{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T14:07:26Z","timestamp":1788876446024,"version":"build-2803163510"},"reference-count":121,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"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. Neurosci."],"abstract":"<jats:p>Motor Imagery-based (MI) Electroencephalography (EEG) has emerged as a leading solution in non-invasive Brain-Computer Interface (BCI) systems, leveraging its strong motor intention correlation to enable reliable neural decoding. However, practical implementation of MI confronts three persistent challenges: low signal-to-noise ratio, substantial variability across subjects or over time, and inherent signal nonstationarity. These fundamental limitations continue to hinder the widespread adoption and operational reliability of MI BCI systems. Despite advances in cross-variability decoding methods, there is a lack of systematic syntheses to guide technological evolution in MI BCI. To address these challenges, this review presents a comprehensive taxonomy of MI EEG cross-variability decoding studies from 2020 to 2025, systematically organizing advances in deep learning and transfer learning. We critically evaluate core algorithmic approaches, including Convolutional Neural Networks (CNN), transformers, feature alignment, domain adaptation, and meta-learning. We then explore the underlying mechanisms of these methods and assess their efficacy across key variability paradigms (mainly cross-subject and cross-session scenarios). Finally, we summarize key findings, highlight unresolved challenges, and outline promising future research directions. These advancements hold significant potential to bridge the gap between laboratory-based MI and real-world clinical and consumer applications.<\/jats:p>","DOI":"10.3389\/fnins.2026.1899645","type":"journal-article","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T13:13:11Z","timestamp":1788873191000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross-variability decoding for motor imagery EEG signals: a comprehensive review"],"prefix":"10.3389","volume":"20","author":[{"given":"Lijun","family":"Wang","sequence":"first","affiliation":[{"name":"School of Mathematics and Systems Science, Liaocheng University","place":["Liaocheng, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueying","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Mathematics and Systems Science, Liaocheng University","place":["Liaocheng, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengpai","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer and Information Engineering, Nanjing Tech University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiujin","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Mathematics and Systems Science, Liaocheng University","place":["Liaocheng, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shufeng","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Mathematics and Systems Science, Liaocheng University","place":["Liaocheng, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,8]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1007\/s10586-025-05187-2","article-title":"Adversarial resilience in EEG-based BCI systems: a two-tiered approach using GANs and transfer learning","volume":"28","author":"Aissa","year":"2025","journal-title":"Clust. Comput."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"783","DOI":"10.1007\/s12553-021-00560-8","article-title":"Systematic review of training environments with motor imagery brain\u2013computer interface: coherent taxonomy, open issues and recommendation pathway solution","volume":"11","author":"Al-Qaysi","year":"2021","journal-title":"Health Technol."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"2249","DOI":"10.1109\/TII.2022.3197419","article-title":"Physics-informed attention temporal convolutional network for EEG-based motor imagery classification","volume":"19","author":"Altaheri","year":"","journal-title":"IEEE Trans. Industr. Inform."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"18579","DOI":"10.1109\/JIOT.2023.3281911","article-title":"Dynamic convolution with multilevel attention for EEG-based motor imagery decoding","volume":"10","author":"Altaheri","year":"","journal-title":"IEEE Internet Things J."