{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T07:02:04Z","timestamp":1784876524225,"version":"3.55.0"},"reference-count":70,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:00:00Z","timestamp":1784851200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:00:00Z","timestamp":1784851200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"crossref","award":["Moonshot"],"award-info":[{"award-number":["Moonshot"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["J. Neural Eng."],"published-print":{"date-parts":[[2026,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective.<\/jats:italic>\n                    Classification of electroencephalogram (EEG) signals obtained during motor imagery (MI) has substantial application potential, including for communication assistance and rehabilitation support for patients with motor impairments. These signals remain inherently susceptible to physiological artifacts (e.g. eye blinking, swallowing), which pose persistent challenges. Although Transformer-based approaches for classifying EEG signals have been widely adopted, they often struggle to capture fine-grained dependencies within them.\n                    <jats:italic>Approach.<\/jats:italic>\n                    To overcome these limitations, we propose Cortical-SSM, a novel architecture that extends deep state space models to capture integrated dependencies of EEG signals across temporal, spatial, and frequency domains. We validated our method across two large-scale public MI EEG datasets containing more than 50 subjects.\n                    <jats:italic>Main results.<\/jats:italic>\n                    Our method outperformed baseline methods on the two benchmarks. Furthermore, visual explanations derived from our model indicate that it effectively captures neurophysiologically relevant regions of EEG signals.\n                    <jats:italic>Significance.<\/jats:italic>\n                    These results indicate that Cortical-SSM provides a robust and interpretable alternative to attention-based architectures for MI EEG decoding. By enabling physiologically grounded feature learning, our method advances the reliability of subject-independent EEG classification and supports the development of practical and clinically deployable brain\u2013computer interface systems.\n                  <\/jats:p>","DOI":"10.1088\/1741-2552\/ae89e8","type":"journal-article","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T02:51:09Z","timestamp":1783997469000},"page":"046032","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Cortical-SSM: a deep state space model for motor imagery decoding from EEG signals"],"prefix":"10.1088","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5564-3835","authenticated-orcid":true,"given":"Shuntaro","family":"Suzuki","sequence":"first","affiliation":[{"name":"Keio University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9741-7628","authenticated-orcid":false,"given":"Shunya","family":"Nagashima","sequence":"additional","affiliation":[{"name":"Keio University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0261-0510","authenticated-orcid":true,"given":"Komei","family":"Sugiura","sequence":"additional","affiliation":[{"name":"Keio University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,7,24]]},"reference":[{"key":"jneae89e8bib1","first-page":"pp 67","type":"book","article-title":"Brain-computer interfaces","volume":"vol 110","author":"Wolpaw","year":"2013"},{"key":"jneae89e8bib2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.physrep.2021.03.002","type":"journal-article","article-title":"Physical principles of brain\u2013computer interfaces and their applications for rehabilitation, robotics and control of human brain states","volume":"918","author":"Hramov","year":"2021","journal-title":"Phys. Rep."},{"key":"jneae89e8bib3","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.neucom.2016.10.024","type":"journal-article","article-title":"Brain computer interface: control signals review","volume":"223","author":"Ramadan","year":"2017","journal-title":"Neurocomputing"},{"key":"jneae89e8bib4","doi-asserted-by":"publisher","first-page":"giz002","DOI":"10.1093\/gigascience\/giz002","type":"journal-article","article-title":"EEG dataset and OpenBMI toolbox for three BCI paradigms: an investigation into BCI illiteracy","volume":"8","author":"Min-Ho Lee","year":"2019","journal-title":"GigaScience"},{"key":"jneae89e8bib5","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aace8c","type":"journal-article","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":"jneae89e8bib6","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1109\/TNSRE.2022.3230250","type":"journal-article","article-title":"EEG conformer: convolutional transformer for EEG decoding and visualization","volume":"31","author":"Song","year":"2022","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"jneae89e8bib7","first-page":"pp 36314","type":"conference-proceedings","article-title":"Medformer: a multi-granularity patching transformer for medical time-series classification","volume":"vol 37","author":"Wang","year":"2024"},{"key":"jneae89e8bib8","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.neuroimage.2005.12.003","type":"journal-article","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":"jneae89e8bib9","article-title":"simplified state space layers for sequence modeling","author":"Smith","year":"2023","type":"conference-proceedings"},{"key":"jneae89e8bib10","doi-asserted-by":"publisher","first-page":"127271","DOI":"10.1109\/ACCESS.2023.3329678","type":"journal-article","article-title":"Deep learning in EEG-based BCIs: a comprehensive review of transformer models, advantages, challenges and applications","volume":"11","author":"Abibullaev","year":"2023","journal-title":"IEEE Acc."