{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T01:28:58Z","timestamp":1788571738593,"version":"build-2803163510"},"reference-count":44,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T00:00:00Z","timestamp":1663113600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"veski\u2014Study Melbourne Research Partnerships (SMRP) program","award":["veski-SMRP #2003"],"award-info":[{"award-number":["veski-SMRP #2003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Efficient, adaptive, locomotor function is critically important for maintaining our health and independence, but falls-related injuries when walking are a significant risk factor, particularly for more vulnerable populations such as older people and post-stroke individuals. Tripping is the leading cause of falls, and the swing-phase event Minimum Foot Clearance (MFC) is recognised as the key biomechanical determinant of tripping probability. MFC is defined as the minimum swing foot clearance, which is seen approximately mid-swing, and it is routinely measured in gait biomechanics laboratories using precise, high-speed, camera-based 3D motion capture systems. For practical intervention strategies designed to predict, and possibly assist, swing foot trajectory to prevent tripping, identification of the MFC event is essential; however, no technique is currently available to determine MFC timing in real-life settings outside the laboratory. One strategy has been to use wearable sensors, such as Inertial Measurement Units (IMUs), but these data are limited to primarily providing only tri-axial linear acceleration and angular velocity. The aim of this study was to develop Machine Learning (ML) algorithms to predict MFC timing based on the preceding toe-off gait event. The ML algorithms were trained using 13 young adults\u2019 foot trajectory data recorded from an Optotrak 3D motion capture system. A Deep Learning configuration was developed based on a Recurrent Neural Network with a Long Short-Term Memory (LSTM) architecture and Huber loss-functions to minimise MFC-timing prediction error. We succeeded in predicting MFC timing from toe-off characteristics with a mean absolute error of 0.07 s. Although further algorithm training using population-specific inputs are needed. The ML algorithms designed here can be used for real-time actuation of wearable active devices to increase foot clearance at critical MFC and reduce devastating tripping falls. Further developments in ML-guided actuation for active exoskeletons could prove highly effective in developing technologies to reduce tripping-related falls across a range of gait impaired populations.<\/jats:p>","DOI":"10.3390\/s22186960","type":"journal-article","created":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T23:16:36Z","timestamp":1663197396000},"page":"6960","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Using Deep Learning to Predict Minimum Foot\u2013Ground Clearance Event from Toe-Off Kinematics"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8454-9356","authenticated-orcid":false,"given":"Clement Ogugua","family":"Asogwa","sequence":"first","affiliation":[{"name":"Institute for Health and Sport (IHES), Victoria University, Melbourne, VIC 8001, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanatsu","family":"Nagano","sequence":"additional","affiliation":[{"name":"Institute for Health and Sport (IHES), Victoria University, Melbourne, VIC 8001, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Tsukuba, Tsukuba 305-8577, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3195-8591","authenticated-orcid":false,"given":"Rezaul","family":"Begg","sequence":"additional","affiliation":[{"name":"Institute for Health and Sport (IHES), Victoria University, Melbourne, VIC 8001, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,9,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1136\/ip.2005.011015","article-title":"The costs of fatal and non-fatal falls among older adults","volume":"12","author":"Stevens","year":"2006","journal-title":"Inj. Prev."},{"key":"ref_2","first-page":"771","article-title":"Falls in the elderly: Spectrum and prevention","volume":"57","year":"2011","journal-title":"Can. Fam. Physician"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Pelicioni, P.H.S., Menant, J.C., Latt, M.D., and Lord, S.R. (2019). Falls in Parkinson\u2019s disease subtypes: Risk factors, locations and circum-stances. Int. J. Environ. Res. Public Health, 16.","DOI":"10.3390\/ijerph16122216"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1191\/0269215505cr796oa","article-title":"Falls and injury prevention should be part of every stroke rehabili-tation plan","volume":"19","author":"Mackintosh","year":"2005","journal-title":"Clin. Rehabil."