{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:04:59Z","timestamp":1783105499841,"version":"3.54.6"},"reference-count":41,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2022,4,13]],"date-time":"2022-04-13T00:00:00Z","timestamp":1649808000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"European Union Interreg 2 Seas Program 2014\u20132020 of the European Regional Development Fund (M.O.T.I.O.N Project)","award":["2S05-038"],"award-info":[{"award-number":["2S05-038"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Forecasted gait trajectories of children could be used as feedforward input to control lower limb robotic devices, such as exoskeletons and actuated orthotic devices (e.g., Powered Ankle Foot Orthosis\u2014PAFO). Several studies have forecasted healthy gait trajectories, but, to the best of our knowledge, none have forecasted gait trajectories of children with pathological gait yet. These exhibit higher inter- and intra-subject variability compared to typically developing gait of healthy subjects. Pathological trajectories represent the typical gait patterns that rehabilitative exoskeletons and actuated orthoses would target. In this study, we implemented two deep learning models, a Long-Term Short Memory (LSTM) and a Convolutional Neural Network (CNN), to forecast hip, knee, and ankle trajectories in terms of corresponding Euler angles in the pitch, roll, and yaw form for children with neurological disorders, up to 200 ms in the future. The deep learning models implemented in our study are trained on data (available online) from children with neurological disorders collected by Gillette Children\u2019s Speciality Healthcare over the years 1994\u20132017. The children\u2019s ages range from 4 to 19 years old and the majority of them had cerebral palsy (73%), while the rest were a combination of neurological, developmental, orthopaedic, and genetic disorders (27%). Data were recorded with a motion capture system (VICON) with a sampling frequency of 120 Hz while walking for 15 m. We investigated a total of 35 combinations of input and output time-frames, with window sizes for input vectors ranging from 50\u20131000 ms, and output vectors from 8.33\u2013200 ms. Results show that LSTMs outperform CNNs, and the gap in performance becomes greater the larger the input and output window sizes are. The maximum difference between the Mean Absolute Errors (MAEs) of the CNN and LSTM networks was 0.91 degrees. Results also show that the input size has no significant influence on mean prediction errors when the output window is 50 ms or smaller. For output window sizes greater than 50 ms, the larger the input window, the lower the error. Overall, we obtained MAEs ranging from 0.095\u20132.531 degrees for the LSTM network, and from 0.129\u20132.840 degrees for the CNN. This study establishes the feasibility of forecasting pathological gait trajectories of children which could be integrated with exoskeleton control systems and experimentally explores the characteristics of such intelligent systems under varying input and output window time-frames.<\/jats:p>","DOI":"10.3390\/s22082969","type":"journal-article","created":{"date-parts":[[2022,4,13]],"date-time":"2022-04-13T23:07:16Z","timestamp":1649891236000},"page":"2969","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Performance of Deep Learning Models in Forecasting Gait Trajectories of Children with Neurological Disorders"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8008-6032","authenticated-orcid":false,"given":"Rania","family":"Kolaghassi","sequence":"first","affiliation":[{"name":"School of Engineering, University of Kent, Canterbury CT2 7NT, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3246-8479","authenticated-orcid":false,"given":"Mohamad Kenan","family":"Al-Hares","sequence":"additional","affiliation":[{"name":"School of Engineering, University of Kent, Canterbury CT2 7NT, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7475-7327","authenticated-orcid":false,"given":"Gianluca","family":"Marcelli","sequence":"additional","affiliation":[{"name":"School of Engineering, University of Kent, Canterbury CT2 7NT, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0847-8880","authenticated-orcid":false,"given":"Konstantinos","family":"Sirlantzis","sequence":"additional","affiliation":[{"name":"School of Engineering, University of Kent, Canterbury CT2 7NT, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,4,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Webster, J.B., and Murphy, D.P. (2019). Introduction. Atlas of Orthoses and Assistive Devices, Elsevier. [5th ed.].","DOI":"10.1016\/B978-0-323-48323-0.00074-3"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Makinson, B.J. (1971). Research and Development Prototype for Machine Augmentation of Human Strength and Endurance Hardiman I Project, General Electric.","DOI":"10.21236\/AD0724797"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Kumar, V., Hote, Y.V., and Jain, S. (2019, January 10\u201311). Review of Exoskeleton: History, Design and Control. Proceedings of the 2019 3rd International Conference on Recent Developments in Control, Automation Power Engineering (RDCAPE), Noida, India.","DOI":"10.1109\/RDCAPE47089.2019.8979099"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1016\/j.apergo.2015.12.003","article-title":"The effects of a passive exoskeleton on muscle activity, discomfort and endurance time in forward bending work","volume":"54","author":"Bosch","year":"2016","journal-title":"Appl. Ergon."