{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T12:30:04Z","timestamp":1789043404472,"version":"build-2803163510"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J NeuroEngineering Rehabil"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Prosthetic legs help individuals with an amputation regain locomotion. Recently, deep neural network (DNN)-based control methods, which take advantage of the end-to-end learning capability of the network, have been proposed. One prominent challenge for these learning-based approaches is obtaining data for the training, particularly for the training of a mid-level controller. In this study, we propose a method for generating synthetic gait patterns (vertical load and lower limb joint angles) using a generative adversarial network (GAN). This approach enables a mid-level controller to execute ambulation modes that are not included in the training datasets.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>The conditional GAN is trained on benchmark datasets that contain the gait data of individuals without amputation; synthetic gait patterns are generated from the user input. Further, a DNN-based controller for the generation of impedance parameters is trained using the synthetic gait pattern and the corresponding synthetic stiffness and damping coefficients.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>The trained GAN generated synthetic gait patterns with a coefficient of determination of 0.97 and a structural similarity index of 0.94 relative to benchmark data that were not included in the training datasets. We trained a DNN-based controller using the GAN-generated synthetic gait patterns for level-ground walking, standing-to-sitting motion, and sitting-to-standing motion. Four individuals without amputation participated in bypass testing and demonstrated the ambulation modes. The model successfully generated control parameters for the knee and ankle based on thigh angle and vertical load.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>This study demonstrates that synthetic gait patterns can be used to train DNN models for impedance control. We believe a conditional GAN trained on benchmark datasets can provide reliable gait data for ambulation modes that are not included in its training datasets. Thus, designing gait data using a conditional GAN could facilitate the efficient and effective training of controllers for prosthetic legs.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12984-023-01232-6","type":"journal-article","created":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T09:01:59Z","timestamp":1693818119000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Generating synthetic gait patterns based on benchmark datasets for controlling prosthetic legs"],"prefix":"10.1186","volume":"20","author":[{"given":"Minjae","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Levi J.","family":"Hargrove","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,9,4]]},"reference":[{"issue":"1","key":"1232_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1743-0003-12-1","volume":"12","author":"MR Tucker","year":"2015","unstructured":"Tucker MR, Olivier J, Pagel A, Bleuler H, Bouri M, Lambercy O, Mill\u00e1n JDR, Riener R, Vallery H, Gassert R. Control strategies for active lower extremity prosthetics and orthotics: a review. J Neuroeng Rehabil. 2015;12(1):1\u201330.","journal-title":"J Neuroeng Rehabil"},{"issue":"4","key":"1232_CR2","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1109\/MRA.2014.2360303","volume":"21","author":"BE Lawson","year":"2014","unstructured":"Lawson BE, Mitchell J, Truex D, Shultz A, Ledoux E, Goldfarb M. A robotic leg prosthesis: design, control, and implementation. IEEE Robot Autom Mag. 2014;21(4):70\u201381.","journal-title":"IEEE Robot Autom Mag"},{"issue":"3","key":"1232_CR3","doi-asserted-by":"publisher","first-page":"6439","DOI":"10.1109\/LRA.2022.3173426","volume":"7","author":"Y Qian","year":"2022","unstructured":"Qian Y, Wang Y, Chen C, Xiong J, Leng Y, Yu H, Fu C. Predictive locomotion mode recognition and accurate gait phase estimation for hip exoskeleton on various terrains. IEEE Robot Autom Lett. 2022;7(3):6439\u201346.","journal-title":"IEEE Robot Autom Lett"},{"key":"1232_CR4","unstructured":"Le D, Cheng S, Gregg RD, Ghaffari M. Deep convolutional neural network and transfer learning for locomotion intent prediction. 