{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:25:37Z","timestamp":1790270737773,"version":"4.1.0"},"reference-count":52,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T00:00:00Z","timestamp":1750377600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100022963","name":"Key Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","award":["2024C03040"],"award-info":[{"award-number":["2024C03040"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurosci."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Motor imagery (MI)-based brain-computer interfaces (BCI) offers promising applications in rehabilitation. Traditional force-based MI-BCI paradigms generally require subjects to imagine constant force during static or dynamic state. It is challenging to meet the demands of dynamic interaction with force intensity variation in MI-BCI systems.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>To address this gap, we designed a novel MI paradigm inspired by daily life, where subjects imagined variations in force intensity during dynamic unilateral upper-limb movements. In a single trial, the subjects were required to complete one of three combinations of force intensity variations: large-to-small, large-to-medium, or medium-to-small. During the execution of this paradigm, electroencephalography (EEG) features exhibit dynamic coupling, with subtle variations in intensity, timing, frequency coverage, and spatial distribution, as the force intensity imagined by the subjects changed. To recognize these fine-grained features, we propose a feature fusion network with a spatial-temporal-enhanced strategy and an information reconstruction (FN-SSIR) algorithm. This model combines a multi-scale spatial-temporal convolution module with a spatial-temporal-enhanced strategy, a convolutional auto-encoder for information reconstruction, and a long short-term memory with self-attention, enabling the comprehensive extraction and fusion of EEG features across fine-grained time-frequency variations and dynamic spatial-temporal patterns.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The proposed FN-SSIR achieved a classification accuracy of 86.7% \u00b1 6.6% on our force variation MI dataset, and 78.4% \u00b1 13.0% on the BCI Competition IV 2a dataset.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>These findings highlight the potential of this paradigm and algorithm for advancing MI-BCI systems in rehabilitation training based on dynamic force interactions.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnins.2025.1591398","type":"journal-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T05:23:29Z","timestamp":1750397009000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A feature fusion network with spatial-temporal-enhanced strategy for the motor imagery of force intensity variation"],"prefix":"10.3389","volume":"19","author":[{"given":"Ankai","family":"Ying","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinwang","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junchen","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peixin","family":"Si","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guokun","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1421922","DOI":"10.3389\/fnhum.2024.1421922","article-title":"Harnessing few-shot learning for EEG signal classification: A survey of state-of-the-art techniques and future directions.","volume":"18","author":"Ahuja","year":"2024","journal-title":"Front. Hum. Neurosci."},{"key":"B2","doi-asserted-by":"publisher","first-page":"14681","DOI":"10.1007\/s00521-021-06352-5","article-title":"Deep learning techniques for classification of electroencephalogram (EEG) motor imagery (MI) signals: A review.","volume":"35","author":"Altaheri","year":"","journal-title":"Neural Comput. Appl."},{"key":"B3","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. Ind. Inform."},{"key":"B4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12984-021-00820-8","article-title":"Brain\u2013computer interface robotics for hand rehabilitation after stroke: A systematic review.","volume":"18","author":"Baniqued","year":"2021","journal-title":"J. NeuroEng. Rehabil."},{"key":"B5","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1109\/THMS.2021.3115094","article-title":"A systematic review on motor-imagery brain-connectivity-based computer interfaces.","volume":"51","author":"Brusini","year":"2021","journal-title":"IEEE Trans. Hum. Mach. Syst."