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"15479","DOI":"10.1109\/TNNLS.2023.3287181","article-title":"Dual attention relation network with fine-tuning for few-shot EEG motor imagery classification","volume":"35","author":"An","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref6","first-page":"2391","article-title":"Filter bank common spatial pattern (FBCSP) in brain-computer interface","author":"Ang","year":"2008"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2024.3366285","article-title":"Multiview contrastive learning for unsupervised domain adaptation in brain\u2013computer interfaces","volume":"73","author":"Asgarian","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"2105","DOI":"10.1109\/TBME.2021.3137184","article-title":"MIN2Net: end-to-end multitask learning for subject-independent motor imagery EEG classification","volume":"69","author":"Autthasan","year":"2022","journal-title":"I.E.E.E. Trans. Biomed. Eng."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"920","DOI":"10.1109\/TBME.2011.2172210","article-title":"Multiclass brain\u2013computer interface classification by Riemannian geometry","volume":"59","author":"Barachant","year":"2012","journal-title":"I.E.E.E. Trans. Biomed. Eng."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1109\/TBME.1968.4502560","article-title":"Temporal stability and individual differences in the human EEG: An analysis of variance of spectral values","author":"Berkhout","year":"1968","journal-title":"I.E.E.E. Trans. Biomed. Eng."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"3958","DOI":"10.1109\/TNSRE.2023.3323509","article-title":"TDLNet: transfer data learning network for cross-subject classification based on multiclass upper limb motor imagery EEG","volume":"31","author":"Bi","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"2866","DOI":"10.1109\/TNSRE.2022.3211818","article-title":"Transfer learning with optimal transportation and frequency mixup for EEG-based motor imagery recognition","volume":"30","author":"Chen","year":"","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1703","DOI":"10.1109\/TNSRE.2024.3391360","article-title":"Alignment-based adversarial training (ABAT) for improving the robustness and accuracy of EEG-based BCIs","volume":"32","author":"Chen","year":"2024","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1992","DOI":"10.1109\/TNSRE.2022.3191869","article-title":"Single-source to single-target cross-subject motor imagery classification based on multisubdomain adaptation network","volume":"30","author":"Chen","year":"","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/gigascience\/gix034","article-title":"EEG datasets for motor imagery brain\u2013computer interface","volume":"6","author":"Cho","year":"2017","journal-title":"GigaScience"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"7908","DOI":"10.3390\/s23187908","article-title":"Enhancing cross-subject motor imagery classification in EEG-based brain\u2013computer interfaces by using multi-branch CNN","volume":"23","author":"Chowdhury","year":"2023","journal-title":"Sensors"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"5459","DOI":"10.1109\/JBHI.2023.3304646","article-title":"Hierarchical transformer for motor imagery-based brain computer interface","volume":"27","author":"Deny","year":"2023","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.3390\/brainsci13071109","article-title":"Subject-independent EEG classification of motor imagery based on dual-branch feature fusion","volume":"13","author":"Dong","year":"2023","journal-title":"Brain Sci."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1109\/TNSRE.2012.2189584","article-title":"Autocalibration and recurrent adaptation: towards a plug and play online ERD-BCI","volume":"20","author":"Faller","year":"2012","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"5390","DOI":"10.1109\/TCE.2025.3573773","article-title":"A domain adaptation framework by aligning the inverse gram matrices for cross-subject motor imagery classification","volume":"71","author":"Fan","year":"2025","journal-title":"IEEE Trans. Consum. Electron."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1068165","DOI":"10.3389\/fnhum.2022.1068165","article-title":"Classification of motor imagery electroencephalogram signals by using adaptive cross-subject transfer learning","volume":"16","author":"Feng","year":"2022","journal-title":"Front. Hum. Neurosci."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1109\/TBME.2006.889160","article-title":"Multiple channel detection of steady-state visual evoked potentials for brain-computer interfaces","volume":"54","author":"Friman","year":"2007","journal-title":"I.E.E.E. Trans. Biomed. Eng."