},{"key":"jneae89e8bib11","doi-asserted-by":"publisher","first-page":"14681","DOI":"10.1007\/s00521-021-06352-5","type":"journal-article","article-title":"Deep learning techniques for classification of electroencephalogram (EEG) motor imagery (MI) signals: a review","volume":"35","author":"Altaheri","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"jneae89e8bib12","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065721300011","type":"journal-article","article-title":"An experimental review on deep learning architectures for time series forecasting","volume":"31","author":"Lara-Ben\u00edtez","year":"2021","journal-title":"Int. J. Neural Syst."},{"key":"jneae89e8bib13","first-page":"pp 6555","type":"conference-proceedings","article-title":"Foundation models for time series analysis: a tutorial and survey","author":"Liang","year":"2024"},{"key":"jneae89e8bib14","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.4930035","type":"preprint","article-title":"Mamba-360: survey of state space models as transformer alternative for long sequence modelling: methods, applications, and challenges","author":"Patro","year":"2024"},{"key":"jneae89e8bib15","article-title":"State space model for new-generation network alternative to transformers: a survey","author":"Wang","year":"2024","type":"preprint"},{"key":"jneae89e8bib16","first-page":"pp 39249","type":"conference-proceedings","article-title":"EEGPT: Pretrained transformer for universal and reliable representation of EEG signals","volume":"vol 37","author":"Wang","year":"2024"},{"key":"jneae89e8bib17","article-title":"FBCNet: a multi-view convolutional neural network for brain-computer interface","author":"Mane","year":"2021","type":"preprint"},{"key":"jneae89e8bib18","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1109\/TNSRE.2023.3237181","type":"journal-article","article-title":"Physics-informed deep learning for musculoskeletal modeling: predicting muscle forces and joint kinematics from surface EMG","volume":"31","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"jneae89e8bib19","first-page":"pp 402","type":"conference-proceedings","article-title":"Frozen language model helps ECG zero-shot learning","author":"Jun","year":"2024"},{"key":"jneae89e8bib20","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/s41586-023-06185-3","type":"journal-article","article-title":"Accurate medium-range global weather forecasting with 3D neural networks","volume":"619","author":"Kaifeng","year":"2023","journal-title":"Nature"},{"key":"jneae89e8bib21","article-title":"Generative learning for financial time series with irregular and scale-invariant patterns","author":"Huang","year":"2024","type":"conference-proceedings"},{"key":"jneae89e8bib22","first-page":"pp 11106","type":"conference-proceedings","article-title":"Informer: beyond efficient transformer for long sequence time-series forecasting","author":"Zhou","year":"2021"},{"key":"jneae89e8bib23","article-title":"Crossformer: transformer utilizing cross-dimension dependency for multivariate time series forecasting","author":"Zhang","year":"2023","type":"conference-proceedings"},{"key":"jneae89e8bib24","article-title":"A time series is worth 64 words: long-term forecasting with transformers","author":"Nie","year":"2023","type":"conference-proceedings"},{"key":"jneae89e8bib25","first-page":"pp 11121","type":"conference-proceedings","article-title":"Are transformers effective for time series forecasting?","author":"Zeng","year":"2023"},{"key":"jneae89e8bib26","article-title":"iTransformer: inverted transformers are effective for time series forecasting","author":"Liu","year":"2024","type":"conference-proceedings"},{"key":"jneae89e8bib27","first-page":"pp 12449","type":"conference-proceedings","article-title":"wav2vec 2.0: a framework for self-supervised learning of speech representations","volume":"vol 33","author":"Baevski","year":"2020"},{"key":"jneae89e8bib28","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","type":"conference-proceedings"},{"key":"jneae89e8bib29","first-page":"pp 22470","type":"conference-proceedings","article-title":"Combiner: full attention transformer with sparse computation cost","volume":"vol 34","author":"Ren","year":"2021"},{"key":"jneae89e8bib30","first-page":"pp 5961","type":"conference-proceedings","article-title":"Flatten transformer: vision transformer using focused linear attention","author":"Han","year":"2023"},{"key":"jneae89e8bib31","article-title":"Mamba: linear-time sequence