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1093\/ageing\/26.4.261","article-title":"Circumstances and consequences of falls in independent community-dwelling older adults","volume":"26","author":"Berg","year":"1997","journal-title":"Age Ageing"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1093\/ageing\/17.6.365","article-title":"Falls by elderly people at home: Prevalence and associated factors","volume":"17","author":"Blake","year":"1988","journal-title":"Age Ageing"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"962","DOI":"10.1016\/j.clinbiomech.2011.05.013","article-title":"Ageing and limb dominance effects on foot-ground clearance during treadmill and overground walking","volume":"26","author":"Nagano","year":"2011","journal-title":"Clin. Biomech."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/j.gaitpost.2006.03.008","article-title":"Minimum foot clearance during walking: Strategies for the minimization of trip-related falls","volume":"25","author":"Begg","year":"2007","journal-title":"Gait Posture"},{"key":"ref_9","unstructured":"Winter, D.A. (2005). Chapter 9: Kinesiological Electromyography. Biomechanics and Motor Control of Human Movement, John Wiley & Sons, Inc.. [3rd ed.]."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1922","DOI":"10.1038\/s41598-017-02189-y","article-title":"Minimum toe clearance: Probing the neural control of locomotion","volume":"7","author":"Killeen","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Nagano, H., and Begg, R.K. (2018). Shoe-Insole Technology for Injury Prevention in Walking. Sensors, 18.","DOI":"10.3390\/s18051468"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1271","DOI":"10.1080\/00140139.2021.1918351","article-title":"A shoe-insole to improve ankle joint mechanics for injury prevention among older adults","volume":"64","author":"Nagano","year":"2021","journal-title":"Ergonomics"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Sarashina, E., Mizukami, K., Yoshizawa, Y., Sakurai, J., Tsuji, A., and Begg, R. (2022). Feasibility of Pilates for Late-Stage Frail Older Adults to Minimize Falls and Enhance Cognitive Functions. Appl. Sci., 12.","DOI":"10.3390\/app12136716"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"243","DOI":"10.3389\/fnhum.2014.00243","article-title":"Gait training with real-time aug-mented toe-ground clearance information decreases tripping risk in older adults and a person with chronic stroke","volume":"8","author":"Begg","year":"2014","journal-title":"Front. Hum. Neurosci."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Nagano, H., Said, C.M., James, L., and Begg, R.K. (2020). Feasibility of Using Foot\u2013Ground Clearance Biofeedback Training in Treadmill Walking for Post-Stroke Gait Rehabilitation. Brain Sci., 10.","DOI":"10.3390\/brainsci10120978"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Delfi, G., Kamachi, M., and Dutta, T. (2021). Development of an automated minimum foot clearance measurement system: Proof of prin-ciple. Sensors, 21.","DOI":"10.3390\/s21030976"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Delfi, G., Al Bochi, A., and Dutta, T. (2021). A Scoping Review on Minimum Foot Clearance Measurement: Sensing Modalities. Int. J. Environ. Res. Public Health, 18.","DOI":"10.3390\/ijerph182010848"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Benoussaad, M., Sijobert, B., Mombaur, K., and Coste, C.A. (2016). Robust Foot Clearance Estimation Based on the Integration of Foot-Mounted IMU Acceleration Data. Sensors, 16.","DOI":"10.3390\/s16010012"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"4309","DOI":"10.1016\/j.jbiomech.2015.10.040","article-title":"A machine learning approach to estimate Minimum Toe Clearance using Inertial Measurement Units","volume":"48","author":"Santhiranayagam","year":"2015","journal-title":"J. Biomech."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Wang, W., and Admczyk, P.G. (2019). Analyzing gait in the real world using wearable movement sensors and frequently repeated movement paths. Sensors, 19.","DOI":"10.3390\/s19081925"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1016\/j.gaitpost.2005.12.004","article-title":"Methodology for determining the sensitivity of swing leg toe clearance and leg length to swing leg joint angles during gait","volume":"24","author":"Moosabhoy","year":"2006","journal-title":"Gait Posture"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1123\/jab.29.2.188","article-title":"A Comparison of Treadmill and Overground Walking Effects on Step Cycle Asymmetry in Young and Older Individuals","volume":"29","author":"Nagano","year":"2013","journal-title":"J. Appl. Biomech."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1186\/1743-0003-11-155","article-title":"Effects of walking-induced fatigue on gait function and tripping risks in older adults","volume":"11","author":"Nagano","year":"2014","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_24","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_25","first-page":"931","article-title":"Implementation of machine learning algorithms for gait recognition","volume":"23","author":"Kececi","year":"2020","journal-title":"Eng. Sci. Technol. Int. J."