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1188","DOI":"10.1109\/TCDS.2021.3099988","article-title":"Logistic regression with tangent-space-based cross-subject learning for enhancing motor imagery classification","volume":"14","author":"Gaur","year":"2022","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"E215","DOI":"10.1161\/01.cir.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"7004","DOI":"10.1109\/TITS.2023.3347075","article-title":"TFAC-net: a temporal-frequential attentional convolutional network for driver drowsiness recognition with single-channel EEG","volume":"25","author":"Gong","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1440","DOI":"10.1109\/TNSRE.2023.3246989","article-title":"A spiking neural network with adaptive graph convolution and LSTM for EEG-based brain-computer interfaces","volume":"31","author":"Gong","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1007\/978-3-642-22092-0_49","article-title":"Time-frequency mixed-norm estimates: sparse M\/EEG imaging with non-stationary source activations","volume":"70","author":"Gramfort","year":"2013","journal-title":"NeuroImage"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"066027","DOI":"10.1088\/1741-2552\/ad09ff","article-title":"EEG decoding for datasets with heterogeneous electrode configurations using transfer learning graph neural networks","volume":"20","author":"Han","year":"2023","journal-title":"J. Neural Eng."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"066011","DOI":"10.1088\/1741-2552\/aadea0","article-title":"MOABB: trustworthy algorithm benchmarking for BCIs","volume":"15","author":"Jayaram","year":"2018","journal-title":"J. Neural Eng."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1109\/TNNLS.2021.3100583","article-title":"Mutual information-driven subject-invariant and class-relevant deep representation learning in BCI","volume":"34","author":"Jeon","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"1311","DOI":"10.1109\/TNSRE.2023.3243992","article-title":"A model combining multi-branch spectral-temporal CNN, efficient channel attention, and LightGBM for MI-BCI classification","volume":"31","author":"Jia","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref32","article-title":"Large brain model for learning generic representations with tremendous EEG data in BCI","volume-title":"The Twelfth International Conference on Learning Representations","author":"Jiang","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1109\/JBHI.2024.3472097","article-title":"Multiscale spatial-temporal feature fusion neural network for motor imagery brain-computer interfaces","volume":"29","author":"Jin","year":"2025","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"3168","DOI":"10.3390\/s24103168","article-title":"Optimal channel selection of multiclass motor imagery classification based on fusion convolutional neural network with attention blocks","volume":"24","author":"Khabti","year":"2024","journal-title":"Sensors"},{"key":"ref35","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":"ref36","doi-asserted-by":"publisher","first-page":"923","DOI":"10.1109\/TCDS.2023.3314351","article-title":"Selective multi-source domain adaptation network for cross-subject motor imagery discrimination","volume":"16","author":"Lee","year":"","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/gigascience\/giz002","article-title":"EEG dataset and OpenBMI toolbox for three BCI paradigms: An investigation into BCI illiteracy","volume":"8","author":"Lee","year":"2019","journal-title":"GigaScience"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1767","DOI":"10.1109\/TNSRE.2024.3395133","article-title":"Multitask heterogeneous ensemble learning-based cross-subject EEG classification under stroke patients","volume":"32","author":"Lee","year":"","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1109\/TNSRE.2007.906956","article-title":"Brain\u2013computer communication: motivation, aim, and impact of exploring a virtual apartment","volume":"15","author":"Leeb","year":"2007","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"116326","DOI":"10.1016\/j.chaos.2025.116326","article-title":"Manifold-based multi-branch transfer learning for MI-EEG decoding","volume":"196","author":"Li","year":"2025","journal-title":"Chaos Solitons Fractals"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"026038","DOI":"10.1088\/1741-2552\/ad3986","article-title":"Self-supervised contrastive learning for EEG-based cross-subject motor imagery recognition","volume":"21","author":"Li","year":"","journal-title":"J. Neural Eng."