{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T16:15:18Z","timestamp":1776960918186,"version":"3.51.4"},"reference-count":57,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2021,3,10]],"date-time":"2021-03-10T00:00:00Z","timestamp":1615334400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"PROGRAMA DE INVESTIGACI\u00d3N RECONSTRUCCI\u00d3N DEL TEJIDO SOCIAL EN ZONAS DE POSCONFLICTO EN COLOMBIA C\u00f3digo SIGP: 57579","award":["FP44842-213-2018"],"award-info":[{"award-number":["FP44842-213-2018"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Motor imaging (MI) induces recovery and neuroplasticity in neurophysical regulation. However, a non-negligible portion of users presents insufficient coordination skills of sensorimotor cortex control. Assessments of the relationship between wakefulness and tasks states are conducted to foster neurophysiological and mechanistic interpretation in MI-related applications. Thus, to understand the organization of information processing, measures of functional connectivity are used. Also, models of neural network regression prediction are becoming popular, These intend to reduce the need for extracting features manually. However, predicting MI practicing\u2019s neurophysiological inefficiency raises several problems, like enhancing network regression performance because of the overfitting risk. Here, to increase the prediction performance, we develop a deep network regression model that includes three procedures: leave-one-out cross-validation combined with Monte Carlo dropout layers, subject clustering of MI inefficiency, and transfer learning between neighboring runs. Validation is performed using functional connectivity predictors extracted from two electroencephalographic databases acquired in conditions close to real MI applications (150 users), resulting in a high prediction of pretraining desynchronization and initial training synchronization with adequate physiological interpretability.<\/jats:p>","DOI":"10.3390\/s21061932","type":"journal-article","created":{"date-parts":[[2021,3,10]],"date-time":"2021-03-10T20:51:42Z","timestamp":1615409502000},"page":"1932","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Deep Neural Regression Prediction of Motor Imagery Skills Using EEG Functional Connectivity Indicators"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9561-3800","authenticated-orcid":false,"given":"Julian","family":"Caicedo-Acosta","sequence":"first","affiliation":[{"name":"Signal Processing and Recognition Group, Universidad Nacional de Colombia, Manizales 170001, Colombia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"German A.","family":"Casta\u00f1o","sequence":"additional","affiliation":[{"name":"Grupo de investigaci\u00f3n Cultura de la Calidad en la Educaci\u00f3n, Universidad Nacional de Colombia, Manizales 170001, Colombia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlos","family":"Acosta-Medina","sequence":"additional","affiliation":[{"name":"Signal Processing and Recognition Group, Universidad Nacional de Colombia, Manizales 170001, Colombia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andres","family":"Alvarez-Meza","sequence":"additional","affiliation":[{"name":"Signal Processing and Recognition Group, Universidad Nacional de Colombia, Manizales 170001, Colombia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0138-5489","authenticated-orcid":false,"given":"German","family":"Castellanos-Dominguez","sequence":"additional","affiliation":[{"name":"Signal Processing and Recognition Group, Universidad Nacional de Colombia, Manizales 170001, Colombia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,3,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.humov.2019.04.005","article-title":"Repetition of a cognitive task promotes motor learning","volume":"66","author":"Kimura","year":"2019","journal-title":"Hum. Mov. Sci."},{"key":"ref_2","first-page":"13","article-title":"Motor imagery as a tool for motor learning and improving sports performance: A mini review on the state of the art","volume":"13","author":"Agosti","year":"2020","journal-title":"Sport Sci."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"101673","DOI":"10.1016\/j.psychsport.2020.101673","article-title":"Generate, maintain, manipulate? Exploring the multidimensional nature of motor imagery","volume":"48","author":"Kraeutner","year":"2020","journal-title":"Psychol. Sport Exerc."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Bunno, Y. (2019). Effectiveness of Motor Imagery on Physical Therapy: Neurophysiological Aspects of Motor Imagery. Physical Therapy Effectiveness, IntechOpen.","DOI":"10.5772\/intechopen.90277"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Sirico, F., and Romano, V. (2020). Effect of Video Observation and Motor Imagery on Simple Reaction Time in Cadet Pilots. J. Funct. Morphol. Kinesiol., 5.","DOI":"10.3390\/jfmk5040089"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1016\/j.jphys.2019.08.007","article-title":"Motor imagery training improves balance and mobility outcomes in older adults: A systematic review","volume":"65","author":"Nicholson","year":"2019","journal-title":"J. Physiother."