},{"key":"ref_5","unstructured":"Bai, S., Virk, G.S., and Sugar, T.G. (2018). Wearable Exoskeleton Systems: Design, Control and Applications, Institution of Engineering and Technology. Control, Robotics & Sensors."},{"key":"ref_6","first-page":"26","article-title":"Recent developments and challenges of lower extremity exoskeletons","volume":"5","author":"Chen","year":"2016","journal-title":"J. Orthop. Transl."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1109\/TNSRE.2005.848628","article-title":"Patient-cooperative strategies for robot-aided treadmill training: First experimental results","volume":"13","author":"Riener","year":"2005","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"H\u00f8yer, E., Opheim, A., and J\u00f8rgensen, V. (2020). Implementing the exoskeleton Ekso GTTM for gait rehabilitation in a stroke unit\u2014Feasibility, functional benefits and patient experiences. Disabil. Rehabil. Assist. Technol., 1\u20137.","DOI":"10.1080\/17483107.2020.1800110"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Winfree, K.N., Stegall, P., and Agrawal, S.K. (July, January 29). Design of a minimally constraining, passively supported gait training exoskeleton: ALEX II. Proceedings of the 2011 IEEE International Conference on Rehabilitation Robotics, Zurich, Switzerland.","DOI":"10.1109\/ICORR.2011.5975499"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"112","DOI":"10.5312\/wjo.v9.i9.112","article-title":"Robotic exoskeletons: The current pros and cons","volume":"9","author":"Gorgey","year":"2018","journal-title":"World J. Orthop."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"041003","DOI":"10.1115\/1.4007181","article-title":"A Method for the Autonomous Control of Lower Limb Exoskeletons for Persons with Paraplegia","volume":"6","author":"Quintero","year":"2012","journal-title":"J. Med. Devices Trans. ASME"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1109\/TMECH.2006.871087","article-title":"Biomechanical design of the Berkeley lower extremity exoskeleton (BLEEX)","volume":"11","author":"Zoss","year":"2006","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Kaneko, M., and Nakamura, Y. (2011). HAL: Hybrid Assistive Limb Based on Cybernics. Robotics Research, Springer.","DOI":"10.1007\/978-3-642-14743-2"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1186\/s12984-021-00906-3","article-title":"Review of control strategies for lower-limb exoskeletons to assist gait","volume":"18","author":"Baud","year":"2021","journal-title":"J. NeuroEng. Rehabil."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Al-Shuka, H.F.N., Song, R., and Ding, C. (2018, January 29\u201331). On high-level control of power-augmentation lower extremity exoskeletons: Human walking intention. Proceedings of the 2018 Tenth International Conference on Advanced Computational Intelligence (ICACI), Xiamen, China.","DOI":"10.1109\/ICACI.2018.8377601"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"113788","DOI":"10.1109\/ACCESS.2021.3104464","article-title":"Systematic Review of Intelligent Algorithms in Gait Analysis and Prediction for Lower Limb Robotic Systems","volume":"9","author":"Kolaghassi","year":"2021","journal-title":"IEEE Access"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"29973","DOI":"10.1109\/ACCESS.2019.2900591","article-title":"Intelligent Prediction of Human Lower Extremity Joint Moment: An Artificial Neural Network Approach","volume":"7","author":"Xiong","year":"2019","journal-title":"IEEE Access"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Song, J., Zhu, A., Tu, Y., Wang, Y., Arif, M.A., Shen, H., Shen, Z., Zhang, X., and Cao, G. (2020). Human Body Mixed Motion Pattern Recognition Method Based on Multi-Source Feature Parameter Fusion. Sensors, 20.","DOI":"10.3390\/s20020537"},{"key":"ref_19","doi-asserted-by":"crossref","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","author":"Laschowski","year":"2022","journal-title":"Front. Neurorobot."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Al-Shuka, H.F.N., and Song, R. (2018, January 29\u201331). On low-level control strategies of lower extremity exoskeletons with power augmentation. Proceedings of the 2018 Tenth International Conference on Advanced Computational Intelligence (ICACI), Xiamen, China.","DOI":"10.1109\/ICACI.2018.8377581"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1186\/s12984-019-0526-8","article-title":"Model-based control for exoskeletons with series elastic actuators evaluated on sit-to-stand movements","volume":"16","author":"Vantilt","year":"2019","journal-title":"J. NeuroEng. Rehabil."