2022; arXiv preprint arXiv:2209.12365"},{"issue":"3","key":"1232_CR5","doi-asserted-by":"publisher","first-page":"7779","DOI":"10.1109\/LRA.2022.3185380","volume":"7","author":"J Liu","year":"2022","unstructured":"Liu J, Zhou X, He B, Li P, Wang C, Wu X. A novel method for detecting misclassifications of the locomotion mode in lower-limb exoskeleton robot control. IEEE Robot Autom Lett. 2022;7(3):7779\u201385.","journal-title":"IEEE Robot Autom Lett"},{"issue":"10","key":"1232_CR6","doi-asserted-by":"publisher","first-page":"5873","DOI":"10.1109\/TNNLS.2021.3071727","volume":"33","author":"X Gao","year":"2021","unstructured":"Gao X, Si J, Wen Y, Li M, Huang H. Reinforcement learning control of robotic knee with human-in-the-loop by flexible policy iteration. IEEE Trans Neural Netw Learn Syst. 2021;33(10):5873\u201387.","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"3","key":"1232_CR7","doi-asserted-by":"publisher","first-page":"7014","DOI":"10.1109\/LRA.2022.3179420","volume":"7","author":"R Wu","year":"2022","unstructured":"Wu R, Li M, Yao Z, Liu W, Si J, Huang H. Reinforcement learning impedance control of a robotic prosthesis to coordinate with human intact knee motion. IEEE Robot Autom Lett. 2022;7(3):7014\u201320.","journal-title":"IEEE Robot Autom Lett"},{"issue":"1","key":"1232_CR8","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1109\/TRO.2021.3078317","volume":"38","author":"M Li","year":"2021","unstructured":"Li M, Wen Y, Gao X, Si J, Huang H. Toward expedited impedance tuning of a robotic prosthesis for personalized gait assistance by reinforcement learning control. IEEE Trans Robot. 2021;38(1):407\u201320.","journal-title":"IEEE Trans Robot"},{"key":"1232_CR9","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1017\/wtc.2022.19","volume":"3","author":"M Kim","year":"2022","unstructured":"Kim M, Simon AM, Hargrove LJ. Seamless and intuitive control of a powered prosthetic leg using deep neural network for transfemoral amputees. Wear Technol. 2022;3:24.","journal-title":"Wear Technol"},{"issue":"3","key":"1232_CR10","doi-asserted-by":"publisher","first-page":"1430","DOI":"10.1109\/TRO.2022.3152134","volume":"38","author":"S Hood","year":"2022","unstructured":"Hood S, Gabert L, Lenzi T. Powered knee and ankle prosthesis with adaptive control enables climbing stairs with different stair heights, cadences, and gait patterns. IEEE Trans Robot. 2022;38(3):1430\u201341.","journal-title":"IEEE Trans Robot"},{"issue":"3","key":"1232_CR11","doi-asserted-by":"publisher","first-page":"840","DOI":"10.1109\/TMRB.2022.3185405","volume":"4","author":"S Cheng","year":"2022","unstructured":"Cheng S, Bol\u00edvar-Nieto E, Welker CG, Gregg RD. Modeling the transitional kinematics between variable-incline walking and stair climbing. IEEE Trans Med Robot Bion. 2022;4(3):840\u201351.","journal-title":"IEEE Trans Med Robot Bion"},{"issue":"1","key":"1232_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-021-01057-9","volume":"8","author":"E Reznick","year":"2021","unstructured":"Reznick E, Embry KR, Neuman R, Bol\u00edvar-Nieto E, Fey NP, Gregg RD. Lower-limb kinematics and kinetics during continuously varying human locomotion. Sci Data. 2021;8(1):1\u201312.","journal-title":"Sci Data"},{"issue":"1","key":"1232_CR13","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1109\/JAS.2021.1004272","volume":"9","author":"R Wu","year":"2021","unstructured":"Wu R, Yao Z, Si J, Huang HH. Robotic knee tracking control to mimic the intact human knee profile based on actor-critic reinforcement learning. IEEE\/CAA J Autom Sin. 2021;9(1):19\u201330.","journal-title":"IEEE\/CAA J Autom Sin"},{"issue":"4","key":"1232_CR14","doi-asserted-by":"publisher","first-page":"10597","DOI":"10.1109\/LRA.2022.3194323","volume":"7","author":"M Kim","year":"2022","unstructured":"Kim M, Hargrove LJ. Deep-learning to map a benchmark dataset of non-amputee ambulation for controlling an open source bionic leg. IEEE Robot Autom Lett. 2022;7(4):10597\u2013604.","journal-title":"IEEE Robot Autom Lett"},{"key":"1232_CR15","doi-asserted-by":"crossref","unstructured":"Truong T, Yanushkevich S. Generative adversarial network for radar signal generation. In: Int. Joint Conf. Neural Networks (IJCNN), 2019; pp. 1\u20136","DOI":"10.1109\/IJCNN.2019.8851887"},{"key":"1232_CR16","doi-asserted-by":"publisher","first-page":"15","DOI":"10.3389\/fninf.2020.00015","volume":"14","author":"T-J Luo","year":"2020","unstructured":"Luo T-J, Fan Y, Chen L, Guo G, Zhou C. Eeg signal reconstruction using a generative adversarial network with wasserstein distance and temporal-spatial-frequency loss. Front Neuroinform. 2020;14:15.","journal-title":"Front Neuroinform"},{"issue":"12","key":"1232_CR17","doi-asserted-by":"publisher","first-page":"441","DOI":"10.3390\/biology9120441","volume":"9","author":"D Hazra","year":"2020","unstructured":"Hazra D, Byun Y-C. Synsiggan: generative adversarial networks for synthetic biomedical signal generation. Biology. 2020;9(12):441.","journal-title":"Biology"},{"key":"1232_CR18","doi-asserted-by":"crossref","unstructured":"Azocar AF, Mooney LM, Hargrove LJ, Rouse EJ. Design and characterization of an open-source robotic leg prosthesis. In: 2018 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Biorob), 2018; pp. 111\u2013118. IEEE","DOI":"10.1109\/BIOROB.2018.8488057"},{"key":"1232_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbiomech.2021.110320","volume":"119","author":"J Camargo","year":"2021","unstructured":"Camargo J, Ramanathan A, Flanagan W, Young A. A comprehensive, open-source dataset of lower limb biomechanics in multiple conditions of stairs, ramps, and level-ground ambulation and transitions. J Biomech. 2021;119.","journal-title":"J Biomech"},{"key":"1232_CR20","unstructured":"Brakel JPGV. Robust peak detection algorithm using z-scores. 