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"102902","DOI":"10.1016\/j.actpsy.2019.102902","article-title":"Motor planning with and without motor imagery in children with Developmental Coordination Disorder","volume":"199","author":"Bhoyroo","year":"2019","journal-title":"Acta Psychol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1016\/j.neubiorev.2018.12.010","article-title":"Dance for neuroplasticity: A descriptive systematic review","volume":"96","author":"Arida","year":"2019","journal-title":"Neurosci. Biobehav. Rev."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"126","DOI":"10.3389\/fspor.2020.550744","article-title":"Thinking Before Doing: A Pilot Study on the Application of Motor Imagery as a Learning Method During Physical Education Lesson in High School","volume":"2","author":"Canepa","year":"2020","journal-title":"Front. Sport. Act. Living"},{"key":"ref_10","first-page":"046014","article-title":"Multiresolution analysis over simple graphs for brain computer interfaces","volume":"10 4","author":"Gan","year":"2013","journal-title":"J. Neural Eng."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"46858","DOI":"10.1109\/ACCESS.2019.2909058","article-title":"Small Sample Motor Imagery Classification Using Regularized Riemannian Features","volume":"7","author":"Singh","year":"2019","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"105808","DOI":"10.1016\/j.cmpb.2020.105808","article-title":"Effect of power feature covariance shift on BCI spatial-filtering techniques: A comparative study","volume":"198","author":"Jarmolowska","year":"2021","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"87","DOI":"10.3389\/fncom.2019.00087","article-title":"Intra- and Inter-subject Variability in EEG-Based Sensorimotor Brain Computer Interface: A Review","volume":"13","author":"Saha","year":"2020","journal-title":"Front. Comput. Neurosci."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zakkay, E., Abu-Rmileh, A., Geva, A.B., and Shriki, O. (2020, January 19\u201324). Asynchronous Brain Computer Interfaces Using Echo State Networks. Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK.","DOI":"10.1109\/IJCNN48605.2020.9207481"},{"key":"ref_15","first-page":"29","article-title":"Short progressive muscle relaxation or motor coordination training does not increase performance in a brain-computer interface based on sensorimotor rhythms (SMR)","volume":"121","author":"Botrel","year":"2017","journal-title":"Int. J. Psychophysiol. Off. J. Int. Organ. Psychophysiol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"76","DOI":"10.3389\/fnins.2020.00076","article-title":"Explaining Individual Differences in Motor Behavior by Intrinsic Functional Connectivity and Corticospinal Excitability","volume":"14","author":"Herszage","year":"2020","journal-title":"Front. Neurosci."},{"key":"ref_17","doi-asserted-by":"crossref","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":"ref_18","doi-asserted-by":"crossref","unstructured":"Vel\u00e1squez-Mart\u00ednez, L., Caicedo-Acosta, J., and Castellanos-Dom\u00ednguez, G. (2020). Entropy-Based Estimation of Event-Related De\/Synchronization in Motor Imagery Using Vector-Quantized Patterns. Entropy, 22.","DOI":"10.3390\/e22060703"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11571-013-9267-8","article-title":"Time domain measures of inter-channel EEG correlations: A comparison of linear, nonparametric and nonlinear measures","volume":"8","author":"Bonita","year":"2013","journal-title":"Cogn. Neurodynamics"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"116500","DOI":"10.1016\/j.neuroimage.2019.116500","article-title":"Functional disconnection of associative cortical areas predicts performance during BCI training","volume":"209","author":"Corsi","year":"2020","journal-title":"NeuroImage"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1016\/j.measurement.2019.04.023","article-title":"Coherence-based correntropy spectral density: A novel coherence measure for functional connectivity of EEG signals","volume":"140","author":"Bakhshali","year":"2019","journal-title":"Measurement"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1284","DOI":"10.1109\/JSTSP.2016.2602007","article-title":"Event-Related Functional Network Identification: Application to EEG Classification","volume":"10","author":"Gonuguntla","year":"2016","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/j.bspc.2017.09.026","article-title":"Can graph metrics be used for EEG-BCIs based on hand motor imagery?","volume":"40","author":"Filho","year":"2018","journal-title":"Biomed. Signal Process. Control."