{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T13:00:56Z","timestamp":1789477256511,"version":"build-2803163510"},"reference-count":32,"publisher":"AIP Publishing","issue":"1","funder":[{"name":"BIT Research and Innovation Promoting Project","award":["2024YCXY065"],"award-info":[{"award-number":["2024YCXY065"]}]},{"name":"Liaoning Province Science and Technology Department Key Research and Development Project","award":["2023JH26\/10200017"],"award-info":[{"award-number":["2023JH26\/10200017"]}]}],"content-domain":{"domain":["pubs.aip.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,1,1]]},"abstract":"<jats:p>Existing lower limb exoskeletons (LLEs) have demonstrated a lack of sufficient patient involvement during rehabilitation training. To address this issue and better incorporate the patient\u2019s motion intentions, this paper proposes an online brain\u2013computer interface (BCI) system for LLE based motor imagery and stacked ensemble. The establishment of this online BCI system enables a comprehensive closed-loop control process, which includes the collection and decoding of brain signals, robotic control, and real-time feedback mechanisms. Additionally, an online experimental protocol that integrates visual and proprioceptive feedback is developed. To enhance decoding precision, we proposed a novel classification algorithm based on the stacking technique, termed weighted random forests-support vector machines (WRF-SVM). In this algorithm, WRFs function as the base learning models, while SVMs act as the meta-learning layer. To assess the efficacy of the BCI system and the classification algorithm, eight subjects were recruited for testing. The outcomes of both online and offline experiments exhibit high classification accuracy, confirming the viability and utility of the BCI system. We are confident that our approach holds significant promise for practical applications in the field of LLE technology.<\/jats:p>","DOI":"10.1063\/5.0232481","type":"journal-article","created":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T13:49:08Z","timestamp":1737553748000},"update-policy":"https:\/\/doi.org\/10.1063\/aip-crossmark-policy-page","source":"Crossref","is-referenced-by-count":4,"title":["A brain\u2013computer interface system for lower-limb exoskeletons based on motor imagery and stacked ensemble approach"],"prefix":"10.1063","volume":"96","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7779-760X","authenticated-orcid":false,"given":"Jing","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University 1 , Beijing 100191,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4524-496X","authenticated-orcid":false,"given":"Xuxu","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University 1 , Beijing 100191,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7984-7620","authenticated-orcid":false,"given":"Zilin","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University 1 , Beijing 100191,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4300-9111","authenticated-orcid":false,"given":"Huanzhi","family":"Lou","sequence":"additional","affiliation":[{"name":"School of Design and Art, Beijing Institute of Technology 2 , Beijing 100081,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5139-1242","authenticated-orcid":false,"given":"Tong","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shenyang Aerospace University 3 , Shenyang, Liaoning Province 110136,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3679-7026","authenticated-orcid":false,"given":"Cheng","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shenyang Aerospace University 3 , Shenyang, Liaoning Province 110136,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhijun","family":"Gao","sequence":"additional","affiliation":[{"name":"Shenyang Bluewisdom Technology Co., Ltd. 4 , Shenyang, Liaoning Province 110623,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"317","published-online":{"date-parts":[[2025,1,22]]},"reference":[{"key":"2025012213485964700_c1","doi-asserted-by":"publisher","first-page":"5759","DOI":"10.1109\/jsen.2024.3352005","article-title":"Interactive control of lower limb exoskeleton robots: A review","volume":"24","year":"2024","journal-title":"IEEE Sens. J."},{"key":"2025012213485964700_c2","doi-asserted-by":"publisher","first-page":"72","DOI":"10.3109\/17483107.2014.921247","article-title":"Evaluation of the performance of paraplegic subjects during walking with a new design of reciprocal gait orthosis","volume":"11","year":"2016","journal-title":"Disability Rehabil.: Assistive Technol."