modeling with selective state spaces","author":"Albert","year":"2024","type":"conference-proceedings"},{"key":"jneae89e8bib32","article-title":"EEG-SSM: leveraging state-space model for dementia detection","author":"Tran","year":"2024","type":"preprint"},{"key":"jneae89e8bib33","article-title":"EEGMamba: bidirectional state space model with mixture of experts for EEG multi-task classification","author":"Gui","year":"2025","type":"conference-proceedings"},{"key":"jneae89e8bib34","first-page":"pp 10041","type":"conference-proceedings","article-title":"Transformers are SSMs: generalized models and efficient algorithms through structured state space duality","volume":"vol 235","author":"Dao","year":"2024"},{"key":"jneae89e8bib35","type":"conference-proceedings","article-title":"Attention is all you need","volume":"vol 30","author":"Vaswani","year":"2017"},{"key":"jneae89e8bib36","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1115\/1.3662552","type":"journal-article","article-title":"A new approach to linear filtering and prediction problems","volume":"82","author":"Kalman","year":"1960","journal-title":"J. Basic Eng."},{"key":"jneae89e8bib37","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Albert","year":"2022","type":"conference-proceedings"},{"key":"jneae89e8bib38","first-page":"2892","type":"conference-proceedings","article-title":"Comparison between first-order hold with zero-order hold in discretization of input-delay nonlinear systems","author":"Zhang","year":"2007"},{"key":"jneae89e8bib39","article-title":"Wavelet pooling for convolutional neural networks","author":"Williams","year":"2018","type":"conference-proceedings"},{"key":"jneae89e8bib40","doi-asserted-by":"publisher","first-page":"74973","DOI":"10.1109\/ACCESS.2019.2921451","type":"journal-article","article-title":"Multi-level wavelet convolutional neural networks","volume":"7","author":"Liu","year":"2019","journal-title":"IEEE Acc."},{"key":"jneae89e8bib41","article-title":"Layer normalization","author":"Jimmy Lei","year":"2016","type":"preprint"},{"key":"jneae89e8bib42","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1175\/1520-0477(1998)079&amp;lt;0061:APGTWA&amp;gt;2.0.CO;2","type":"journal-article","article-title":"A practical guide to wavelet analysis","volume":"79","author":"Torrence","year":"1998","journal-title":"BAMS"},{"key":"jneae89e8bib43","first-page":"pp 448","type":"conference-proceedings","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015"},{"key":"jneae89e8bib44","first-page":"pp 3","type":"conference-proceedings","article-title":"Group normalization","author":"Yuxin","year":"2018"},{"key":"jneae89e8bib45","first-page":"pp 9881","type":"conference-proceedings","article-title":"Non-stationary transformers: exploring the stationarity in time series forecasting","volume":"vol 35","author":"Liu","year":"2022"},{"key":"jneae89e8bib46","article-title":"Reversible instance normalization for accurate time-series forecasting against distribution shift","author":"Kim","year":"2022","type":"conference-proceedings"},{"key":"jneae89e8bib47","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1109\/5.939829","type":"journal-article","article-title":"Motor imagery and direct brain-computer communication","volume":"89","author":"Pfurtscheller","year":"2001","journal-title":"Proc. IEEE"},{"key":"jneae89e8bib48","doi-asserted-by":"publisher","first-page":"2424","DOI":"10.1523\/JNEUROSCI.3886-06.2007","type":"journal-article","article-title":"Spectral changes in cortical surface potentials during motor movement","volume":"27","author":"Miller","year":"2007","journal-title":"J. Neurosci."},{"key":"jneae89e8bib49","first-page":"pp 7616","type":"conference-proceedings","article-title":"It\u2019s raw! audio generation with state-space models","author":"Goel","year":"2022"},{"key":"jneae89e8bib50","article-title":"S7: selective and simplified state space layers for sequence modeling","author":"Soydan","year":"2024","type":"preprint"},{"key":"jneae89e8bib51","first-page":"618","type":"conference-proceedings","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"jneae89e8bib52","doi-asserted-by":"publisher","first-page":"gix034","DOI":"10.1093\/gigascience\/gix034","type":"journal-article","article-title":"EEG datasets for motor imagery brain\u2013computer interface","volume":"6","author":"Cho","year":"2017","journal-title":"GigaScience"},{"key":"jneae89e8bib53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.211","type":"journal-article","article-title":"A large electroencephalographic motor imagery dataset for electroencephalographic brain computer interfaces","volume":"5","author":"Kaya","year":"2018","journal-title":"Sci. Data"},{"key":"jneae89e8bib54","doi-asserted-by":"publisher","first-page":"2372","DOI":"10.1038\/s41598-023-27528-0","type":"journal-article","article-title":"EEG is better left alone","volume":"13","author":"Delorme","year":"2023","journal-title":"Sci. Rep."},{"key":"jneae89e8bib55","first-page":"3","type":"journal-article","article-title":"The ten-twenty electrode system of the international federation. the international federation of clinical neurophysiology","volume":"52","author":"Klem","year":"1999","journal-title":"Electroencephalogr. Clin. Neurophysiol. Suppl."