{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T15:30:46Z","timestamp":1771515046793,"version":"3.50.1"},"reference-count":58,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2021,11,12]],"date-time":"2021-11-12T00:00:00Z","timestamp":1636675200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["AAL-2017-066"],"award-info":[{"award-number":["AAL-2017-066"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Gait performance is an important marker of motor and cognitive decline in older adults. An instrumented gait analysis resorting to inertial sensors allows the complete evaluation of spatiotemporal gait parameters, offering an alternative to laboratory-based assessments. To estimate gait parameters, foot trajectories are typically obtained by integrating acceleration two times. However, to deal with cumulative integration errors, additional error handling strategies are required. In this study, we propose an alternative approach based on a deep recurrent neural network to estimate heel and toe trajectories. We propose a coordinate frame transformation for stride trajectories that eliminates the dependency from previous strides and external inputs. Predicted trajectories are used to estimate an extensive set of spatiotemporal gait parameters. We evaluate the results in a dataset comprising foot-worn inertial sensor data acquired from a group of young adults, using an optical motion capture system as a reference. Heel and toe trajectories are predicted with low errors, in line with reference trajectories. A good agreement is also achieved between the reference and estimated gait parameters, in particular when turning strides are excluded from the analysis. The performance of the method is shown to be robust to imperfect sensor-foot alignment conditions.<\/jats:p>","DOI":"10.3390\/s21227517","type":"journal-article","created":{"date-parts":[[2021,11,14]],"date-time":"2021-11-14T20:51:53Z","timestamp":1636923113000},"page":"7517","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["A Deep Learning Approach for Foot Trajectory Estimation in Gait Analysis Using Inertial Sensors"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8133-0789","authenticated-orcid":false,"given":"V\u00e2nia","family":"Guimar\u00e3es","sequence":"first","affiliation":[{"name":"Fraunhofer Portugal AICOS, 4200-135 Porto, Portugal"},{"name":"Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8488-256X","authenticated-orcid":false,"given":"In\u00eas","family":"Sousa","sequence":"additional","affiliation":[{"name":"Fraunhofer Portugal AICOS, 4200-135 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6065-9358","authenticated-orcid":false,"given":"Miguel Velhote","family":"Correia","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal"},{"name":"INESC TEC (Institute for Systems and Computer Engineering, Technology and Science), 4200-465 Porto, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2021,11,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"881","DOI":"10.3389\/fphys.2020.00881","article-title":"Mobility in Older Community-Dwelling Persons: A Narrative Review","volume":"11","author":"Freiberger","year":"2020","journal-title":"Front. Physiol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"110625","DOI":"10.1016\/j.exger.2019.05.014","article-title":"Measuring gait speed to better identify prodromal dementia","volume":"124","author":"Grande","year":"2019","journal-title":"Exp. Gerontol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1016\/j.gaitpost.2015.12.008","article-title":"Usual walking speed and all-cause mortality risk in older people: A systematic review and meta-analysis","volume":"44","author":"Liu","year":"2016","journal-title":"Gait Posture"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1159\/000322194","article-title":"Laboratory Review: The Role of Gait Analysis in Seniors\u2019 Mobility and Fall Prevention","volume":"57","author":"Bridenbaugh","year":"2011","journal-title":"Gerontology"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1257","DOI":"10.1016\/j.gerinurse.2021.08.010","article-title":"Predictive value of intrinsic capacity on adverse outcomes among community-dwelling older adults","volume":"42","author":"Yu","year":"2021","journal-title":"Geriatr. Nurs."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"313","DOI":"10.3389\/fneur.2019.00313","article-title":"Comprehensive Quantitative Spatiotemporal Gait Analysis Identifies Gait Characteristics for Early Dementia Subtyping in Community Dwelling Older Adults","volume":"10","author":"Fransen","year":"2019","journal-title":"Front. Neurol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.neubiorev.2019.10.008","article-title":"Revealing the optimal thresholds for movement performance: A systematic review and meta-analysis to benchmark pathological walking behaviour","volume":"108","author":"Ravi","year":"2020","journal-title":"Neurosci. Biobehav. Rev."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1007\/s00391-019-01520-8","article-title":"Spatiotemporal gait analysis of older persons in clinical practice and research: Which parameters are relevant?","volume":"53","author":"Lindemann","year":"2020","journal-title":"Z. F\u00fcR Gerontol. Und Geriatr."