{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T07:18:28Z","timestamp":1791271108756,"version":"4.1.0"},"reference-count":66,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T00:00:00Z","timestamp":1751587200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Hum. Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Motor imagery-based brain-computer interfaces (BCIs) are a technique for decoding and classifying the intention of motor execution, solely based on imagined (rather than executed) movements. Although deep learning techniques have increased the potential of BCIs, the complexity of decoding unilateral upper limb motor imagery remains challenging. To understand whether neurophysiological features, which are directly related to neural mechanisms of motor imagery, might influence classification accuracy, most studies have largely leveraged traditional machine learning frameworks, leaving deep learning-based techniques underexplored.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this work, three different deep learning models from the literature (EEGNet, FBCNet, NFEEG) and two common spatial pattern-based machine learning classifiers (SVM, LDA) were used to classify imagined right elbow flexion and extension from participants using electroencephalography data. From two recorded resting states (eyes-open, eyes-closed), absolute and relative alpha and beta power of the frontal, fronto-central and central electrodes were used to predict the accuracy of the different classifiers.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The prediction of classifier accuracies by neurophysiological features revealed negative correlations between the relative alpha band and classifier accuracies and positive correlations between the absolute and relative beta band and classifiers accuracies. Most ipsilateral EEG channels yielded significant correlations with classifier accuracies, especially for the machine learning classifier.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>This pattern contrasts with previous findings from bilateral MI paradigms, where contralateral alpha and beta activity were more influential. These inverted correlations suggest task-specific neurophysiological mechanisms in unilateral MI, emphasizing the role of ipsilateral inhibition and attentional processes.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnhum.2025.1617748","type":"journal-article","created":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T08:41:46Z","timestamp":1751618506000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Neurophysiological predictors of deep learning based unilateral upper limb motor imagery classification"],"prefix":"10.3389","volume":"19","author":[{"given":"Justin","family":"Sonntag","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xilu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Schack","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,7,4]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"100003","DOI":"10.1016\/j.array.2019.100003","article-title":"Signal processing techniques for motor imagery brain computer interface: a review","volume":"1","author":"Aggarwal","year":"2019","journal-title":"Array"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"e80886","DOI":"10.1371\/journal.pone.0080886","article-title":"High Theta and low alpha powers may be indicative of BCI-illiteracy in motor imagery","volume":"8","author":"Ahn","year":"2013","journal-title":"PLoS One"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"106081","DOI":"10.1016\/j.bspc.2024.106081","article-title":"NF-EEG: a generalized CNN model for multi class EEG motor imagery classification without signal preprocessing for brain computer interfaces","volume":"92","author":"Ar\u0131","year":"2024","journal-title":"Biomed. Signal Process. Control."},{"key":"ref9008","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1016\/j.clinph.2015.04.068","article-title":"Alpha, beta and gamma electrocorticographic rhythms in somatosensory, motor, premotor and prefrontal cortical areas differ in movement execution and observation in humans","volume":"127","author":"Babiloni","year":"2015","journal-title":"Clin Neurophysiol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"e0130140","DOI":"10.1371\/journal.pone.0130140","article-title":"On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation","volume":"10","author":"Bach","year":"2015","journal-title":"PLoS One"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e14077","DOI":"10.1111\/psyp.14077","article-title":"The role of the primary motor cortex in motor imagery: a theta burst stimulation study","volume":"59","author":"Barhoun","year":"2022","journal-title":"Psychophysiology"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-57263-4","volume-title":"Neurowissenschaften","author":"Bear","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1303","DOI":"10.1016\/j.neuroimage.2010.03.022","article-title":"Neurophysiological predictor of SMR-based BCI performance","volume":"51","author":"Blankertz","year":"2010","journal-title":"NeuroImage"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"14783","DOI":"10.1523\/JNEUROSCI.2039-14.2014","article-title":"Distinct roles for alpha- and Beta-band oscillations during mental simulation of goal-directed actions","volume":"34","author":"Brinkman","year":"2014","journal-title":"J. Neurosci."