},{"key":"B6","doi-asserted-by":"publisher","first-page":"13776","DOI":"10.1109\/JSEN.2020.3005968","article-title":"Decoding EEG rhythms during action observation, motor imagery, and execution for standing and sitting.","volume":"20","author":"Chaisaen","year":"2020","journal-title":"IEEE Sens. J."},{"key":"B7","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks.","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"B8","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1109\/BioCAS.2016.7833851","article-title":"EEG channel interpolation using ellipsoid geodesic length","author":"Courellis","year":"2016","journal-title":"Proceedings of the 2016 IEEE biomedical circuits and systems conference (BioCAS)"},{"key":"B9","doi-asserted-by":"publisher","first-page":"990892","DOI":"10.3389\/fncom.2022.990892","article-title":"Analysis of instantaneous brain interactions contribution to a motor imagery classification task.","volume":"16","author":"Cristancho Cuervo","year":"2022","journal-title":"Front. Comput. Neurosci."},{"key":"B10","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.jneumeth.2003.10.009","article-title":"EEGLAB: An open source toolbox for analysis of single-trial EEG dynamics including independent component analysis.","volume":"134","author":"Delorme","year":"2004","journal-title":"J. Neurosci. Methods"},{"key":"B11","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1016\/j.eswa.2018.08.031","article-title":"An end-to-end deep learning approach to MI-EEG signal classification for BCIs.","volume":"114","author":"Dose","year":"2018","journal-title":"Expert Syst. Appl."},{"key":"B12","doi-asserted-by":"publisher","first-page":"1169","DOI":"10.1109\/TSMCC.2012.2226444","article-title":"A new gaze-BCI-driven control of an upper limb exoskeleton for rehabilitation in real-world tasks.","volume":"42","author":"Frisoli","year":"2012","journal-title":"IEEE Trans. Syst. Man Cybern. Part C Appl. Rev."},{"key":"B13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4018\/IJSWIS.337286","article-title":"Channel semantic enhancement-based emotional recognition method using SCLE-2D-CNN.","volume":"20","author":"Fu","year":"2024","journal-title":"Int. J. Seman. Web Inf. Syst."},{"key":"B14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.heliyon.2024.e30016","article-title":"Changes in spinal motoneuron excitability during the improvement of fingertip dexterity by actual execution combined with motor imagery practice.","volume":"10","author":"Fukumoto","year":"2024","journal-title":"Heliyon"},{"key":"B15","doi-asserted-by":"publisher","first-page":"3878","DOI":"10.1109\/TNSRE.2024.3487216","article-title":"A novel multi-feature fusion network with spatial partitioning strategy and cross-attention for armband-based gesture recognition.","volume":"32","author":"Hu","year":"2024","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"B16","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift.","author":"Ioffe","year":"2015","journal-title":"arXiv"},{"key":"B17","doi-asserted-by":"publisher","first-page":"52978","DOI":"10.1109\/ACCESS.2024.3386554","article-title":"Object weight perception in motor imagery using fourier-based synchrosqueezing transform and regularized common spatial patterns.","volume":"12","author":"Karakullukcu","year":"2024","journal-title":"IEEE Access"},{"key":"B18","doi-asserted-by":"publisher","first-page":"26002","DOI":"10.1038\/s41598-024-77876-8","article-title":"Fusing convolutional learning and attention-based Bi-LSTM networks for early Alzheimer\u2019s diagnosis from EEG signals towards IoMT.","volume":"14","author":"Khosravi","year":"2024","journal-title":"Sci. Rep."},{"key":"B19","doi-asserted-by":"publisher","first-page":"120054","DOI":"10.1016\/j.neuroimage.2023.120054","article-title":"Deep learning-based EEG analysis to classify normal, mild cognitive impairment, and dementia: Algorithms and dataset.","volume":"272","author":"Kim","year":"2023","journal-title":"Neuroimage"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1","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":"B21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.bspc.2021.103342","article-title":"Motor imagery EEG classification algorithm based on CNN-LSTM feature fusion network.","volume":"72","author":"Li","year":"2022","journal-title":"Biomed. Signal Process. Control"},{"key":"B22","doi-asserted-by":"publisher","first-page":"975","DOI":"10.1007\/s11571-022-09875-2","article-title":"A novel noninvasive brain\u2013computer interface by imagining isometric force levels.","volume":"17","author":"Li","year":"2023","journal-title":"Cogn. Neurodyn."