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1521","DOI":"10.1109\/JBHI.2016.2608720","article-title":"Toward Pervasive Gait Analysis With Wearable Sensors: A Systematic Review","volume":"20","author":"Chen","year":"2016","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Guimar\u00e3es, V., Sousa, I., and Correia, M.V. (2021, January 23\u201325). Gait events detection from heel and toe trajectories: Comparison of methods using multiple datasets. Proceedings of the 2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA), Lausanne, Switzerland.","DOI":"10.1109\/MeMeA52024.2021.9478606"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1109\/TBME.2012.2227317","article-title":"On-Shoe Wearable Sensors for Gait and Turning Assessment of Patients with Parkinson\u2019s Disease","volume":"60","author":"Mariani","year":"2013","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.gaitpost.2005.01.001","article-title":"Defining spatial parameters for non-linear walking","volume":"23","author":"Huxham","year":"2006","journal-title":"Gait Posture"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1530","DOI":"10.3389\/fphys.2019.01530","article-title":"Inertial Measurement Unit-Based Estimation of Foot Trajectory for Clinical Gait Analysis","volume":"10","author":"Hori","year":"2020","journal-title":"Front. Physiol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.gaitpost.2017.06.019","article-title":"A systematic review of gait analysis methods based on inertial sensors and adaptive algorithms","volume":"57","author":"Caldas","year":"2017","journal-title":"Gait Posture"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1186\/s13634-020-00715-1","article-title":"Efficiency of deep neural networks for joint angle modeling in digital gait assessment","volume":"2021","author":"Moghaddamnia","year":"2021","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2999","DOI":"10.1016\/j.jbiomech.2010.07.003","article-title":"3D gait assessment in young and elderly subjects using foot-worn inertial sensors","volume":"43","author":"Mariani","year":"2010","journal-title":"J. Biomech."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1089","DOI":"10.1109\/TBME.2014.2368211","article-title":"Inertial sensor-based stride parameter calculation from gait sequences in geriatric patients","volume":"62","author":"Rampp","year":"2015","journal-title":"IEEE Trans. Bio. Med. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"727","DOI":"10.1016\/j.gaitpost.2014.07.016","article-title":"Towards the importance of minimum toe clearance in level ground walking in a healthy elderly population","volume":"40","author":"Hamacher","year":"2014","journal-title":"Gait Posture"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Hannink, J., Ollenschl\u00e4ger, M., Kluge, F., Roth, N., Klucken, J., and Eskofier, B.M. (2017). Benchmarking Foot Trajectory Estimation Methods for Mobile Gait Analysis. Sensors, 17.","DOI":"10.3390\/s17091940"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"3162","DOI":"10.1109\/TBME.2012.2216263","article-title":"Heel and Toe Clearance Estimation for Gait Analysis Using Wireless Inertial Sensors","volume":"59","author":"Mariani","year":"2012","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Kanzler, C.M., Barth, J., Rampp, A., Schlarb, H., Rott, F., Klucken, J., and Eskofier, B.M. (2015, January 25\u201329). Inertial sensor based and shoe size independent gait analysis including heel and toe clearance estimation. Proceedings of the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, Italy.","DOI":"10.1109\/EMBC.2015.7319618"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1109\/JBHI.2017.2679486","article-title":"Mobile Stride Length Estimation With Deep Convolutional Neural Networks","volume":"22","author":"Hannink","year":"2018","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1109\/JBHI.2016.2636456","article-title":"Sensor-Based Gait Parameter Extraction with Deep Convolutional Neural Networks","volume":"21","author":"Hannink","year":"2017","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Silva do Monte Lima, J.P., Uchiyama, H., and Taniguchi, R.I. (2019). End-to-End Learning Framework for IMU-Based 6-DOF Odometry. Sensors, 19.","DOI":"10.3390\/s19173777"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1351","DOI":"10.1109\/TMC.2019.2960780","article-title":"Deep Neural Network Based Inertial Odometry Using Low-Cost Inertial Measurement Units","volume":"20","author":"Chen","year":"2021","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Wang, Q., Ye, L., Luo, H., Men, A., Zhao, F., and Huang, Y. (2019). Pedestrian Stride-Length Estimation Based on LSTM and Denoising Autoencoders. Sensors, 19.","DOI":"10.3390\/s19040840"},{"key":"ref_27","first-page":"1","article-title":"PDRNet: A Deep-Learning Pedestrian Dead Reckoning Framework","volume":"1","author":"Asraf","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Guimar\u00e3es, V., Sousa, I., and Correia, M.V. (2021). Orientation-Invariant Spatio-Temporal Gait Analysis Using Foot-Worn Inertial Sensors. Sensors, 21.","DOI":"10.3390\/s21113940"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Shoemake, K. (1992). Uniform Random Rotations. Graphics Gems III (IBM Version), Elsevier.","DOI":"10.1016\/B978-0-08-050755-2.50036-1"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1994","DOI":"10.1109\/JBHI.2019.2958879","article-title":"Deep Learning for Fall Risk Assessment with Inertial Sensors: Utilizing Domain Knowledge in Spatio-Temporal Gait Parameters","volume":"24","author":"Tunca","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11517-019-02061-3","article-title":"Prediction of lower limb joint angles and moments during gait using artificial neural networks","volume":"58","author":"Mundt","year":"2020","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Weber, D., G\u00fchmann, C., and Seel, T. (2020, January 6\u20139). Neural Networks Versus Conventional Filters for Inertial-Sensor-based Attitude Estimation. Proceedings of the 2020 IEEE 23rd International Conference on Information Fusion (FUSION), Rustenburg, South Africa.","DOI":"10.23919\/FUSION45008.2020.9190634"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1235","DOI":"10.1162\/neco_a_01199","article-title":"A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures","volume":"31","author":"Yu","year":"2019","journal-title":"Neural Comput."