{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T22:17:19Z","timestamp":1768515439584,"version":"3.49.0"},"reference-count":45,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2023,3,24]],"date-time":"2023-03-24T00:00:00Z","timestamp":1679616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Research Foundation of Korea (NRF)","award":["2022R1A2C1013370"],"award-info":[{"award-number":["2022R1A2C1013370"]}]},{"name":"National Research Foundation of Korea (NRF)","award":["HF20C0113"],"award-info":[{"award-number":["HF20C0113"]}]},{"DOI":"10.13039\/501100003710","name":"Korea Health Industry Development Institute (KHIDI)","doi-asserted-by":"publisher","award":["2022R1A2C1013370"],"award-info":[{"award-number":["2022R1A2C1013370"]}],"id":[{"id":"10.13039\/501100003710","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003710","name":"Korea Health Industry Development Institute (KHIDI)","doi-asserted-by":"publisher","award":["HF20C0113"],"award-info":[{"award-number":["HF20C0113"]}],"id":[{"id":"10.13039\/501100003710","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Ground reaction force (GRF) is essential for estimating muscle strength and joint torque in inverse dynamic analysis. Typically, it is measured using a force plate. However, force plates have spatial limitations, and studies of gaits involve numerous steps and thus require a large number of force plates, which is disadvantageous. To overcome these challenges, we developed a deep learning model for estimating three-axis GRF utilizing shoes with three uniaxial load cells. GRF data were collected from 81 people as they walked on two force plates while wearing shoes with three load cells. The three-axis GRF was calculated using a seq2seq approach based on long short-term memory (LSTM). To conduct the learning, validation, and testing, random selection was performed based on the subjects. The 60 selected participants were divided as follows: 37 were in the training set, 12 were in the validation set, and 11 were in the test set. The estimated GRF matched the force plate-measured GRF with correlation coefficients of 0.97, 0.96, and 0.90 and root mean square errors of 65.12 N, 15.50 N, and 9.83 N for the vertical, anterior\u2013posterior, and medial\u2013lateral directions, respectively, and there was a mid-stance timing error of 5.61% in the test dataset. A Bland\u2013Altman analysis showed good agreement for the maximum vertical GRF. The proposed shoe with three uniaxial load cells and seq2seq LSTM can be utilized for estimating the 3D GRF in an outdoor environment with level ground and\/or for gait research in which the subject takes several steps at their preferred walking speed, and hence can supply crucial data for a basic inverse dynamic analysis.<\/jats:p>","DOI":"10.3390\/s23073428","type":"journal-article","created":{"date-parts":[[2023,3,24]],"date-time":"2023-03-24T08:43:03Z","timestamp":1679647383000},"page":"3428","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["A Deep Learning Model for 3D Ground Reaction Force Estimation Using Shoes with Three Uniaxial Load Cells"],"prefix":"10.3390","volume":"23","author":[{"given":"Junggil","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, Konkuk University, Chungju 27478, Republic of Korea"}]},{"given":"Hyeon","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Konkuk University, Chungju 27478, Republic of Korea"}]},{"given":"Seulgi","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Konkuk University, Chungju 27478, Republic of Korea"}]},{"given":"Jinseung","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Konkuk University, Chungju 27478, Republic of Korea"},{"name":"BK21 Plus Research Institute of Biomedical Engineering, Konkuk University, Chungju 27478, Republic of Korea"}]},{"given":"Gyerae","family":"Tack","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Konkuk University, Chungju 27478, Republic of Korea"},{"name":"BK21 Plus Research Institute of Biomedical Engineering, Konkuk University, Chungju 27478, Republic of Korea"}]}],"member":"1968","published-online":{"date-parts":[[2023,3,24]]},"reference":[{"key":"ref_1","first-page":"560","article-title":"Gait Analysis: Clinical Facts","volume":"52","author":"Baker","year":"2016","journal-title":"Eur. J. Phys. Rehabil. Med."},{"key":"ref_2","unstructured":"Winter, D.A. (1991). Biomechanics and Motor Control of Human Gait, Normal, Elderly and Pathological, University of Waterloo Press."},{"key":"ref_3","unstructured":"(2022, December 13). CIR System Inc. Available online: https:\/\/www.gaitrite.com\/."},{"key":"ref_4","unstructured":"(2023, February 08). XSENSOR Inc. Available online: https:\/\/www.xsensor.com\/solutions-and-platform\/human-performance\/walkways-stance-pads\/."},{"key":"ref_5","unstructured":"(2022, December 08). Tekscan Inc. Available online: https:\/\/www.tekscan.com."