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Feng, F., Qian, L., Hu, H., and Sun, Y. (2020, January 11\u201314). Functional Connectivity for Motor Imaginary Recognition in Brain-computer Interface. Proceedings of the 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Toronto, ON, Canada.","DOI":"10.1109\/SMC42975.2020.9283075"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1016\/j.neuroimage.2018.05.003","article-title":"Resting-state connectivity predicts visuo-motor skill learning","volume":"176","author":"Manuel","year":"2018","journal-title":"NeuroImage"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Yoon, J., and Lee, M. (2020, January 26\u201328). Effective Correlates of Motor Imagery Performance based on Default Mode Network in Resting-State. Proceedings of the 2020 8th International Winter Conference on Brain-Computer Interface (BCI), Gangwon, Korea.","DOI":"10.1109\/BCI48061.2020.9061649"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Gonzalez-Astudillo, J., Cattai, T., Bassignana, G., Corsi, M., and De Vico Fallani, F. (2020). Network-based brain computer interfaces: Principles and applications. J. Neural Eng.","DOI":"10.1088\/1741-2552\/abc760"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1162\/NECO_a_00838","article-title":"Electroencephalographic Motor Imagery Brain Connectivity Analysis for BCI: A Review","volume":"28","author":"Hamedi","year":"2016","journal-title":"Neural Comput."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Li, X., Wu, Y., Wei, M., Guo, Y., Yu, Z., Wang, H., Li, Z., and Fan, H. (2020). A novel index of functional connectivity: Phase lag based on Wilcoxon signed rank test. Cogn. Neurodynamics, 1\u201316.","DOI":"10.1007\/s11571-020-09646-x"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.conb.2017.08.002","article-title":"Parsing learning in networks using brain\u2013machine interfaces","volume":"46","author":"Orsborn","year":"2017","journal-title":"Curr. Opin. Neurobiol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"066032","DOI":"10.1088\/1741-2552\/aae597","article-title":"Neurophysiological predictors and spectro-spatial discriminative features for enhancing SMR-BCI","volume":"15 6","author":"Robinson","year":"2018","journal-title":"J. Neural Eng."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"116562","DOI":"10.1016\/j.neuroimage.2020.116562","article-title":"Role of beta-band resting-state functional connectivity as a predictor of motor learning ability","volume":"210","author":"Sugata","year":"2020","journal-title":"NeuroImage"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1037\/pag0000408","article-title":"Constraints on motor planning across the life span: Physical, cognitive, and motor factors","volume":"35","author":"Wang","year":"2019","journal-title":"Psychol. Aging"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"116276","DOI":"10.1016\/j.neuroimage.2019.116276","article-title":"Deep neural networks and kernel regression achieve comparable accuracies for functional connectivity prediction of behavior and demographics","volume":"206","author":"He","year":"2020","journal-title":"NeuroImage"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Cha, H., Han, C., and Im, C. (2020). Prediction of Individual User\u2019s Dynamic Ranges of EEG Features from Resting-State EEG Data for Evaluating Their Suitability for Passive Brain\u2014Computer Interface Applications. Sensors, 20.","DOI":"10.3390\/s20040988"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1007\/s10548-018-0688-x","article-title":"Brain Network Reconfiguration During Motor Imagery Revealed by a Large-Scale Network Analysis of Scalp EEG","volume":"32","author":"Li","year":"2018","journal-title":"Brain Topogr."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"056020","DOI":"10.1088\/1741-2552\/ab221a","article-title":"Two-stage regression of high-density scalp electroencephalograms visualizes force regulation signaling during muscle contraction","volume":"16","author":"Hayashi","year":"2019","journal-title":"J. Neural Eng."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"93","DOI":"10.3389\/fnins.2018.00093","article-title":"Fast Recognition of BCI-Inefficient Users Using Physiological Features from EEG Signals: A Screening Study of Stroke Patients","volume":"12","author":"Shu","year":"2018","journal-title":"Front. Neurosci."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.neuroimage.2012.02.064","article-title":"A clustering-based method to detect functional connectivity differences","volume":"61","author":"G","year":"2012","journal-title":"NeuroImage"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Kim, Y., Lee, S., Kim, H., Lee, S., Lee, S., and Kim, D. (2019, January 6\u20139). Reduced Burden of Individual Calibration Process in Brain-Computer Interface by Clustering the Subjects based on Brain Activation. Proceedings of the 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), Toronto, ON, Canada.","DOI":"10.1109\/SMC.2019.8914176"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Sannelli, C., Vidaurre, C., M\u00fcller, K., and Blankertz, B. (2019). A large scale screening study with a SMR-based BCI: Categorization of BCI users and differences in their SMR activity. PLoS ONE, 14.","DOI":"10.1371\/journal.pone.0207351"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"76","DOI":"10.3389\/fnbot.2019.00076","article-title":"Hybrid Brain-Computer-Interfacing for Human-Compliant Robots: Inferring Continuous Subjective Ratings With Deep Regression","volume":"13","author":"Fiederer","year":"2019","journal-title":"Front. Neurorobotics"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"210","DOI":"10.4103\/IJPSYM.IJPSYM_193_19","article-title":"The P Value and Statistical Significance: Misunderstandings, Explanations, Challenges, and Alternatives","volume":"41","author":"Andrade","year":"2019","journal-title":"Indian J. Psychol. Med."