},{"key":"B23","doi-asserted-by":"publisher","first-page":"1392599","DOI":"10.3389\/fbioe.2024.1392599","article-title":"Multi-mode adaptive control strategy for a lower limb rehabilitation robot.","volume":"12","author":"Liang","year":"2024","journal-title":"Front. Bioeng. Biotechnol."},{"key":"B24","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1109\/TBME.2022.3193277","article-title":"FBMSNet: A filter-bank multi-scale convolutional neural network for EEG-based motor imagery decoding.","volume":"70","author":"Liu","year":"2023","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"B25","doi-asserted-by":"publisher","first-page":"1116721","DOI":"10.3389\/fnins.2023.1116721","article-title":"Transformed common spatial pattern for motor imagery-based brain-computer interfaces.","volume":"17","author":"Ma","year":"2023","journal-title":"Front. Neurosci."},{"key":"B26","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1523\/JNEUROSCI.5371-13.2015","article-title":"Alpha and beta band event-related desynchronization reflects kinematic regularities.","volume":"35","author":"Meirovitch","year":"2015","journal-title":"J. Neurosci."},{"key":"B27","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/s43154-020-00015-4","article-title":"Human-robot interaction in rehabilitation and assistance: A review.","volume":"1","author":"Mohebbi","year":"2020","journal-title":"Curr. Robot. Rep."},{"key":"B28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/BCI57258.2023.10078658","article-title":"A channel selection method for motor imagery EEG based on fisher score of OVR-CSP","author":"Mu","year":"2023","journal-title":"Proceedings of the 2023 11th international winter conference on brain-computer interface (BCI)"},{"key":"B29","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/s13755-021-00142-y","article-title":"Crosstalk disrupts the production of motor imagery brain signals in brain\u2013computer interfaces.","volume":"9","author":"Neo","year":"2021","journal-title":"Health Inf. Sci. Syst."},{"key":"B30","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":"B31","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1109\/TNSRE.2024.3351863","article-title":"M-FANet: Multi-feature attention convolutional neural network for motor imagery decoding.","volume":"32","author":"Qin","year":"2024","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"B32","doi-asserted-by":"publisher","first-page":"25","DOI":"10.3389\/fnbot.2020.00025","article-title":"Current status, challenges, and possible solutions of EEG-based brain-computer interface: A comprehensive review.","volume":"14","author":"Rashid","year":"2020","journal-title":"Front. Neurorobotics"},{"key":"B33","doi-asserted-by":"publisher","first-page":"103241","DOI":"10.1016\/j.bspc.2021.103241","article-title":"High accuracy decoding of motor imagery directions from EEG-based brain computer interface using filter bank spatially regularised common spatial pattern method.","volume":"72","author":"Rithwik","year":"2022","journal-title":"Biomed. Signal Process. Control"},{"key":"B34","doi-asserted-by":"publisher","first-page":"051001","DOI":"10.1088\/1741-2552\/ab260c","article-title":"Deep learning-based electroencephalography analysis: A systematic review.","volume":"16","author":"Roy","year":"2019","journal-title":"J. Neural Eng."},{"key":"B35","doi-asserted-by":"publisher","first-page":"578875","DOI":"10.3389\/fnsys.2021.578875","article-title":"Progress in brain computer interface: Challenges and opportunities.","volume":"15","author":"Saha","year":"2021","journal-title":"Front. Syst. Neurosci."},{"key":"B36","doi-asserted-by":"publisher","first-page":"1962","DOI":"10.1111\/ejn.14629","article-title":"Dynamics of movement-related cortical potentials and sensorimotor oscillations during palmar grasp movements.","volume":"51","author":"Savi\u0107","year":"2020","journal-title":"Eur. J. Neurosci."},{"key":"B37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/e25030464","article-title":"A multi-scale temporal convolutional network with attention mechanism for force level classification during motor imagery of unilateral upper-limb movements.","volume":"25","author":"Sheng","year":"2023","journal-title":"Entropy"},{"key":"B38","doi-asserted-by":"publisher","first-page":"55","DOI":"10.3389\/fnins.2012.00055","article-title":"Review of the BCI competition IV","volume":"6","author":"Tangermann","year":"2012","journal-title":"Front. Neurosci."