},{"key":"2025012213485964700_c3","first-page":"724","article-title":"Adaptive assist-as-needed controller to improve gait symmetry in robot-assisted gait training","year":"2014"},{"key":"2025012213485964700_c4","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1016\/j.jocn.2019.07.026","article-title":"Feasibility and safety of Robot Suit HAL treatment for adolescents and adults with cerebral palsy","volume":"68","year":"2019","journal-title":"J.\u00a0Clin. Neurosci."},{"key":"2025012213485964700_c5","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1310\/sci2102-110","article-title":"Time and effort required by Persons with spinal cord injury to learn to use a powered exoskeleton for assisted walking","volume":"21","year":"2015","journal-title":"Top. Spinal Cord Inj. Rehabil."},{"key":"2025012213485964700_c6","first-page":"1","article-title":"Differentiating ability in users of the rewalk TM powered exoskeleton: An analysis of walking kinematics","year":"2013"},{"key":"2025012213485964700_c7","doi-asserted-by":"publisher","first-page":"33401","DOI":"10.1007\/s11042-023-14733-2","article-title":"Gait reference trajectory generation at different walking speeds using LSTM and CNN","volume":"82","year":"2023","journal-title":"Multimedia Tools Appl."},{"key":"2025012213485964700_c8","doi-asserted-by":"publisher","first-page":"4191","DOI":"10.1109\/TMECH.2024.3367348","article-title":"Gait-generation strategy for lower limb exoskeleton based on central pattern generator","volume":"29","year":"2024","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"2025012213485964700_c9","doi-asserted-by":"publisher","first-page":"108954","DOI":"10.1016\/j.engappai.2024.108954","article-title":"A wearable knee rehabilitation system based on graphene textile composite sensor: Implementation and validation","volume":"136","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"2025012213485964700_c10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tase.2024.3421318","article-title":"Robust sensor fusion and biomimetic control of a lower-limb exoskeleton with multimodal sensors","volume":"2024","year":"2024","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"2025012213485964700_c11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tmech.2024.3453037","article-title":"Gait planning and multimodal human-exoskeleton cooperative control based on central pattern generator","volume":"2024","year":"2024","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"2025012213485964700_c12","doi-asserted-by":"publisher","first-page":"730965","DOI":"10.3389\/fnbot.2021.730965","article-title":"Environment classification for robotic leg prostheses and exoskeletons using deep convolutional neural networks","volume":"15","year":"2022","journal-title":"Front. Neurorobot."},{"key":"2025012213485964700_c13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tim.2022.3141163","article-title":"Toward generalization of sEMG-based pattern recognition: A novel feature extraction for gesture recognition","volume":"71","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"2025012213485964700_c14","doi-asserted-by":"publisher","first-page":"106311","DOI":"10.1016\/j.bspc.2024.106311","article-title":"A novel deep transfer learning framework integrating general and domain-specific features for EEG-based brain\u2013computer interface","volume":"95","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"2025012213485964700_c15","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1109\/tnsre.2023.3346462","article-title":"Lower limb activity recognition based on sEMG using stacked weighted random forest","volume":"32","year":"2024","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"2025012213485964700_c16","doi-asserted-by":"publisher","first-page":"105556","DOI":"10.1016\/j.bspc.2023.105556","article-title":"Manifold embedded instance selection to suppress negative transfer in motor imagery-based brain\u2013computer interface","volume":"88","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"2025012213485964700_c17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tim.2023.3300424","article-title":"STMI: Stiffness estimation method based on sEMG-driven model for elbow joint","volume":"72","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"2025012213485964700_c18","doi-asserted-by":"publisher","first-page":"107910","DOI":"10.1016\/j.compbiomed.2023.107910","article-title":"Boosting lower-limb motor imagery performance through an ensemble method for gait rehabilitation","volume":"169","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"2025012213485964700_c19","doi-asserted-by":"publisher","first-page":"2615","DOI":"10.1109\/tnsre.2020.3037326","article-title":"A multi-scale fusion convolutional neural network based on attention mechanism for the visualization analysis of EEG signals decoding","volume":"28","year":"2020","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"2025012213485964700_c20","doi-asserted-by":"publisher","first-page":"1534","DOI":"10.1109\/tnsre.2021.3099908","article-title":"A temporal-spectral-based squeeze-and- excitation feature fusion network for motor imagery EEG decoding","volume":"29","year":"2021","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"2025012213485964700_c21","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","year":"2018","journal-title":"J.