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/S0966-6362(02)00053-X","article-title":"Concurrent Related Validity of the GAITRite\u00ae Walkway System for Quantification of the Spatial and Temporal Parameters of Gait","volume":"17","author":"Bilney","year":"2003","journal-title":"Gait Posture"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"973","DOI":"10.2522\/ptj.2008.88.8.973","article-title":"Physical Rehabilitation: Evidence-Based Examination, Evaluation, and Intervention","volume":"88","author":"Vaillancourt","year":"2008","journal-title":"Phys. Ther."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Honert, E.C., Hoitz, F., Blades, S., Nigg, S.R., and Nigg, B.M. (2022). Estimating Running Ground Reaction Forces from Plantar Pressure during Graded Running. Sensors, 22.","DOI":"10.3390\/s22093338"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"3496","DOI":"10.1038\/s41598-019-39695-0","article-title":"Relationship between Daily and in-Laboratory Gait Speed among Healthy Community-Dwelling Older Adults","volume":"9","author":"Takayanagi","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1390","DOI":"10.1016\/j.apmr.2010.06.015","article-title":"Differences in Preferred Walking Speeds in a Gait Laboratory Compared with the Real World after Total Hip Replacement","volume":"91","author":"Foucher","year":"2010","journal-title":"Arch. Phys. Med. Rehabil."},{"key":"ref_11","unstructured":"(2023, January 11). Pedar\u00ae: Dynamic Pressure Distribution inside the Footwear. Available online: https:\/\/www.novel.de\/products\/pedar\/."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1016\/S0268-0033(99)00036-4","article-title":"Assessment of the Horizontal, Fore-Aft Component of the Ground Reaction Force from Insole Pressure Patterns by using Artificial Neural Networks","volume":"14","author":"Savelberg","year":"1999","journal-title":"Clin. Biomech."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1109\/TBME.2020.3006158","article-title":"Multidimensional Ground Reaction Forces and Moments from Wearable Sensor Accelerations via Deep Learning","volume":"68","author":"Johnson","year":"2020","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Choi, H.S., Lee, C.H., Shim, M., Han, J.I., and Baek, Y.S. (2018). Design of an Artificial Neural Network Algorithm for a Low-Cost Insole Sensor to Estimate the Ground Reaction Force (GRF) and Calibrate the Center of Pressure (CoP). Sensors, 18.","DOI":"10.3390\/s18124349"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1461","DOI":"10.1109\/TBME.2021.3120346","article-title":"Estimating Ground Reaction Force and Center of Pressure using Low-Cost Wearable Devices","volume":"69","author":"Oubre","year":"2021","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_16","first-page":"186","article-title":"Validation of F-Scan Pressure Sensor System: A Technical Note","volume":"35","author":"Luo","year":"1998","journal-title":"J. Rehabil. Res. Dev."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Rana, N.K. (2009, January 28\u201330). Application of Force Sensing Resistor (FSR) in Design of Pressure Scanning System for Plantar Pressure Measurement. Proceedings of the 2009 Second International Conference on Computer and Electrical Engineering, Dubai, United Arab Emirates.","DOI":"10.1109\/ICCEE.2009.234"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.3390\/s140101073","article-title":"A Wireless Flexible Sensorized Insole for Gait Analysis","volume":"14","author":"Crea","year":"2014","journal-title":"Sensors"},{"key":"ref_19","first-page":"25701","article-title":"A Wearable Sensor System for Lower-Limb Rehabilitation Evaluation using the GRF and CoP Distributions","volume":"27","author":"Tao","year":"2015","journal-title":"MST"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"836","DOI":"10.3390\/s23020836","article-title":"An Innovative Compact System to Measure Skiing Ground Reaction Forces and Flexural Angles of Alpine and Touring Ski Boots","volume":"23","author":"Giuseppe","year":"2023","journal-title":"Sensors"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/j.neucom.2014.02.054","article-title":"Feed Forward Artificial Neural Network to Predict Contact Force at Medial Knee Joint: Application to Gait Modification","volume":"139","author":"Ardestani","year":"2014","journal-title":"Neurocomputing"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/j.gaitpost.2019.07.190","article-title":"A Robust Machine Learning Enabled Decomposition of Shear Ground Reaction Forces during the Double Contact Phase of Walking","volume":"73","author":"Bastien","year":"2019","journal-title":"Gait Posture"},{"key":"ref_23","first-page":"3104","article-title":"Sequence to Sequence Learning with Neural Networks","volume":"27","author":"Sutskever","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_24","unstructured":"(2022, January 03). Seq2Seq Model in Machine Learning. Available online: https:\/\/www.geeksforgeeks.org\/seq2seq-model-in-machine-learning\/."