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"106044","DOI":"10.1016\/j.bspc.2024.106044","article-title":"Parameter transfer and Riemannian space coordinate alignment for EEG intention recognition","volume":"92","author":"Li","year":"","journal-title":"Biomed. Signal Process. Control"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1109\/TETCI.2023.3301385","article-title":"Subdomain adversarial network for motor imagery EEG classification using graph data","volume":"8","author":"Li","year":"","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"ref44","doi-asserted-by":"publisher","first-page":"1743","DOI":"10.1109\/TNSRE.2023.3259730","article-title":"MDTL: a novel and model-agnostic transfer learning strategy for cross-subject motor imagery BCI","volume":"31","author":"Li","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref45","doi-asserted-by":"publisher","first-page":"022013","DOI":"10.1088\/2516-1091\/ae65f0","article-title":"Cross-subject generalization for EEG decoding: a survey of deep learning methods","volume":"8","author":"Li","year":"2026","journal-title":"Prog. Biomed. Eng."},{"key":"ref46","doi-asserted-by":"publisher","first-page":"1535","DOI":"10.1109\/TNSRE.2024.3382267","article-title":"EISATC-fusion: inception self-attention temporal convolutional network fusion for motor imagery EEG decoding","volume":"32","author":"Liang","year":"2024","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref47","doi-asserted-by":"publisher","first-page":"121612","DOI":"10.1016\/j.eswa.2023.121612","article-title":"A cross-session motor imagery classification method based on Riemannian geometry and deep domain adaptation","volume":"237","author":"Liu","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref48","doi-asserted-by":"publisher","first-page":"026003","DOI":"10.1088\/1741-2552\/abd82b","article-title":"Multiscale space-time-frequency feature-guided multitask learning CNN for motor imagery EEG classification","volume":"18","author":"Liu","year":"2021","journal-title":"J. Neural Eng."},{"key":"ref49","first-page":"16","article-title":"Epileptic detection method for EEG data based on model pruning federated learning","author":"Liu","year":"2025"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2023.1274320","article-title":"Dual selections based knowledge transfer learning for cross-subject motor imagery EEG classification","volume":"17","author":"Luo","year":"2023","journal-title":"Front. Neurosci."},{"key":"ref51","doi-asserted-by":"publisher","first-page":"124673","DOI":"10.1016\/j.eswa.2024.124673","article-title":"Dual regularized spatial-temporal features adaptation for multi-source selected cross-subject motor imagery EEG classification","volume":"255","author":"Luo","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref52","doi-asserted-by":"publisher","first-page":"107254","DOI":"10.1016\/j.compbiomed.2023.107254","article-title":"A shallow mirror transformer for subject-independent motor imagery BCI","volume":"164","author":"Luo","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref53","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1038\/s41597-022-01647-1","article-title":"A large EEG dataset for studying cross-session variability in motor imagery brain-computer interface","volume":"9","author":"Ma","year":"2022","journal-title":"Sci. Data"},{"key":"ref54","doi-asserted-by":"publisher","first-page":"2365","DOI":"10.1109\/JBHI.2023.3243698","article-title":"Autoencoder filter bank common spatial patterns to decode motor imagery from EEG","volume":"27","author":"Mammone","year":"2023","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref55","doi-asserted-by":"publisher","first-page":"066021","DOI":"10.1088\/1741-2552\/ad0c61","article-title":"Explainable cross-task adaptive transfer learning for motor imagery EEG classification","volume":"20","author":"Miao","year":"2023","journal-title":"J. Neural Eng."},{"key":"ref56","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1088\/1741-2560\/3\/3\/003","article-title":"Separability of four-class motor imagery data using independent components analysis","volume":"3","author":"Naeem","year":"2006","journal-title":"J. Neural Eng."},{"key":"ref57","doi-asserted-by":"publisher","first-page":"016007","DOI":"10.1088\/1741-2552\/ad152f","article-title":"Transferring a deep learning model from healthy subjects to stroke patients in a motor imagery brain\u2013computer interface","volume":"21","author":"Nagarajan","year":"2024","journal-title":"J. Neural Eng."