\u00a0Neural Eng."},{"key":"2025012213485964700_c22","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1016\/j.asoc.2018.11.031","article-title":"Classification of multiple motor imagery using deep convolutional neural networks and spatial filters","volume":"75","year":"2019","journal-title":"Appl. Soft Comput."},{"key":"2025012213485964700_c23","doi-asserted-by":"publisher","first-page":"6084","DOI":"10.1109\/access.2018.2889093","article-title":"Wavelet transform time-frequency image and convolutional network-based motor imagery EEG classification","volume":"7","year":"2019","journal-title":"IEEE Access"},{"key":"2025012213485964700_c24","first-page":"6000","article-title":"Attention is all you need","volume":"30","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2025012213485964700_c25","doi-asserted-by":"publisher","first-page":"104554","DOI":"10.1016\/j.compbiomed.2021.104554","article-title":"A novel stacking technique for prediction of diabetes","volume":"135","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"2025012213485964700_c26","doi-asserted-by":"publisher","first-page":"113127","DOI":"10.1016\/j.eswa.2019.113127","article-title":"A hierarchical structure based on stacking approach for skin lesion classification","volume":"145","year":"2020","journal-title":"Expert Syst. Appl."},{"key":"2025012213485964700_c27","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1016\/j.knosys.2019.04.015","article-title":"A weighted random survival forest","volume":"177","year":"2019","journal-title":"Knowl. Based Syst."},{"key":"2025012213485964700_c28","doi-asserted-by":"publisher","first-page":"1485","DOI":"10.3390\/mi13091485","article-title":"Deep convolutional neural network for EEG-Based motor decoding","volume":"13","year":"2022","journal-title":"Micromachines"},{"key":"2025012213485964700_c29","doi-asserted-by":"publisher","first-page":"3188","DOI":"10.1109\/tnsre.2023.3299355","article-title":"A temporal dependency learning CNN with attention mechanism for MI-EEG decoding","volume":"31","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"2025012213485964700_c30","doi-asserted-by":"publisher","first-page":"102983","DOI":"10.1016\/j.bspc.2021.102983","article-title":"Boosting-LDA algriothm with multi-domain feature fusion for motor imagery EEG decoding","volume":"70","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"2025012213485964700_c31","doi-asserted-by":"publisher","first-page":"8200","DOI":"10.1016\/j.jfranklin.2023.05.030","article-title":"Novel neuromuscular controller application method to improve the balance recovery ability of lower limb exoskeletons","volume":"360","year":"2023","journal-title":"J.\u00a0Franklin Inst."},{"key":"2025012213485964700_c32","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/s10462-023-10520-5","article-title":"Brain works principle followed by neural information processing: A review of novel brain theory","volume":"56","year":"2023","journal-title":"Artif. Intell. Rev."}],"container-title":["Review of Scientific Instruments"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.aip.org\/aip\/rsi\/article-pdf\/doi\/10.1063\/5.0232481\/20356942\/015114_1_5.0232481.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.aip.org\/aip\/rsi\/article-pdf\/doi\/10.1063\/5.0232481\/20356942\/015114_1_5.0232481.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T13:49:11Z","timestamp":1737553751000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.aip.org\/rsi\/article\/96\/1\/015114\/3331948\/A-brain-computer-interface-system-for-lower-limb"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,1]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1,1]]}},"URL":"https:\/\/doi.org\/10.1063\/5.0232481","relation":{},"ISSN":["0034-6748","1089-7623"],"issn-type":[{"value":"0034-6748","type":"print"},{"value":"1089-7623","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,1,1]]},"published":{"date-parts":[[2025,1,1]]},"article-number":"015114"}}