},{"key":"jneae89e8bib56","doi-asserted-by":"publisher","first-page":"5391","DOI":"10.1002\/hbm.23730","type":"journal-article","article-title":"Deep learning with convolutional neural networks for EEG decoding and visualization","volume":"38","author":"Schirrmeister","year":"2017","journal-title":"Human Brain Mapp."},{"key":"jneae89e8bib57","first-page":"pp 1","type":"conference-proceedings","article-title":"TSception: a deep learning framework for emotion detection using EEG","author":"Ding","year":"2020"},{"key":"jneae89e8bib58","first-page":"pp 22419","type":"conference-proceedings","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume":"vol 34","author":"Haixu","year":"2021"},{"key":"jneae89e8bib59","first-page":"pp 27268","type":"conference-proceedings","article-title":"FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting","author":"Zhou","year":"2022"},{"key":"jneae89e8bib60","article-title":"TimesNet: temporal 2D-variation modeling for general time series analysis","author":"Haixu","year":"2023","type":"conference-proceedings"},{"key":"jneae89e8bib61","article-title":"TimeMixer: decomposable multiscale mixing for time series forecasting","author":"Wang","year":"2024","type":"conference-proceedings"},{"key":"jneae89e8bib62","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.129178","type":"journal-article","article-title":"Is mamba effective for time series forecasting?","volume":"619","author":"Wang","year":"2025","journal-title":"Neurocomputing"},{"key":"jneae89e8bib63","doi-asserted-by":"crossref","DOI":"10.3233\/FAIA240677","type":"conference-proceedings","article-title":"TimeMachine: a time series is worth 4 mambas for long-term forecasting","author":"Ahamed","year":"2024"},{"key":"jneae89e8bib64","doi-asserted-by":"crossref","DOI":"10.52202\/079017-4463","type":"conference-proceedings","article-title":"UniTS: a unified multi-task time series model","author":"Gao","year":"2024"},{"key":"jneae89e8bib65","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1038\/s41597-021-00883-1","type":"journal-article","article-title":"Continuous sensorimotor rhythm based brain computer interface learning in a large population","volume":"8","author":"Stieger","year":"2021","journal-title":"Sci. Data"},{"key":"jneae89e8bib66","first-page":"pp 151","type":"conference-proceedings","article-title":"RISE: randomized input sampling for explanation of black-box models","author":"Petsiuk","year":"2018"},{"key":"jneae89e8bib67","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-24466-x","type":"journal-article","article-title":"Adaptive EEG preprocessing to mitigate electrode shift variability for robust motor imagery classification","volume":"15","author":"Xiong","year":"2025","journal-title":"Sci. Rep."},{"key":"jneae89e8bib68","article-title":"Mega: moving average equipped gated attention","author":"Xuezhe","year":"2022","type":"preprint"},{"key":"jneae89e8bib69","first-page":"5","type":"journal-article","article-title":"Standardized low-resolution brain electromagnetic tomography (sLORETA): technical details","volume":"24","author":"Pascual-Marqui","year":"2002","journal-title":"Methods Find. Exp. Clin. Pharmacol."},{"key":"jneae89e8bib70","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2201128119","type":"journal-article","article-title":"Deep neural networks constrained by neural mass models improve electrophysiological source imaging of spatiotemporal brain dynamics","volume":"119","author":"Sun","year":"2022","journal-title":"Proc. Natl Acad. Sci."}],"container-title":["Journal of Neural Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae89e8","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae89e8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae89e8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae89e8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae89e8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae89e8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae89e8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae89e8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T06:25:17Z","timestamp":1784874317000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae89e8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,24]]},"references-count":70,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,7,24]]},"published-print":{"date-parts":[[2026,8,1]]}},"URL":"https:\/\/doi.org\/10.1088\/1741-2552\/ae89e8","relation":{},"ISSN":["1741-2560","1741-2552"],"issn-type":[{"value":"1741-2560","type":"print"},{"value":"1741-2552","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,24]]},"assertion":[{"value":"Cortical-SSM: a deep state space model for motor imagery decoding from EEG signals","name":"article_title","label":"Article Title"},{"value":"Journal of Neural Engineering","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2026-01-16","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-07-13","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-07-24","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}