},{"key":"ref58","doi-asserted-by":"publisher","first-page":"106108","DOI":"10.1016\/j.neunet.2024.106108","article-title":"Subject-independent meta-learning framework towards optimal training of EEG-based classifiers","volume":"172","author":"Ng","year":"2024","journal-title":"Neural Netw."},{"key":"ref59","doi-asserted-by":"publisher","first-page":"123354","DOI":"10.1016\/j.eswa.2024.123354","article-title":"EEG-based motor imagery classification with quantum algorithms","volume":"247","author":"Olvera","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref60","article-title":"ChatGPT: optimizing language models for dialogue","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","first-page":"066011","DOI":"10.1088\/1741-2552\/ad0a01","article-title":"Riemannian geometric and ensemble learning for decoding cross-session motor imagery electroencephalography signals","volume":"20","author":"Pan","year":"2023","journal-title":"J. Neural Eng."},{"key":"ref62","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1109\/TBME.2021.3105912","article-title":"Transfer learning based on optimal transport for motor imagery brain-computer interfaces","volume":"69","author":"Peterson","year":"2022","journal-title":"I.E.E.E. Trans. Biomed. Eng."},{"key":"ref63","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1109\/5.939829","article-title":"Motor imagery and direct brain-computer communication","volume":"89","author":"Pfurtscheller","year":"2001","journal-title":"Proc. IEEE"},{"key":"ref64","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/s11633-022-1382-8","article-title":"Pre-training in medical data: a survey","volume":"20","author":"Qiu","year":"2023","journal-title":"Mach. Intell. Res."},{"key":"ref65","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1109\/86.895946","article-title":"Optimal spatial filtering of single trial EEG during imagined hand movement","volume":"8","author":"Ramoser","year":"2000","journal-title":"IEEE Trans. Rehabil. Eng."},{"key":"ref66","doi-asserted-by":"publisher","first-page":"105347","DOI":"10.1016\/j.engappai.2022.105347","article-title":"Adaptive transfer learning-based multiscale feature fused deep convolutional neural network for EEG MI multiclassification in brain\u2013computer interface","volume":"116","author":"Roy","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref67","doi-asserted-by":"publisher","first-page":"17703","DOI":"10.1109\/JSEN.2023.3270281","article-title":"Sliding window along with EEGNet-based prediction of EEG motor imagery","volume":"23","author":"Saideepthi","year":"2023","journal-title":"IEEE Sensors J."},{"key":"ref68","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":"ref69","doi-asserted-by":"publisher","first-page":"5391","DOI":"10.1002\/hbm.23730","article-title":"Deep learning with convolutional neural networks for EEG decoding and visualization","volume":"38","author":"Schirrmeister","year":"2017","journal-title":"Hum. Brain Mapp."},{"key":"ref70","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TNSRE.2023.3241846","article-title":"Improved domain adaptation network based on Wasserstein distance for motor imagery EEG classification","volume":"31","author":"She","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref71","doi-asserted-by":"publisher","first-page":"2767","DOI":"10.1109\/TNSRE.2023.3285309","article-title":"Global adaptive transformer for cross-subject enhanced EEG classification","volume":"31","author":"Song","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref72","doi-asserted-by":"publisher","first-page":"106470","DOI":"10.1016\/j.neunet.2024.106470","article-title":"Leveraging temporal dependency for cross-subject-MI BCIs by contrastive learning and self-attention","volume":"178","author":"Sun","year":"2024","journal-title":"Neural Netw."},{"key":"ref73","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1109\/TASE.2020.3021456","article-title":"EEG motor imagery classification with sparse spectrotemporal decomposition and deep learning","volume":"18","author":"Sun","year":"2021","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref74","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/s11633-024-1492-6","article-title":"Attention detection using EEG signals and machine learning: a review","volume":"22","author":"Sun","year":"2025","journal-title":"Mach. Intell. Res."