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1109\/TNSRE.2008.2008278","article-title":"Reference trajectory generation for rehabilitation robots: Complementary limb motion estimation","volume":"17","author":"Vallery","year":"2009","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1109\/TNSRE.2019.2950309","article-title":"Gait Trajectory and Event Prediction from State Estimation for Exoskeletons During Gait","volume":"28","author":"Tanghe","year":"2020","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Liu, D.X., Wu, X., Wang, C., and Chen, C. (2017, January 27\u201331). Gait trajectory prediction for lower-limb exoskeleton based on Deep Spatial-Temporal Model (DSTM). Proceedings of the 2017 2nd International Conference on Advanced Robotics and Mechatronics (ICARM), Hefei and Tai\u2019an, China.","DOI":"10.1109\/ICARM.2017.8273224"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"362","DOI":"10.3389\/fbioe.2020.00362","article-title":"Lower Limb Kinematics Trajectory Prediction Using Long Short-Term Memory Neural Networks","volume":"8","author":"Zaroug","year":"2020","journal-title":"Front. Bioeng. Biotechnol."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Su, B., and Gutierrez-Farewik, E.M. (2020). Gait Trajectory and Gait Phase Prediction Based on an LSTM Network. Sensors, 20.","DOI":"10.3390\/s20247127"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/j.gaitpost.2020.10.026","article-title":"Lower body kinematics estimation from wearable sensors for walking and running: A deep learning approach","volume":"83","author":"Hernandez","year":"2021","journal-title":"Gait Posture"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Jia, L., Ai, Q., Meng, W., Liu, Q., and Xie, S.Q. (2021, January 12\u201316). Individualized Gait Trajectory Prediction Based on Fusion LSTM Networks for Robotic Rehabilitation Training. Proceedings of the 2021 IEEE\/ASME International Conference on Advanced Intelligent Mechatronics (AIM), Delft, The Netherlands.","DOI":"10.1109\/AIM46487.2021.9517616"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zaroug, A., Garofolini, A., Lai, D.T.H., Mudie, K., and Begg, R. (2021). Prediction of gait trajectories based on the Long Short Term Memory neural networks. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0255597"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhu, C., Liu, Q., Meng, W., Ai, Q., and Xie, S.Q. (2021, January 12\u201316). An Attention-Based CNN-LSTM Model with Limb Synergy for Joint Angles Prediction. Proceedings of the 2021 IEEE\/ASME International Conference on Advanced Intelligent Mechatronics (AIM), Delft, The Netherlands.","DOI":"10.1109\/AIM46487.2021.9517544"},{"key":"ref_31","unstructured":"Kirtley, C. (2006). Clinical Gait Analysis: Theory and Practice, Churchill Livingstone Elsevier."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1016\/S0268-0033(99)00057-1","article-title":"Intrasubject repeatability of gait analysis data in normal and spastic children","volume":"15","author":"Steinwender","year":"2000","journal-title":"Clin. Biomech."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.humov.2016.03.010","article-title":"Gait variability in people with neurological disorders: A systematic review and meta-analysis","volume":"47","author":"Moon","year":"2016","journal-title":"Hum. Mov. Sci."},{"key":"ref_34","unstructured":"(2021, October 01). Automatic Real-Time Gait Event Detection in Children Using Deep Neural Networks. Available online: https:\/\/simtk.org\/frs\/?group_id=1946."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Kidzinski, L., Delp, S., and Schwartz, M. (2019). Automatic real-time gait event detection in children using deep neural networks. PLoS ONE, 14.","DOI":"10.1371\/journal.pone.0211466"},{"key":"ref_36","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press. Available online: http:\/\/www.deeplearningbook.org."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019, January 4\u20138). Optuna: A Next-generation Hyperparameter Optimization Framework. Proceedings of the 25rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Anchorage, AK, USA.","DOI":"10.1145\/3292500.3330701"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Gieysztor, E., Kowal, M., and Paprocka-Borowicz, M. (2021). Gait Parameters in Healthy Preschool and School Children Assessed Using Wireless Inertial Sensor. Sensors, 21.","DOI":"10.3390\/s21196423"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"107398","DOI":"10.1016\/j.ymssp.2020.107398","article-title":"1D convolutional neural networks and applications: A survey","volume":"151","author":"Kiranyaz","year":"2021","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Moreira, L., Figueiredo, J., Vilas-Boas, J.P., and Santos, C.P. (2021). Kinematics, Speed, and Anthropometry-Based Ankle Joint Torque Estimation: A Deep Learning Regression Approach. Machines, 9.","DOI":"10.3390\/machines9080154"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1109\/TMRB.2022.3144025","article-title":"Subject-Independent, Biological Hip Moment Estimation During Multimodal Overground Ambulation Using Deep Learning","volume":"4","author":"Molinaro","year":"2022","journal-title":"IEEE Trans. Med Robot. Bionics"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/8\/2969\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:52:57Z","timestamp":1760136777000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/8\/2969"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,13]]},"references-count":41,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2022,4]]}},"alternative-id":["s22082969"],"URL":"https:\/\/doi.org\/10.3390\/s22082969","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,13]]}}}