{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T13:01:57Z","timestamp":1780923717954,"version":"3.54.1"},"reference-count":29,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T00:00:00Z","timestamp":1780876800000},"content-version":"vor","delay-in-days":7,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T00:00:00Z","timestamp":1780876800000},"content-version":"tdm","delay-in-days":7,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62472319"],"award-info":[{"award-number":["62472319"]}],"id":[{"id":"10.13039\/501100001809","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":[[2026,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective.<\/jats:italic>\n                    Surface electromyography (sEMG)-based motion recognition technologies have found widespread application across various fields. While researchers increasingly emphasize the decoding of complex real-world movements, significant challenges remain in sequential feature extraction, application generalization, and other aspects.\n                    <jats:italic>Approach.<\/jats:italic>\n                    To address this, we propose a novel Transformer-based architecture named multi-interval driven transformer (MIDT). The network introduces a muscle correlation-guided adaptive segmentation module aligning signal partitions with motor phase transitions, and applies hierarchical self-attention mechanisms within and across intervals to capture sub-movement features and long-range dependencies, thereby improving sequential feature modeling. We validated the effectiveness of MIDT on a new sequential movement-based sEMG dataset. This dataset includes recording data from 10 subjects and uses 4 types of upper-limb sequential movement paradigms.\n                    <jats:italic>Main results.<\/jats:italic>\n                    The proposed MIDT architecture achieves a classification accuracy of 92.56% on the ULSE dataset, surpassing state-of-the-art models by 5.07% with 46.14% lower cross-subject variance for superior robustness. It also reaches 80.93% top accuracy on the public dataset, outperforming mainstream methods.\n                    <jats:italic>Significance.<\/jats:italic>\n                    Through visualization analysis, MIDT enables decoding of sub-movement execution and motion state transitions, thereby providing quantitative technical support for personalized and refined motion control and rehabilitation assessment. These findings fully demonstrate the broad application potential of MIDT in wearable human-machine interfaces and neurorehabilitation engineering.\n                  <\/jats:p>","DOI":"10.1088\/1741-2552\/ae697a","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T22:54:30Z","timestamp":1778108070000},"page":"036029","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Transformer-based network with spatial correlation change and multi-segment attention for sequential EMG recognition"],"prefix":"10.1088","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7769-3800","authenticated-orcid":true,"given":"Xianghe","family":"Chen","sequence":"first","affiliation":[{"name":"Tongji University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6984-7648","authenticated-orcid":true,"given":"Lugui","family":"Xia","sequence":"additional","affiliation":[{"name":"Tongji University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9299-3251","authenticated-orcid":true,"given":"Jie","family":"Li","sequence":"additional","affiliation":[{"name":"Tongji University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhilin","family":"Li","sequence":"additional","affiliation":[{"name":"Tongji University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Tongji University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongfei","family":"Bai","sequence":"additional","affiliation":[{"name":"Tongji University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongfei","family":"Ji","sequence":"additional","affiliation":[{"name":"Tongji University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingjing","family":"Jin","sequence":"additional","affiliation":[{"name":"Tongji University"},{"name":"Tongji University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,6,8]]},"reference":[{"key":"jneae697abib1","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1109\/JAS.2021.1003865","type":"journal-article","article-title":"Deep learning for EMG-based human-machine interaction: a review","volume":"8","author":"Xiong","year":"2021","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"jneae697abib2","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1038\/s41528-023-00246-3","type":"journal-article","article-title":"Stretchable array electromyography sensor with graph neural network for static and dynamic gestures recognition system","volume":"7","author":"Lee","year":"2023","journal-title":"npj Flex. Electron."},{"key":"jneae697abib3","doi-asserted-by":"publisher","first-page":"10200","DOI":"10.1109\/LRA.2022.3192623","type":"journal-article","article-title":"Electromyography-based, robust hand motion classification employing temporal multi-channel vision transformers","volume":"7","author":"Godoy","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"jneae697abib4","doi-asserted-by":"publisher","first-page":"23649","DOI":"10.1109\/JSEN.2022.3220930","type":"journal-article","article-title":"EEG-and EMG-driven poststroke rehabilitation: a review","volume":"22","author":"Yang","year":"2022","journal-title":"IEEE Sens. J."},{"key":"jneae697abib5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0302707","type":"journal-article","article-title":"Combining enhanced spectral resolution of EMG and a deep learning approach for knee pathology diagnosis","volume":"19","author":"Khader","year":"2024","journal-title":"PLoS One"},{"key":"jneae697abib6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41586-025-09255-w","type":"journal-article","article-title":"A generic non-invasive neuromotor interface for human-computer interaction","volume":"645","author":"Kaifosh","year":"2025","journal-title":"Nature"},{"key":"jneae697abib7","doi-asserted-by":"publisher","first-page":"85","DOI":"10.3390\/bios10080085","type":"journal-article","article-title":"EMG-centered multisensory based technologies for pattern recognition in rehabilitation: state of the art and challenges","volume":"10","author":"Fang","year":"2020","journal-title":"Biosensors"},{"key":"jneae697abib8","doi-asserted-by":"publisher","first-page":"174940","DOI":"10.1109\/ACCESS.2019.2956951","type":"journal-article","article-title":"A continuous estimation model of upper limb joint angles by using surface electromyography and deep learning method","volume":"7","author":"Chen","year":"2019","journal-title":"IEEE Access"},{"key":"jneae697abib9","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0262810","type":"journal-article","article-title":"A novel concatenate feature fusion RCNN architecture for sEMG-based hand gesture recognition","volume":"17","author":"Xu","year":"2022","journal-title":"PLoS One"},{"key":"jneae697abib10","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102024","type":"journal-article","article-title":"Continuous