},{"key":"ref75","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.1126\/science.150.3700.1187","article-title":"Evoked-potential correlates of stimulus uncertainty","volume":"150","author":"Sutton","year":"1965","journal-title":"Science"},{"key":"ref76","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1109\/TCDS.2021.3082648","article-title":"Transfer learning: rotation alignment with Riemannian mean for brain\u2013computer interfaces and wheelchair control","volume":"15","author":"Tang","year":"2023","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"ref77","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1109\/TNSRE.2023.3342331","article-title":"ADFCNN: attention-based dual-scale fusion convolutional neural network for motor imagery brain\u2013computer interface","volume":"32","author":"Tao","year":"2024","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref78","doi-asserted-by":"publisher","first-page":"106267","DOI":"10.1016\/j.compbiomed.2022.106267","article-title":"Segment alignment based cross-subject motor imagery classification under fading data","volume":"151","author":"Wan","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref79","doi-asserted-by":"publisher","first-page":"10698","DOI":"10.1109\/TNNLS.2023.3243339","article-title":"EEG-based motor imagery recognition framework via multisubject dynamic transfer and iterative self-training","volume":"35","author":"Wang","year":"","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref80","doi-asserted-by":"publisher","first-page":"106351","DOI":"10.1016\/j.neunet.2024.106351","article-title":"Channel reflection: knowledge-driven data augmentation for EEG-based brain\u2013computer interfaces","volume":"176","author":"Wang","year":"","journal-title":"Neural Netw."},{"key":"ref81","doi-asserted-by":"publisher","first-page":"4134","DOI":"10.1109\/JBHI.2025.3622725","article-title":"DBConformer: dual-branch convolutional transformer for EEG decoding","volume":"30","author":"Wang","year":"","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref82","doi-asserted-by":"publisher","first-page":"2834","DOI":"10.1109\/TNSRE.2025.3591254","article-title":"Enhanced online continuous brain-control by deep learning-based EEG decoding","volume":"33","author":"Wang","year":"","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref83","doi-asserted-by":"publisher","first-page":"107816","DOI":"10.1016\/j.neunet.2025.107816","article-title":"EEGMamba: An EEG foundation model with mamba","volume":"192","author":"Wang","year":"","journal-title":"Neural Netw."},{"key":"ref84","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1109\/TRE.2000.847807","article-title":"Brain-computer interface technology: a review of the first international meeting","volume":"8","author":"Wolpaw","year":"2000","journal-title":"IEEE Trans. Rehabil. Eng."},{"key":"ref85","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1016\/B978-0-444-63934-9.00007-X","article-title":"Brain-computer interfaces for communication and control","volume":"113","author":"Wolpaw","year":"2002","journal-title":"Clin. Neurophysiol."},{"key":"ref86","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1109\/TNSRE.2024.3356916","article-title":"Motor imagery classification for asynchronous EEG-based brain\u2013computer interfaces","volume":"32","author":"Wu","year":"2024","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref87","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TCDS.2020.3007453","article-title":"Transfer learning for EEG-based brain\u2013computer interfaces: a review of progress made since 2016","volume":"14","author":"Wu","year":"2022","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"ref88","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1007\/s11633-020-1273-9","article-title":"Research on transfer learning of vision-based gesture recognition","volume":"18","author":"Wu","year":"2021","journal-title":"Int. J. Autom. Comput."},{"key":"ref89","doi-asserted-by":"publisher","first-page":"3365","DOI":"10.1109\/TBME.2022.3168570","article-title":"Privacy-preserving domain adaptation for motor imagery-based brain-computer interfaces","volume":"69","author":"Xia","year":"2022","journal-title":"I.E.E.E. Trans. Biomed. Eng."},{"key":"ref90","doi-asserted-by":"publisher","first-page":"14708","DOI":"10.1038\/s41598-018-32283-8","article-title":"A high-speed SSVEP-based BCI using dry EEG electrodes","volume":"8","author":"Xing","year":"2018","journal-title":"Sci. Rep."},{"key":"ref91","doi-asserted-by":"publisher","first-page":"779231","DOI":"10.3389\/fnins.2021.779231","article-title":"Selective cross-subject transfer learning based on Riemannian tangent space for motor imagery brain-computer interface","volume":"15","author":"Xu","year":"2021","journal-title":"Front. Neurosci."