"10.3389\/fnhum.2020.569508","article-title":"Performance improvement for detecting brain function using fNIRS: a multi-distance probe configuration with PPL method","volume":"14","author":"X Chen","year":"2020","journal-title":"Front Hum Neurosci"},{"issue":"4","key":"pone.0314447.ref034","doi-asserted-by":"crossref","first-page":"2808","DOI":"10.1016\/j.neuroimage.2010.10.069","article-title":"A quantitative comparison of NIRS and fMRI across multiple cognitive tasks","volume":"54","author":"X Cui","year":"2011","journal-title":"Neuroimage"},{"issue":"5","key":"pone.0314447.ref035","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1007\/s10548-016-0507-1","article-title":"Effective connectivity of cortical sensorimotor networks during finger movement tasks: a simultaneous fNIRS, fMRI, EEG study","volume":"29","author":"AR Anwar","year":"2016","journal-title":"Brain Topogr"},{"issue":"21","key":"pone.0314447.ref036","doi-asserted-by":"crossref","first-page":"20695","DOI":"10.1109\/JSEN.2022.3205956","article-title":"Multimodal multitask neural network for motor imagery classification with EEG and fNIRS signals","volume":"22","author":"Q He","year":"2022","journal-title":"IEEE Sensors J"},{"issue":"10","key":"pone.0314447.ref037","doi-asserted-by":"crossref","first-page":"3040","DOI":"10.3390\/s24103040","article-title":"Enhancing classification accuracy with integrated contextual gate network: deep learning approach for functional near-infrared spectroscopy brain-computer interface application","volume":"24","author":"J Akhter","year":"2024","journal-title":"Sensors (Basel)"},{"key":"pone.0314447.ref038","doi-asserted-by":"crossref","first-page":"117944","DOI":"10.1109\/ACCESS.2024.3443066","article-title":"Enhancing classification accuracy of fNIRS-BCI for gait rehabilitation","volume":"12","author":"H Shabbir Minhas","year":"2024","journal-title":"IEEE Access"},{"issue":"1","key":"pone.0314447.ref039","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1364\/AO.36.000021","article-title":"Theoretical and experimental investigation of near-infrared light propagation in a model of the adult head","volume":"36","author":"E Okada","year":"1997","journal-title":"Appl Opt"},{"issue":"2","key":"pone.0314447.ref040","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1007\/s00221-013-3764-1","article-title":"Online binary decision decoding using functional near-infrared spectroscopy for the development of brain-computer interface","volume":"232","author":"N Naseer","year":"2014","journal-title":"Exp Brain Res"},{"key":"pone.0314447.ref041","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.neulet.2013.08.021","article-title":"Classification of functional near-infrared spectroscopy signals corresponding to the right- and left-wrist motor imagery for development of a brain-computer interface","volume":"553","author":"N Naseer","year":"2013","journal-title":"Neurosci Lett"},{"issue":"12","key":"pone.0314447.ref042","doi-asserted-by":"crossref","first-page":"1486","DOI":"10.3390\/electronics8121486","article-title":"Open-access fNIRS dataset for classification of unilateral finger- and foot-tapping","volume":"8","author":"S Bak","year":"2019","journal-title":"Electronics"},{"key":"pone.0314447.ref043","doi-asserted-by":"crossref","first-page":"683735","DOI":"10.3389\/fninf.2021.683735","article-title":"NIRS-ICA: A MATLAB toolbox for independent component analysis applied in fNIRS studies","volume":"15","author":"Y Zhao","year":"2021","journal-title":"Front Neuroinform"},{"issue":"8","key":"pone.0314447.ref044","doi-asserted-by":"crossref","first-page":"3805","DOI":"10.1364\/BOE.9.003805","article-title":"Wavelet-based method for removing global physiological noise in functional near-infrared spectroscopy","volume":"9","author":"L Duan","year":"2018","journal-title":"Biomed Opt Express"},{"issue":"15","key":"pone.0314447.ref045","doi-asserted-by":"crossref","first-page":"5865","DOI":"10.3390\/s22155865","article-title":"Concurrent fNIRS and EEG for brain function investigation: a systematic, methodology-focused review","volume":"22","author":"R Li","year":"2022","journal-title":"Sensors (Basel)"},{"key":"pone.0314447.ref046","doi-asserted-by":"crossref","first-page":"119283","DOI":"10.1016\/j.eswa.2022.119283","article-title":"Matching pursuit-based analysis of fNIRS in combination with cascade PCA and reliefF for mental task recognition","volume":"213","author":"A Goshvarpour","year":"2023","journal-title":"Expert Syst Appl"},{"key":"pone.0314447.ref047","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.neulet.2017.03.013","article-title":"Optimal feature selection from fNIRS signals using genetic algorithms for BCI","volume":"647","author":"FM Noori","year":"2017","journal-title":"Neurosci Lett"},{"key":"pone.0314447.ref048","doi-asserted-by":"crossref","first-page":"33","DOI":"10.3389\/fnbot.2017.00033","article-title":"Enhancing classification performance of functional near-infrared spectroscopy- brain-computer interface using adaptive estimation of general linear model coefficients","volume":"11","author":"NK Qureshi","year":"2017","journal-title":"Front Neurorobot"},{"issue":"4","key":"pone.0314447.ref049","doi-asserted-by":"crossref","first-page":"041411","DOI":"10.1117\/1.NPh.9.4.041411","article-title":"Deep learning in fNIRS: A review","volume":"9","author":"C Eastmond","year":"2022","journal-title":"Neurophotonics"},{"key":"pone.0314447.ref050","doi-asserted-by":"crossref","first-page":"644490","DOI":"10.3389\/fnrgo.2021.644490","article-title":"Task-related hemodynamic response alterations during slacklining: an fNIRS study in advanced slackliners","volume":"2","author":"O Seidel-Marzi","year":"2021","journal-title":"Front Neuroergon"},{"issue":"1","key":"pone.0314447.ref051","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1186\/s12984-018-0346-2","article-title":"fNIRS-based Neurorobotic Interface for gait rehabilitation","volume":"15","author":"RA Khan","year":"2018","journal-title":"J Neuroeng Rehabil"},{"issue":"3","key":"pone.0314447.ref052","doi-asserted-by":"crossref","first-page":"726","DOI":"10.3390\/s22030726","article-title":"fNIRS-based upper limb motion intention recognition using an artificial neural network for transhumeral amputees","volume":"22","author":"NY Sattar","year":"2022","journal-title":"Sensors (Basel)"},{"key":"pone.0314447.ref053","doi-asserted-by":"crossref","unstructured":"Re R, Contini L, Contini D, Orihuela-Espina F, Torricelli AM, Spinelli L. Cerebral resting state oscillations study with TD fNIRS. Diffuse optical spectroscopy and imaging IX. 2023. p. 17. doi: 10.1117\/12.2668895","DOI":"10.1117\/12.2668895"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0314447","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T17:35:19Z","timestamp":1744911319000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0314447"}},"subtitle":[],"editor":[{"given":"Farzan Majeed","family":"Noori","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,4,17]]},"references-count":53,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4,17]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0314447","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,17]]}}}