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1017\/S0317167100032947","article-title":"Role of the ipsilateral motor cortex in voluntary movement","volume":"24","author":"Chen","year":"1997","journal-title":"Can. J. Neurol. Sci."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1184","DOI":"10.3758\/s13415-019-00745-9","article-title":"The wandering mind oscillates: EEG alpha power is enhanced during moments of mind-wandering","volume":"19","author":"Compton","year":"2019","journal-title":"Cogn. Affect. Behav. Neurosci."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"7","DOI":"10.3389\/neuro.09.007.2008","article-title":"Interactions between posterior gamma and frontal alpha\/beta oscillations during imagined actions","volume":"2","author":"De Lange","year":"2008","journal-title":"Front. Hum. Neurosci."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"3304","DOI":"10.1152\/jn.01113.2002","article-title":"Imagery of voluntary movement of fingers, toes, and tongue activates corresponding body-part-specific motor representations","volume":"90","author":"Ehrsson","year":"2003","journal-title":"J. Neurophysiol."},{"key":"ref14","volume-title":"Discovering statistics using IBM SPSS statistics","author":"Field","year":"2013"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1186\/s12984-017-0294-2","article-title":"Ipsilateral EEG mu rhythm reflects the excitability of uncrossed pathways projecting to shoulder muscles","volume":"14","author":"Hasegawa","year":"2017","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1016\/j.neubiorev.2013.03.017","article-title":"The neural network of motor imagery: an ALE meta-analysis","volume":"37","author":"H\u00e9tu","year":"2013","journal-title":"Neurosci. Biobehav. Rev."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"6672","DOI":"10.3390\/s21196672","article-title":"Multi-domain convolutional neural networks for lower-limb motor imagery using dry vs. wet electrodes","volume":"21","author":"Jeong","year":"2021","journal-title":"Sensors"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1226","DOI":"10.1109\/TNSRE.2020.2981659","article-title":"Brain-controlled robotic arm system based on multi-directional CNN-BiLSTM network using EEG signals","volume":"28","author":"Jeong","year":"2020","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"663101","DOI":"10.3389\/fnins.2021.663101","article-title":"Effects of frontal Theta rhythms in a prior resting state on the subsequent motor imagery brain-computer Interface performance","volume":"15","author":"Kang","year":"2021","journal-title":"Front. Neurosci."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1016\/j.neuroimage.2007.11.040","article-title":"The suppressive influence of SMA on M1 in motor imagery revealed by fMRI and dynamic causal modeling","volume":"40","author":"Kasess","year":"2008","journal-title":"NeuroImage"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.expneurol.2012.09.014","article-title":"The ups and downs of beta oscillations in sensorimotor cortex","volume":"245","author":"Kilavik","year":"2013","journal-title":"Exp. Neurol."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1016\/S0167-8760(97)00773-3","article-title":"EEG-alpha rhythms and memory processes","volume":"26","author":"Klimesch","year":"1997","journal-title":"Int. J. Psychophysiol."},{"key":"ref9006","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-981-13-0908-3_3","article-title":"EEG Spectral analysis","author":"Kim","year":"2018","journal-title":"In Biological and medical physics series"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"690","DOI":"10.3390\/electronics9040690","article-title":"Use of both eyes-open and eyes-closed resting states may yield a more robust predictor of motor imagery BCI performance","volume":"9","author":"Kwon","year":"2020","journal-title":"Electronics"},{"key":"ref26","volume-title":"MNE-Python (v1.7.0) [Computer software]","author":"Larson","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"056013","DOI":"10.1088\/1741-2552\/aace8c","article-title":"EEGNet: a compact convolutional neural network for EEG-based brain\u2013computer interfaces","volume":"15","author":"Lawhern","year":"2018","journal-title":"J. Neural Eng."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1016\/j.jphysparis.2006.03.012","article-title":"Motor imagery","volume":"99","author":"Lotze","year":"2006","journal-title":"J. Physiol. Paris"},{"key":"ref30","first-page":"30","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1038\/s41597-020-0535-2","article-title":"Multi-channel EEG recording during motor imagery of different joints from the same limb","volume":"7","author":"Ma","year":"2020","journal-title":"Sci. Data"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2104.01233","article-title":"FBCNet: a multi-view convolutional neural network for brain-computer interface","author":"Mane","year":"2021","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"24076","DOI":"10.1038\/srep24076","article-title":"Quantifying the role of motor imagery in brain-machine interfaces","volume":"6","author":"Marchesotti","year":"2016","journal-title":"Sci. Rep."