},{"key":"ref92","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2024.3420350","article-title":"A relation feature comparison network for cross-domain recognition of motion intention","volume":"73","author":"Xu","year":"","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref93","doi-asserted-by":"publisher","first-page":"125452","DOI":"10.1016\/j.eswa.2024.125452","article-title":"Unsupervised multi-source domain adaptation via contrastive learning for EEG classification","volume":"261","author":"Xu","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref94","doi-asserted-by":"publisher","first-page":"4565","DOI":"10.1109\/JBHI.2024.3402324","article-title":"Riemannian locality preserving method for transfer learning with applications on brain-computer interface","volume":"28","author":"Xu","year":"","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref95","doi-asserted-by":"publisher","first-page":"103","DOI":"10.3389\/fnhum.2020.00103","article-title":"Cross-dataset variability problem in EEG decoding with deep learning","volume":"14","author":"Xu","year":"2020","journal-title":"Front. Hum. Neurosci."},{"key":"ref96","doi-asserted-by":"publisher","first-page":"127312","DOI":"10.1016\/j.eswa.2025.127312","article-title":"Joint spatial feature adaption and confident pseudo-label selection for cross-subject motor imagery EEG signals classification","volume":"278","author":"Yang","year":"","journal-title":"Expert Syst. Appl."},{"key":"ref97","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1038\/s41597-025-04826-y","article-title":"A multi-day and high-quality EEG dataset for motor imagery brain-computer interface","volume":"12","author":"Yang","year":"","journal-title":"Sci. Data"},{"key":"ref98","doi-asserted-by":"publisher","first-page":"110015","DOI":"10.1016\/j.patcog.2023.110015","article-title":"GITGAN: generative inter-subject transfer for EEG motor imagery analysis","volume":"146","author":"Yin","year":"2024","journal-title":"Pattern Recogn."},{"key":"ref99","doi-asserted-by":"publisher","first-page":"bhad511","DOI":"10.1093\/cercor\/bhad511","article-title":"Multiclass classification of motor imagery tasks based on multi-branch convolutional neural network and temporal convolutional network model","volume":"34","author":"Yu","year":"2024","journal-title":"Cereb. Cortex"},{"key":"ref100","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2024.3451593","article-title":"Toward cross-brain-computer interface: a prototype-supervised adversarial transfer learning approach with multiple sources","volume":"73","author":"Zhang","year":"","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref101","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1016\/j.neunet.2023.06.005","article-title":"MI-CAT: a transformer-based domain adaptation network for motor imagery classification","volume":"165","author":"Zhang","year":"","journal-title":"Neural Netw."},{"key":"ref102","doi-asserted-by":"publisher","first-page":"106497","DOI":"10.1016\/j.neunet.2024.106497","article-title":"Unsupervised and semi-supervised domain adaptation networks considering both global knowledge and prototype-based local class information for motor imagery classification","volume":"179","author":"Zhang","year":"","journal-title":"Neural Netw."},{"key":"ref103","doi-asserted-by":"publisher","first-page":"126659","DOI":"10.1016\/j.neucom.2023.126659","article-title":"Priming cross-session motor imagery classification with a universal deep domain adaptation framework","volume":"556","author":"Zhang","year":"","journal-title":"Neurocomputing"},{"key":"ref104","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neunet.2020.12.013","article-title":"Adaptive transfer learning for EEG motor imagery classification with deep convolutional neural network","volume":"136","author":"Zhang","year":"","journal-title":"Neural Netw."},{"key":"ref105","doi-asserted-by":"publisher","first-page":"106150","DOI":"10.1016\/j.cmpb.2021.106150","article-title":"Sub-band target alignment common spatial pattern in brain-computer interface","volume":"207","author":"Zhang","year":"","journal-title":"Comput. Methods Prog. Biomed."