},{"key":"B39","article-title":"Attention is all you need.","author":"Vaswani","year":"2023","journal-title":"arXiv"},{"key":"B40","article-title":"Long short-term memory RNN.","author":"Venner\u00f8d","year":"2021","journal-title":"arXiv"},{"key":"B41","doi-asserted-by":"publisher","first-page":"104627","DOI":"10.1016\/j.bspc.2023.104627","article-title":"A 2D CNN-LSTM hybrid algorithm using time series segments of EEG data for motor imagery classification.","volume":"83","author":"Wang","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"B42","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1186\/s12984-017-0307-1","article-title":"A brain-computer interface driven by imagining different force loads on a single hand: An online feasibility study.","volume":"14","author":"Wang","year":"2017","journal-title":"J. Neuroeng. Rehabil."},{"key":"B43","doi-asserted-by":"publisher","first-page":"1075","DOI":"10.1109\/ICCSEC.2017.8446999","article-title":"Comparison of EEG changes during action observation, action observation combined with motor imagery and motor execution of lower limb","author":"Wang","year":"2017","journal-title":"Proceedings of the 2017 international conference on computer systems, electronics and control (ICCSEC)"},{"key":"B44","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1016\/j.neunet.2023.11.037","article-title":"BrainGridNet: A two-branch depthwise CNN for decoding EEG-based multi-class motor imagery.","volume":"170","author":"Wang","year":"2024","journal-title":"Neural Netw."},{"key":"B45","doi-asserted-by":"publisher","first-page":"7078","DOI":"10.1109\/JBHI.2024.3452701","article-title":"EEG characteristic comparison of motor imagery between supernumerary and inherent limb: Sixth-finger MI enhances the ERD pattern and classification performance.","volume":"28","author":"Wang","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"B46","doi-asserted-by":"publisher","first-page":"2092","DOI":"10.1109\/tbme.2014.2313867","article-title":"A closed-loop brain-computer interface triggering an active ankle-foot orthosis for inducing cortical neural plasticity.","volume":"61","author":"Xu","year":"2014","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"B47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/s24072323","article-title":"The EEG-based fusion entropy-featured identification of isometric contraction forces under the same action.","volume":"24","author":"Yao","year":"2024","journal-title":"Sensors"},{"key":"B48","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1186\/1743-0003-10-106","article-title":"EEG feature comparison and classification of simple and compound limb motor imagery.","volume":"10","author":"Yi","year":"2013","journal-title":"J. Neuroeng. Rehabil."},{"key":"B49","doi-asserted-by":"publisher","first-page":"2596","DOI":"10.1016\/j.neuroimage.2009.10.028","article-title":"Negative covariation between task-related responses in alpha\/beta-band activity and BOLD in human sensorimotor cortex: An EEG and fMRI study of motor imagery and movements.","volume":"49","author":"Yuan","year":"2010","journal-title":"Neuroimage"},{"key":"B50","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.brainres.2011.06.038","article-title":"Behavioral improvements and brain functional alterations by motor imagery training.","volume":"1407","author":"Zhang","year":"2011","journal-title":"Brain Res."},{"key":"B51","doi-asserted-by":"publisher","first-page":"3859","DOI":"10.1007\/s11571-024-10164-3","article-title":"Decoding of movement-related cortical potentials at different speeds.","volume":"18","author":"Zhang","year":"2024","journal-title":"Cogn. Neurodyn."},{"key":"B52","doi-asserted-by":"publisher","first-page":"2164","DOI":"10.1109\/TNSRE.2019.2938295","article-title":"A multi-branch 3D convolutional neural network for EEG-based motor imagery classification.","volume":"27","author":"Zhao","year":"2019","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2025.1591398\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T05:23:30Z","timestamp":1750397010000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2025.1591398\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":52,"alternative-id":["10.3389\/fnins.2025.1591398"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2025.1591398","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,20]]},"article-number":"1591398"}}