estimation of upper limb joint angle from sEMG signals based on SCA-LSTM deep learning approach","volume":"61","author":"Ma","year":"2020","journal-title":"Biomed. Signal Process. Control"},{"key":"jneae697abib11","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1109\/JBHI.2024.3457026","type":"journal-article","article-title":"Sequential sEMG recognition with knowledge transfer and dynamic graph network based on spatio-temporal feature extraction network","volume":"29","author":"Li","year":"2025","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"jneae697abib12","doi-asserted-by":"publisher","first-page":"5998","DOI":"10.48550\/arXiv.1706.03762","type":"journal-article","article-title":"Attention is all you need","volume":"vol 30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"jneae697abib13","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2021.653659","type":"journal-article","article-title":"BENDR: using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG data","volume":"15","author":"Kostas","year":"2021","journal-title":"Front. Hum. Neurosci."},{"key":"jneae697abib14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JBHI.2025.3555255","type":"journal-article","article-title":"Dual transformer network for predicting joint angles and torques from multi-channel EMG signals in the lower limbs","volume":"29","author":"Wang","year":"2025","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"jneae697abib15","first-page":"pp 105","type":"conference-proceedings","article-title":"Feasibility analysis of sEMG recognition via channel-wise transformer","author":"Zhang","year":"2022"},{"key":"jneae697abib16","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbsr.2025.100749","type":"journal-article","article-title":"TraxVBF: a hybrid transformer-xLSTM framework for EMG signal processing and assistive technology development in rehabilitation","volume":"47","author":"Zendehbad","year":"2025","journal-title":"Sens. Bio-Sens. Res."},{"key":"jneae697abib17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109967","type":"journal-article","article-title":"Transformer-based network with temporal depthwise convolutions for sEMG recognition","volume":"145","author":"Wang","year":"2024","journal-title":"Pattern Recognit."},{"key":"jneae697abib18","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1093\/ptj\/46.4.357","type":"journal-article","article-title":"Motor testing procedures in hemiplegia: based on sequential recovery stages","volume":"46","author":"Brunnstrom","year":"1966","journal-title":"Phys. Ther."},{"key":"jneae697abib19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2014.53","type":"journal-article","article-title":"Electromyography data for non-invasive naturally-controlled robotic hand prostheses","volume":"1","author":"Atzori","year":"2014","journal-title":"Sci. Data"},{"key":"jneae697abib20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0186132","type":"journal-article","article-title":"Comparison of six electromyography acquisition setups on hand movement classification tasks","volume":"12","author":"Pizzolato","year":"2017","journal-title":"PLoS One"},{"key":"jneae697abib21","doi-asserted-by":"publisher","first-page":"9","DOI":"10.3389\/fnbot.2016.00009","type":"journal-article","article-title":"Deep learning with convolutional neural networks applied to electromyography data: a resource for the classification of movements for prosthetic hands","volume":"10","author":"Atzori","year":"2016","journal-title":"Front. Neurorobotics"},{"key":"jneae697abib22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0206049","type":"journal-article","article-title":"A novel attention-based hybrid CNN-RNN architecture for sEMG-based gesture recognition","volume":"13","author":"Hu","year":"2018","journal-title":"PLoS One"},{"key":"jneae697abib23","doi-asserted-by":"publisher","first-page":"9700","DOI":"10.3390\/app12199700","type":"journal-article","article-title":"LSTM recurrent neural network for hand gesture recognition using EMG signals","volume":"12","author":"Toro-Ossaba","year":"2022","journal-title":"Appl. Sci."},{"key":"jneae697abib24","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-36490-w","type":"journal-article","article-title":"Transformer-based hand gesture recognition from instantaneous to fused neural decomposition of high-density EMG signals","volume":"13","author":"Montazerin","year":"2023","journal-title":"Sci. Rep."},{"key":"jneae697abib25","first-page":"pp 1509","type":"conference-proceedings","article-title":"sEMG-based continuous hand gesture recognition using GMM-HMM and threshold model","author":"Yang","year":"2017"},{"key":"jneae697abib26","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1034\/j.1600-0404.2003.00021.x","type":"journal-article","article-title":"Motor compensation and recovery for reaching in stroke patients","volume":"107","author":"Roby-Brami","year":"2003","journal-title":"Acta Neurol. Scand."},{"key":"jneae697abib27","doi-asserted-by":"publisher","first-page":"2579","DOI":"10.5555\/2986459.2986743","type":"journal-article","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"jneae697abib28","doi-asserted-by":"publisher","first-page":"940","DOI":"10.1093\/brain\/123.5.940","type":"journal-article","article-title":"Compensatory strategies for reaching in stroke","volume":"123","author":"Cirstea","year":"2000","journal-title":"Brain"},{"key":"jneae697abib29","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.19471609)","type":"journal-article","article-title":"upper-limb sequential sEMG dataset (ULSE)","author":"Xianghe","year":"2026","journal-title":"Zenodo"}],"container-title":["Journal of Neural Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae697a","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae697a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae697a","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae697a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae697a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae697a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae697a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae697a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T12:11:49Z","timestamp":1780920709000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae697a"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,1]]},"references-count":29,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,6,8]]},"published-print":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/1741-2552\/ae697a","relation":{},"ISSN":["1741-2560","1741-2552"],"issn-type":[{"value":"1741-2560","type":"print"},{"value":"1741-2552","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,1]]},"assertion":[{"value":"Transformer-based network with spatial correlation change and multi-segment attention for sequential EMG recognition","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":"2025-11-12","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-05-06","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-06-08","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}