},{"key":"ref106","doi-asserted-by":"publisher","first-page":"2710","DOI":"10.1109\/TNSRE.2022.3207494","article-title":"Multi-source decentralized transfer for privacy-preserving BCIs","volume":"30","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref107","doi-asserted-by":"publisher","first-page":"1117","DOI":"10.1109\/TNSRE.2020.2985996","article-title":"Manifold embedded knowledge transfer for brain-computer interfaces","volume":"28","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref108","doi-asserted-by":"publisher","first-page":"938","DOI":"10.1109\/TCDS.2022.3193731","article-title":"Lightweight source-free transfer for privacy-preserving motor imagery classification","volume":"15","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"ref109","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2020\/1683013","article-title":"Instance transfer subject-dependent strategy for motor imagery signal classification using deep convolutional neural networks","volume":"2020","author":"Zhang","year":"2020","journal-title":"Comput. Math. Methods Med."},{"key":"ref110","doi-asserted-by":"publisher","first-page":"1722","DOI":"10.1109\/TCDS.2022.3174660","article-title":"Graph learning with co-teaching for EEG-based motor imagery recognition","volume":"15","author":"Zhang","year":"","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"ref111","first-page":"4155","article-title":"Brant-X: a unified physiological signal alignment framework for healthcare","volume-title":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Zhang","year":""},{"key":"ref112","first-page":"26304","article-title":"Brant: foundation model for intracranial neural signal neural information processing systems conference","volume-title":"Advances in Neural Information Processing Systems","author":"Zhang","year":""},{"key":"ref113","first-page":"7285057","article-title":"Deep neural network with joint distribution matching for cross-subject motor imagery brain\u2013computer interfaces","volume-title":"Biomed. Res. Int.","author":"Zhao","year":"2020"},{"key":"ref114","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/TNNLS.2020.3010780","article-title":"Deep representation-based domain adaptation for nonstationary EEG classification","volume":"32","author":"Zhao","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref115","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1109\/TBME.2024.3432934","article-title":"Supervised contrastive learning-based domain generalization network for cross-subject motor decoding","volume":"72","author":"Zhi","year":"2025","journal-title":"I.E.E.E. Trans. Biomed. Eng."},{"key":"ref116","doi-asserted-by":"publisher","first-page":"107235","DOI":"10.1016\/j.compbiomed.2023.107235","article-title":"A deep domain adaptation framework with correlation alignment for EEG-based motor imagery classification","volume":"163","author":"Zhong","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref117","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1109\/TCDS.2021.3090217","article-title":"Cognitive workload recognition using EEG signals and machine learning: a review","volume":"14","author":"Zhou","year":"2022","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"ref118","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1007\/s11571-024-10215-9","article-title":"Cross-subject mental workload recognition using bi-classifier domain adversarial learning","volume":"19","author":"Zhou","year":"2025","journal-title":"Cogn. Neurodyn."},{"key":"ref119","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2023.3341217","article-title":"Dual contrastive training and transferability-aware adaptation for multisource privacy-preserving motor imagery classification","volume":"73","author":"Zhu","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref120","doi-asserted-by":"publisher","first-page":"21772","DOI":"10.1109\/JSEN.2021.3101684","article-title":"Multi-source fusion domain adaptation using resting-state knowledge for motor imagery classification tasks","volume":"21","author":"Zhu","year":"2021","journal-title":"IEEE Sensors J."},{"key":"ref121","doi-asserted-by":"publisher","first-page":"1381572","DOI":"10.3389\/fnins.2024.1381572","article-title":"Riemannian transfer learning based on log-Euclidean metric for EEG classification","volume":"18","author":"Zhuo","year":"2024","journal-title":"Front. Neurosci."}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2026.1899645\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T13:13:13Z","timestamp":1788873193000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2026.1899645\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,8]]},"references-count":121,"alternative-id":["10.3389\/fnins.2026.1899645"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2026.1899645","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,8]]},"article-number":"1899645"}}