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning Representations by Back-Propagating Errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding Structure in Time","volume":"14","author":"Elman","year":"1990","journal-title":"Cogn. Sci."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Noh, S. (2021). Analysis of Gradient Vanishing of RNNs and Performance Comparison. Information, 12.","DOI":"10.3390\/info12110442"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Manaswi, N.K. (2018). Deep Learning with Applications Using Python, Springer.","DOI":"10.1007\/978-1-4842-3516-4"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"132306","DOI":"10.1016\/j.physd.2019.132306","article-title":"Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network","volume":"404","author":"Sherstinsky","year":"2020","journal-title":"Phys. D"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/S0140-6736(86)90837-8","article-title":"Statistical Methods for Assessing Agreement between Two Methods of Clinical Measurement","volume":"327","author":"Bland","year":"1986","journal-title":"Lancet"},{"key":"ref_31","unstructured":"(2022, December 01). i2A Systems Corp. Available online: https:\/\/i2asys.com\/."},{"key":"ref_32","unstructured":"Morton, D.J. (1935). The Human Foot: Its Evolution, Physiology and Functional Disorders, Columbia University Press."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/0141-5425(85)90040-8","article-title":"Foot Pressure Patterns during Gait","volume":"7","author":"Soames","year":"1985","journal-title":"J. Biomed. Eng."},{"key":"ref_34","unstructured":"(2023, January 03). National Instruments Corp. Available online: https:\/\/ni.nubicom.co.kr\/img\/pdf\/376047d.pdf."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1016\/S1050-6411(99)00014-0","article-title":"Dynamic Muscle Force Predictions from EMG: An Artificial Neural Network Approach","volume":"9","author":"Liu","year":"1999","journal-title":"J. Electromyogr. Kinesiol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"2597","DOI":"10.1016\/j.jbiomech.2008.05.007","article-title":"Estimating the Complete Ground Reaction Forces with Pressure Insoles in Walking","volume":"41","author":"Fong","year":"2008","journal-title":"J. Biomech."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.jbiomech.2018.12.015","article-title":"Prediction of Ground Reaction Forces in Level and Incline\/Decline Walking from a Multistage Analysis of Plantar Pressure Data","volume":"84","author":"Wei","year":"2019","journal-title":"J. Biomech."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Aqueveque, P., Germany, E., Osorio, R., and Pastene, F. (2020). Gait Segmentation Method using a Plantar Pressure Measurement System with Custom-made Capacitive Sensors. Sensors, 20.","DOI":"10.3390\/s20030656"},{"key":"ref_39","unstructured":"Heinemann, B. (2014). Gait Analysis: An Introduction, University of Oxford."},{"key":"ref_40","first-page":"56","article-title":"Implementation of Gait Pattern Monitoring System using FSR (Force Sensitive Resistor) Sensor","volume":"20","author":"Kim","year":"2021","journal-title":"J. Semicond. Disp. Technol."},{"key":"ref_41","unstructured":"Perry, J. (2010). Gait Analysis. Normal and Pathological Function, Slack."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Koltermann, J.J., Gerber, M., Beck, H., and Beck, M. (2017). Validation of the HUMAC Balance System in Comparison with Conventional Force Plates. Technologies, 5.","DOI":"10.3390\/technologies5030044"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1050","DOI":"10.1053\/apmr.2001.24893","article-title":"Gait Variability and Fall Risk in Community-Living Older Adults: A 1-Year Prospective Study","volume":"82","author":"Hausdorff","year":"2001","journal-title":"Arch. Phys. Med. Rehabil."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1016\/j.jamda.2015.12.092","article-title":"Poor Gait Performance and Prediction of Dementia: Results from a Meta-Analysis","volume":"17","author":"Olivier","year":"2016","journal-title":"J. Am. Med. Dir. Assoc."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/0966-6362(96)01063-6","article-title":"Hemiparetic Gait Following Stroke. Part I: Characteristics","volume":"4","author":"Olney","year":"1996","journal-title":"Gait Posture"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/7\/3428\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:02:25Z","timestamp":1760122945000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/7\/3428"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,24]]},"references-count":45,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2023,4]]}},"alternative-id":["s23073428"],"URL":"https:\/\/doi.org\/10.3390\/s23073428","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,24]]}}}