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Lee, S.-S., and Choi, S.T. (2019). Classification of Gait Type Based on Deep Learning Using Various Sensors with Smart Insole. Sensors, 19.","DOI":"10.3390\/s19081757"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1016\/j.knee.2015.06.016","article-title":"Modelling knee flexion effects on joint power absorption and adduction moment","volume":"22","author":"Nagano","year":"2015","journal-title":"Knee"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Jafarnezhadgero, A., Fatollahi, A., Amirzadeh, N., Siahkouhian, M., and Granacher, U. (2019). Ground reaction forces and muscle activity while walking on sand versus stable ground in individuals with pronated feet compared with healthy controls. PLoS ONE, 14.","DOI":"10.1371\/journal.pone.0223219"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"3067","DOI":"10.1016\/j.jbiomech.2010.07.009","article-title":"Determination of toe-off event time during treadmill locomotion using kinematic data","volume":"43","year":"2010","journal-title":"J. Biomech."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Sarshar, M., Polturi, S., and Schega, L. (2021). Gait Phase Estimation by Using LSTM in IMU-Based Gait Analysis\u2014Proof of Concept. Sensors, 21.","DOI":"10.3390\/s21175749"},{"key":"ref_31","unstructured":"Welcome to Python.org (2022, April 03). Python.org. Available online: https:\/\/www.python.org\/."},{"key":"ref_32","unstructured":"(2022, June 28). Scipy. Available online: https:\/\/scipy.org\/."},{"key":"ref_33","unstructured":"(2022, June 28). Pandas. Available online: https:\/\/pandas.pydata.org\/."},{"key":"ref_34","unstructured":"(2018, December 26). Keras Documentation. Available online: https:\/\/keras.io."},{"key":"ref_35","unstructured":"(2018, March 10). TensorFlow. Available online: https:\/\/www.tensorflow.org\/."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"4502719","DOI":"10.1155\/2019\/4502719","article-title":"Prediction Algorithm of Parameters of Toe Clearance in the Swing Phase","volume":"2019","author":"Miyake","year":"2019","journal-title":"Appl. Bionics Biomech."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"260","DOI":"10.19101\/IJACR.PID77","article-title":"Determining the impact of window length on time series forecasting using deep learning","volume":"9","author":"Azlan","year":"2019","journal-title":"Int. J. Adv. Comput. Res."},{"key":"ref_38","unstructured":"Gokcesu, K., and Gokcesu, H. (2021). Generalized huber loss for robust learning and its efficient minimiza-tion for a robust statistics. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Meyer, G.P. (2021, January 20\u201325). An alternative probabilistic interpretation of the huber loss. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00522"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1016\/S0021-9290(00)00200-1","article-title":"Disturbance type and gait speed affect fall direction and impact location","volume":"34","author":"Smeesters","year":"2001","journal-title":"J. Biomech."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Kubota, S., Kadone, H., Shimizu, Y., Koda, M., Noguchi, H., Takahashi, H., Watanabe, H., Hada, Y., Sankai, Y., and Yamazaki, M. (2022). Development of a New Ankle Joint Hybrid Assistive Limb. Medicina, 58.","DOI":"10.3390\/medicina58030395"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1007\/s41315-019-00088-1","article-title":"A survey on foot drop and functional electrical stimulation","volume":"3","author":"York","year":"2019","journal-title":"Int. J. Intell. Robot. Appl."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1682\/JRRD.2004.05.0059","article-title":"Electromyographic and kinematic nondisabled gait dif-ferences at extremely slow overground and treadmill walking speeds","volume":"42","author":"Nymark","year":"2005","journal-title":"J. Rehabil. Res. Dev."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"299","DOI":"10.3233\/NRE-141126","article-title":"EMG of the tibialis anterior demonstrates a training effect after utilization of a foot drop stimulator","volume":"35","author":"Pilkar","year":"2014","journal-title":"NeuroRehabilitation"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/18\/6960\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:31:26Z","timestamp":1760142686000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/18\/6960"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,14]]},"references-count":44,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2022,9]]}},"alternative-id":["s22186960"],"URL":"https:\/\/doi.org\/10.3390\/s22186960","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,14]]}}}