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1800","DOI":"10.1152\/jn.90531.2008","article-title":"Complex organization of human primary motor cortex: a high-resolution fMRI study","volume":"100","author":"Meier","year":"2008","journal-title":"J. Neurophysiol."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/MEMB.2009.935475","article-title":"Invasive or noninvasive: understanding brain-machine Interface technology conversations in BME","volume":"29","author":"Milan","year":"2010","journal-title":"IEEE Eng. Med. Biol. Mag."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"103","DOI":"10.7600\/jpfsm.1.103","article-title":"Motor imagery and sport performance","volume":"1","author":"Mizuguchi","year":"2012","journal-title":"J. Phys. Fit. Sports Med."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/0028-3932(71)90067-4","article-title":"The assessment and analysis of handedness: the Edinburgh inventory","volume":"9","author":"Oldfield","year":"1971","journal-title":"Neuropsychologia"},{"key":"ref9007","first-page":"214","article-title":"Correlation coefficient","volume":"58","author":"Pearson","year":"1895","journal-title":"In Royal Society Proceedings"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"6285","DOI":"10.3390\/s21186285","article-title":"Motor-imagery EEG-based BCIs in wheelchair movement and control: a systematic literature review","volume":"21","author":"Palumbo","year":"2021","journal-title":"Sensors"},{"key":"ref9001","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/0013-4694(95)00258-8","article-title":"Post-movement beta synchronization. A correlate of an idling motor area?","volume":"98","author":"Pfurtscheller","year":"1996","journal-title":"Electroencephalogr Clin Neurophysiol"},{"key":"ref9002","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1016\/s0013-4694(97)00080-1","article-title":"EEG-based discrimination between imagination of right and left hand movement","volume":"103","author":"Pfurtscheller","year":"1997","journal-title":"Electroencephalogr Clin Neurophysiol"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.neuroimage.2005.12.003","article-title":"Mu rhythm (de)synchronization and EEG single-trial classification of different motor imagery tasks","volume":"31","author":"Pfurtscheller","year":"2006","journal-title":"NeuroImage"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.neulet.2004.12.034","article-title":"Beta rebound after different types of motor imagery in man","volume":"378","author":"Pfurtscheller","year":"2005","journal-title":"Neurosci. Lett."},{"key":"ref43","doi-asserted-by":"publisher","first-page":"2940","DOI":"10.1016\/j.cub.2014.10.043","article-title":"Prefrontal control over Motor cortex cycles at Beta frequency during movement inhibition","volume":"24","author":"Picazio","year":"2014","journal-title":"Curr. Biol."},{"key":"ref44","first-page":"152","article-title":"The paradigm design of a novel 2-class unilateral upper limb motor imagery tasks and its EEG signal classification","author":"Qiu","year":"2021"},{"key":"ref45","first-page":"1135","article-title":"\u201cWhy Should I Trust You?\u201d: Explaining the predictions of any classifier","author":"Ribeiro","year":"2016"},{"key":"ref46","first-page":"103","article-title":"Incep-EEGNet: A ConvNet for motor imagery decoding","volume-title":"Lecture notes in computer science","author":"Riyad","year":""},{"key":"ref9010","doi-asserted-by":"publisher","first-page":"109037","DOI":"10.1016\/j.jneumeth.2020.109037","article-title":"MI-EEGNET: A novel convolutional neural network for motor imagery classification","volume":"353","author":"Riyad","year":"","journal-title":"J. Neurosci. Methods"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"5064","DOI":"10.1038\/s41598-020-61866-7","article-title":"Resting-state EEG activity predicts frontoparietal network reconfiguration and improved attentional performance","volume":"10","author":"Rogala","year":"2020","journal-title":"Sci. Rep."},{"key":"ref48","doi-asserted-by":"publisher","first-page":"066020","DOI":"10.1088\/1741-2552\/aca220","article-title":"Data augmentation for learning predictive models on EEG: a systematic comparison","volume":"19","author":"Rommel","year":"2022","journal-title":"J. Neural Eng."},{"key":"ref49","doi-asserted-by":"publisher","first-page":"2074","DOI":"10.1523\/JNEUROSCI.1292-14.2015","article-title":"Attention drives synchronization of alpha and Beta rhythms between right inferior frontal and primary sensory neocortex","volume":"35","author":"Sacchet","year":"2015","journal-title":"J. Neurosci."