2014. https:\/\/stackoverflow.com\/questions\/22583391\/peak-signal-detection-in-realtime-timeseries-data\/22640362#22640362. Accessed 2022-10-07."},{"key":"1232_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fnbot.2022.1064313","volume":"16","author":"M Kim","year":"2023","unstructured":"Kim M, Hargrove LJ. A gait phase prediction model trained on benchmark datasets for evaluating a controller for prosthetic legs. Front Neurorobot. 2023;16:1\u201313.","journal-title":"Front Neurorobot"},{"key":"1232_CR22","doi-asserted-by":"crossref","unstructured":"Isola P, Zhu J-Y, Zhou T, Efros AA. Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017; pp. 1125\u20131134","DOI":"10.1109\/CVPR.2017.632"},{"key":"1232_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JTEHM.2016.2601613","volume":"4","author":"H Lee","year":"2016","unstructured":"Lee H, Rouse EJ, Krebs HI. Summary of human ankle mechanical impedance during walking. IEEE J Transl Eng Health Med. 2016;4:1\u20137.","journal-title":"IEEE J Transl Eng Health Med"},{"issue":"1","key":"1232_CR24","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1109\/TNSRE.2017.2758325","volume":"26","author":"AL Shorter","year":"2017","unstructured":"Shorter AL, Rouse EJ. Mechanical impedance of the ankle during the terminal stance phase of walking. IEEE Trans Neural Syst Rehabil Eng. 2017;26(1):135\u201343.","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"issue":"4","key":"1232_CR25","doi-asserted-by":"publisher","first-page":"041005","DOI":"10.1115\/1.4051843","volume":"144","author":"YF Nazon","year":"2022","unstructured":"Nazon YF, Doshi RM, Rouse EJ. Validation of methods for estimation of knee joint mechanical impedance during locomotion using a torque-controllable knee exoskeleton. J Biomech Eng. 2022;144(4):041005.","journal-title":"J Biomech Eng"},{"key":"1232_CR26","unstructured":"Nazon Y, Rouse EJ. Estimation of knee impedance during exoskeleton assisted gait. In: Dynamic Walking. 2021. p. 1. https:\/\/static1.squarespace.com\/static\/6005cfec3753c24df2490e0a\/t\/609e9386ca745e0bc0d9e026\/1621005190668\/Yves+Nazon+-+Nazon_Yves_DW2021.pdf."},{"issue":"6","key":"1232_CR27","doi-asserted-by":"publisher","first-page":"99387","DOI":"10.1371\/journal.pone.0099387","volume":"9","author":"AM Simon","year":"2014","unstructured":"Simon AM, Ingraham KA, Fey NP, Finucane SB, Lipschutz RD, Young AJ, Hargrove LJ. Configuring a powered knee and ankle prosthesis for transfemoral amputees within five specific ambulation modes. PLoS ONE. 2014;9(6):99387.","journal-title":"PLoS ONE"},{"issue":"3","key":"1232_CR28","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1109\/TRO.2018.2794536","volume":"34","author":"D Quintero","year":"2018","unstructured":"Quintero D, Villarreal DJ, Lambert DJ, Kapp S, Gregg RD. Continuous-phase control of a powered knee-ankle prosthesis: amputee experiments across speeds and inclines. IEEE Trans Robot. 2018;34(3):686\u2013701.","journal-title":"IEEE Trans Robot"},{"issue":"2","key":"1232_CR29","doi-asserted-by":"publisher","first-page":"3467","DOI":"10.1109\/LRA.2022.3144790","volume":"7","author":"VS Shetty","year":"2022","unstructured":"Shetty VS, Lee UH, Ingraham KA, Rouse EJ. A data driven approach for predicting preferred ankle stiffness of a quasi-passive prosthesis. IEEE Robot Autom Lett. 2022;7(2):3467\u201374.","journal-title":"IEEE Robot Autom Lett"},{"issue":"5","key":"1232_CR30","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1080\/10749357.2019.1609182","volume":"26","author":"KA Hawkins","year":"2019","unstructured":"Hawkins KA, Balasubramanian CK, Vistamehr A, Conroy C, Rose DK, Clark DJ, Fox EJ. Assessment of backward walking unmasks mobility impairments in post-stroke community ambulators. Top Stroke Rehabil. 2019;26(5):382\u20138.","journal-title":"Top Stroke Rehabil"}],"container-title":["Journal of NeuroEngineering and Rehabilitation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12984-023-01232-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12984-023-01232-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12984-023-01232-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,18]],"date-time":"2023-11-18T17:26:00Z","timestamp":1700328360000},"score":1,"resource":{"primary":{"URL":"https:\/\/jneuroengrehab.biomedcentral.com\/articles\/10.1186\/s12984-023-01232-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,4]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["1232"],"URL":"https:\/\/doi.org\/10.1186\/s12984-023-01232-6","relation":{},"ISSN":["1743-0003"],"issn-type":[{"value":"1743-0003","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,4]]},"assertion":[{"value":"5 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 August 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 September 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was approved by the Northwestern University Institutional Review Board; all individuals provided written informed consent.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"115"}}