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"321","DOI":"10.3389\/fnhum.2020.00321","article-title":"Predicting Motor Imagery Performance From Resting-State EEG Using Dynamic Causal Modeling","volume":"14","author":"Lee","year":"2020","journal-title":"Front. Hum. Neurosci."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1016\/S0167-2789(00)00087-7","article-title":"Mean phase coherence as a measure for phase synchronization and its application to the EEG of epilepsy patients","volume":"144","author":"Mormann","year":"2000","journal-title":"Phys. Nonlinear Phenom."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/j.jneumeth.2004.03.002","article-title":"Fourier-, Hilbert-and wavelet-based signal analysis: Are they really different approaches?","volume":"137","author":"Bruns","year":"2004","journal-title":"J. Neurosci. Methods"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1548","DOI":"10.1016\/j.neuroimage.2011.01.055","article-title":"An improved index of phase-synchronization for electrophysiological data in the presence of volume-conduction, noise and sample-size bias","volume":"55","author":"Vinck","year":"2011","journal-title":"Neuroimage"},{"key":"ref_48","first-page":"8","article-title":"Efficient computation of functional brain networks: Towards real-time functional connectivity","volume":"11","author":"Bajo","year":"2017","journal-title":"Front. Neuroinform."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Cheng, H., Koc, L., Harmsen, J., Shaked, T., Aradhye, H., Anderson, G., Corrado, G., Chai, W., Ispir, M., and Anil, R. (2016, January 15). Wide & deep learning for recommender systems. Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, Boston, MA, USA.","DOI":"10.1145\/2988450.2988454"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"gix034","DOI":"10.1093\/gigascience\/gix034","article-title":"EEG datasets for motor imagery brain-computer interface","volume":"6","author":"Cho","year":"2017","journal-title":"GigaScience"},{"key":"ref_51","first-page":"13","article-title":"An Empirical Comparison of Multiple Linear Regression and Artificial Neural Network for Concrete Dam Deformation Modelling","volume":"2019","author":"Mingjun","year":"2019","journal-title":"Math. Probl. Eng."},{"key":"ref_52","unstructured":"Chen, Y., Meng, L., and Zhang, J. (2019). Graph Neural Lasso for Dynamic Network Regression. arXiv."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1016\/j.bspc.2019.04.020","article-title":"Supervised piecewise network connectivity analysis for enhanced confidence of auditory oddball tasks","volume":"52","author":"Hurtado","year":"2019","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"066017","DOI":"10.1088\/1741-2560\/10\/6\/066017","article-title":"Prediction of SSVEP-based BCI performance by the resting-state EEG network","volume":"10","author":"Zhang","year":"2013","journal-title":"J. Neural Eng."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"1278","DOI":"10.3389\/fnins.2020.575081","article-title":"Sensorimotor functional connectivity: A neurophysiological factor related to BCI performance","volume":"14","author":"Vidaurre","year":"2020","journal-title":"Front. Neurosci."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Mahmud, M., Vassanelli, S.O., Kaiser, M., and Zhong, N. (2020). A Systematic Assessment of Feature Extraction Methods for Robust Prediction of Neuropsychological Scores from Functional Connectivity Data. Brain Informatics, Springer International Publishing.","DOI":"10.1007\/978-3-030-59277-6"},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"1207","DOI":"10.1007\/s10462-019-09694-8","article-title":"Filtering techniques for channel selection in motor imagery EEG applications: A survey","volume":"53","author":"Baig","year":"2019","journal-title":"Artif. Intell. Rev."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/6\/1932\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:35:50Z","timestamp":1760160950000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/6\/1932"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,10]]},"references-count":57,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2021,3]]}},"alternative-id":["s21061932"],"URL":"https:\/\/doi.org\/10.3390\/s21061932","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,10]]}}}