},{"key":"ref50","doi-asserted-by":"publisher","first-page":"17810","DOI":"10.1073\/pnas.0504678102","article-title":"Brain signals for spatial attention predict performance in a motion discrimination task","volume":"102","author":"Sapir","year":"2005","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref51","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1109\/TNSRE.2024.3360194","article-title":"Subject-independent deep architecture for EEG-based motor imagery classification","volume":"32","author":"Sartipi","year":"2024","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref52","doi-asserted-by":"publisher","first-page":"328","DOI":"10.3389\/fnhum.2014.00328","article-title":"Mental representation and motor imagery training","volume":"8","author":"Schack","year":"2014","journal-title":"Front. Hum. Neurosci."},{"key":"ref9009","doi-asserted-by":"publisher","first-page":"8231","DOI":"10.1523\/jneurosci.1163-19.2019","article-title":"Beta oscillations in working memory, executive control of movement and thought, and sensorimotor function","volume":"39","author":"Schmidt","year":"2019","journal-title":"J. Neurosci"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1611.07450","article-title":"Grad-cam: why did you say that?","author":"Selvaraju","year":"2016","journal-title":"arXiv"},{"key":"ref9005","doi-asserted-by":"publisher","first-page":"32679","DOI":"10.1109\/access.2024.3371904","article-title":"A study of unilateral upper limb fine motor imagery decoding using Frequency-Band Attention Network","volume":"12","author":"Shi","year":"2024","journal-title":"IEEE Access"},{"key":"ref54","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1016\/j.neuron.2008.09.010","article-title":"Neuronal synchronization along the dorsal visual pathway reflects the focus of spatial attention","volume":"60","author":"Siegel","year":"2008","journal-title":"Neuron"},{"key":"ref55","doi-asserted-by":"publisher","first-page":"103612","DOI":"10.1016\/j.bspc.2022.103612","article-title":"LSDD-EEGNet: an efficient end-to-end framework for EEG-based depression detection","volume":"75","author":"Song","year":"2022","journal-title":"Biomed. Signal Process. Control"},{"key":"ref56","doi-asserted-by":"publisher","first-page":"e48065","DOI":"10.7554\/eLife.48065","article-title":"Electrocorticographic dissociation of alpha and beta rhythmic activity in the human sensorimotor system","volume":"8","author":"Stolk","year":"2019","journal-title":"eLife"},{"key":"ref57","doi-asserted-by":"publisher","first-page":"312","DOI":"10.3389\/fnhum.2018.00312","article-title":"EEG-based BCI control schemes for lower-limb assistive-robots","volume":"12","author":"Tariq","year":"2018","journal-title":"Front. Hum. Neurosci."},{"key":"ref59","doi-asserted-by":"publisher","first-page":"2088","DOI":"10.1111\/j.1460-9568.2012.08122.x","article-title":"Differential modulations of ipsilateral and contralateral beta (de)synchronization during unimanual force production","volume":"36","author":"Van Wijk","year":"2012","journal-title":"Eur. J. Neurosci."},{"key":"ref60","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1016\/S0926-6410(01)00025-8","article-title":"Temporal evolution of \u03b1 and \u03b2 bands during visual spatial attention","volume":"12","author":"V\u00e1zquez Marrufo","year":"2001","journal-title":"Cogn. Brain Res."},{"key":"ref61","doi-asserted-by":"publisher","first-page":"1556","DOI":"10.3390\/e24111556","article-title":"Resting-state EEG in alpha rhythm may be indicative of the performance of motor imagery-based brain\u2013computer interface","volume":"24","author":"Wang","year":"2022","journal-title":"Entropy"},{"key":"ref62","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1109\/TAU.1967.1161901","article-title":"The use of fast Fourier transform for the estimation of power spectra: a method based on time averaging over short, modified periodograms","volume":"15","author":"Welch","year":"1967","journal-title":"IEEE Trans. Audio Electroacoust."},{"key":"ref63","doi-asserted-by":"publisher","first-page":"1129049","DOI":"10.3389\/fnins.2023.1129049","article-title":"Recognition of single upper limb motor imagery tasks from EEG using multi-branch fusion convolutional neural network","volume":"17","author":"Zhang","year":"2023","journal-title":"Front. Neurosci."},{"key":"ref64","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1007\/s10548-015-0429-3","article-title":"Predicting inter-session performance of SMR-based brain\u2013computer interface using the spectral entropy of resting-state EEG","volume":"28","author":"Zhang","year":"2015","journal-title":"Brain Topogr."},{"key":"ref9004","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2022.831995","article-title":"Neurofeedback training of alpha relative power improves the performance of motor imagery Brain-Computer Interface","volume":"16","author":"Zhou","year":"2022","journal-title":"Front. Hum. Neurosci"}],"container-title":["Frontiers in Human Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnhum.2025.1617748\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T08:41:48Z","timestamp":1751618508000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnhum.2025.1617748\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,4]]},"references-count":66,"alternative-id":["10.3389\/fnhum.2025.1617748"],"URL":"https:\/\/doi.org\/10.3389\/fnhum.2025.1617748","relation":{},"ISSN":["1662-5161"],"issn-type":[{"value":"1662-5161","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,4]]},"article-number":"1617748"}}