{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T02:37:16Z","timestamp":1794537436060,"version":"4.9.1"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:00:00Z","timestamp":1732838400000},"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>Brain-computer interfaces (BCIs) establish a direct communication pathway between the brain and external devices and have been widely applied in upper limb rehabilitation for hemiplegic patients. However, significant individual variability in motor imagery electroencephalogram (MI-EEG) signals leads to poor generalization performance of MI-based BCI decoding methods to new patients. This paper proposes a Multi-scale Frequency domain Feature-based Dynamic graph Attention Network (MFF-DANet) for upper limb MI decoding in hemiplegic patients. MFF-DANet employs convolutional kernels of various scales to extract feature information across multiple frequency bands, followed by a channel attention-based average pooling operation to retain the most critical frequency domain features. Additionally, MFF-DANet integrates a graph attention convolutional network to capture spatial topological features across different electrode channels, utilizing electrode positions as prior knowledge to construct and update the graph adjacency matrix. We validated the performance of MFF-DANet on the public PhysioNet dataset, achieving optimal decoding accuracies of 61.6% for within-subject case and 52.7% for cross-subject case. t-Distributed Stochastic Neighbor Embedding (t-SNE) visualization of the features demonstrates the effectiveness of each designed module, and visualization of the adjacency matrix indicates that the extracted spatial topological features have physiological interpretability.<\/jats:p>","DOI":"10.3389\/fnins.2024.1493264","type":"journal-article","created":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T07:09:25Z","timestamp":1732864165000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Dynamic graph attention network based on multi-scale frequency domain features for motion imagery decoding in hemiplegic patients"],"prefix":"10.3389","volume":"18","author":[{"given":"Yinan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lizhou","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yewei","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanxu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,11,29]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"102172","DOI":"10.1016\/j.bspc.2020.102172","article-title":"Deep learning for motor imagery EEG-based classification: a review","volume":"63","author":"Al-Saegh","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"ref2","author":"Andac","year":"2021"},{"key":"ref3","author":"Ang","year":"2008"},{"key":"ref4","author":"Anh","year":"2015"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1038\/s41583-023-00752-3","article-title":"Towards a biologically annotated brain connectome","volume":"24","author":"Bazinet","year":"2023","journal-title":"Nat. Rev. Neurosci."},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1109\/IJCNN.2014.6889535","article-title":"A novel classification method for motor imagery based on brain-computer Interface","author":"Chen","year":"2014"},{"key":"ref7","author":"Demir","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1113\/jphysiol.2006.123067","article-title":"Brain\u2013computer interface technology as a tool to augment plasticity and outcomes for neurological rehabilitation","volume":"579","author":"Dobkin","year":"2007","journal-title":"J. Physiol."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"2150047","DOI":"10.1142\/S0129065721500477","article-title":"Motor intention decoding from the upper limb by graph convolutional network based on functional connectivity","volume":"31","author":"Feng","year":"2021","journal-title":"Int. J. Neural Syst."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1109\/TBME.2004.827072","article-title":"BCI2000: a general-purpose brain-computer interface (BCI) system","volume":"51","author":"Gerwin","year":"2004","journal-title":"I.E.E.E. Trans. Biomed. Eng."},{"key":"ref11","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":"ref12","doi-asserted-by":"publisher","first-page":"7312","DOI":"10.1109\/TNNLS.2022.3202569","article-title":"GCNs-net: a graph convolutional neural network approach for decoding time-resolved eeg motor imagery signals","volume":"35","author":"Hou","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1016\/j.jneumeth.2009.01.015","article-title":"Neurofeedback-based motor imagery training for brain\u2013computer interface (BCI)","volume":"179","author":"Hwang","year":"2009","journal-title":"J. Neurosci. Methods"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","first-page":"041001","DOI":"10.1088\/1741-2552\/aba162","article-title":"BCI for stroke rehabilitation: motor and beyond","volume":"17","author":"Mane","year":"2020","journal-title":"J. Neural Eng."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1711.06104","article-title":"Towards better understanding of gradient-based attribution methods for deep neural networks","author":"Marco","year":"2017","journal-title":"arXiv"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1109\/TNSRE.2012.2229296","article-title":"Classification of motor imagery BCI using multivariate empirical mode decomposition","volume":"21","author":"Park","year":"2012","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref18","author":"Ribeiro","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"5619","DOI":"10.1109\/TNNLS.2018.2789927","article-title":"Learning temporal information for brain-computer interface using convolutional neural networks","volume":"29","author":"Sakhavi","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"704603","DOI":"10.3389\/fnins.2021.704603","article-title":"MCSNet: channel synergy-based human-exoskeleton interface with surface electromyogram","volume":"15","author":"Shi","year":"2021","journal-title":"Front. Neurosci."},{"key":"ref21","author":"Shi","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1600","DOI":"10.1016\/j.neuroimage.2006.09.024","article-title":"10\/20, 10\/10, and 10\/5 systems revisited: their validity as relative head-surface-based positioning systems","volume":"34","author":"Valer","year":"2007","journal-title":"NeuroImage"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/s11517-018-1883-3","article-title":"The control of a virtual automatic car based on multiple patterns of motor imagery BCI","volume":"57","author":"Wang","year":"","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2020.3047502","article-title":"Linking attention-based multiscale cnn with dynamical gcn for driving fatigue detection","volume":"70","author":"Wang","year":"","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"86850","DOI":"10.1109\/ACCESS.2020.2992631","article-title":"An approach of one-vs-rest filter bank common spatial pattern and spiking neural networks for multiple motor imagery decoding","volume":"8","author":"Wang","year":"","journal-title":"IEEE Access"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"155590","DOI":"10.1109\/ACCESS.2020.3018962","article-title":"Diverse feature blend based on filter-bank common spatial pattern and brain functional connectivity for multiple motor imagery detection","volume":"8","author":"Wang","year":"","journal-title":"IEEE Access"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"e68910","DOI":"10.1371\/journal.pone.0068910","article-title":"BrainNet viewer: a network visualization tool for human brain connectomics","volume":"8","author":"Xia","year":"2013","journal-title":"PLoS One"},{"key":"ref28","author":"Yang","year":"2015"},{"key":"ref29","author":"Zhang","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/j.neunet.2019.02.009","article-title":"Learning joint space\u2013time\u2013frequency features for EEG decoding on small labeled data","volume":"114","author":"Zhao","year":"2019","journal-title":"Neural Netw."}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2024.1493264\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T07:09:27Z","timestamp":1732864167000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2024.1493264\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,29]]},"references-count":30,"alternative-id":["10.3389\/fnins.2024.1493264"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2024.1493264","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,29]]},"article-number":"1493264"}}