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Mundt, M., Johnson, W.R., Potthast, W., Markert, B., Mian, A., and Alderson, J. (2021). A Comparison of Three Neural Network Approaches for Estimating Joint Angles and Moments from Inertial Measurement Units. Sensors, 21.","DOI":"10.3390\/s21134535"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Mundt, M., Koeppe, A., Bamer, F., David, S., and Markert, B. (2020). Artificial Neural Networks in Motion Analysis\u2014Applications of Unsupervised and Heuristic Feature Selection Techniques. Sensors, 20.","DOI":"10.3390\/s20164581"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1109\/LRA.2019.2959507","article-title":"OriNet: Robust 3-D Orientation Estimation with a Single Particular IMU","volume":"5","author":"Esfahani","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"56855","DOI":"10.1109\/ACCESS.2020.2982225","article-title":"LSTM-CNN Architecture for Human Activity Recognition","volume":"8","author":"Xia","year":"2020","journal-title":"IEEE Access"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Zebin, T., Sperrin, M., Peek, N., and Casson, A.J. (2018, January 18\u201321). Human activity recognition from inertial sensor time-series using batch normalized deep LSTM recurrent networks. Proceedings of the 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Honolulu, HI, USA.","DOI":"10.1109\/EMBC.2018.8513115"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Alawneh, L., Mohsen, B., Al-Zinati, M., Shatnawi, A., and Al-Ayyoub, M. (2020, January 23\u201327). A Comparison of Unidirectional and Bidirectional LSTM Networks for Human Activity Recognition. Proceedings of the 2020 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), Austin, TX, USA.","DOI":"10.1109\/PerComWorkshops48775.2020.9156264"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"486","DOI":"10.1109\/TBME.2004.840727","article-title":"Assessment of walking features from foot inertial sensing","volume":"52","author":"Sabatini","year":"2005","journal-title":"IEEE Trans.-Bio-Med. Eng."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Kluge, F., Ga\u00dfner, H., Hannink, J., Pasluosta, C., Klucken, J., and Eskofier, B. (2017). Towards Mobile Gait Analysis: Concurrent Validity and Test-Retest Reliability of an Inertial Measurement System for the Assessment of Spatio-Temporal Gait Parameters. Sensors, 17.","DOI":"10.3390\/s17071522"},{"key":"ref_42","unstructured":"Kingma, D.P., and Ba, J. (2017). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_43","first-page":"6765","article-title":"Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization","volume":"18","author":"Li","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref_44","unstructured":"O\u2019Malley, T., Bursztein, E., Long, J., Chollet, F., Jin, H., Invernizzi, L., de Marmiesse, G., Fu, Y., Podiv\u00ecn, J., and Sch\u00e4fer, F. (2021, July 07). Keras Tuner. Available online: https:\/\/github.com\/keras-team\/keras-tuner."},{"key":"ref_45","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Skog, I., Nilsson, J.O., and Handel, P. (2010, January 15\u201317). Evaluation of zero-velocity detectors for foot-mounted inertial navigation systems. Proceedings of the 2010 International Conference on Indoor Positioning and Indoor Navigation, Zurich, Switzerland.","DOI":"10.1109\/IPIN.2010.5646936"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"307","DOI":"10.2307\/2987937","article-title":"Measurement in Medicine: The Analysis of Method Comparison Studies","volume":"32","author":"Altman","year":"1983","journal-title":"Statistician"},{"key":"ref_48","first-page":"69","article-title":"A guide to appropriate use of Correlation coefficient in medical research","volume":"24","author":"Mukaka","year":"2012","journal-title":"Malawi Med. J."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1016\/j.compbiomed.2017.08.026","article-title":"Fuzzy inference model evaluating turn for Parkinson\u2019s disease patients","volume":"89","year":"2017","journal-title":"Comput. Biol. Med."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1897","DOI":"10.1109\/ACCESS.2018.2886899","article-title":"An End-to-End Multi-Task and Fusion CNN for Inertial-Based Gait Recognition","volume":"7","author":"Castro","year":"2019","journal-title":"IEEE Access"},{"key":"ref_51","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_52","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.jbiomech.2017.06.025","article-title":"Locomotion pattern and foot pressure adjustments during gentle turns in healthy subjects","volume":"60","author":"Peyer","year":"2017","journal-title":"J. Biomech."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Bonnyaud, C., Pradon, D., Bensmail, D., and Roche, N. (2015). Dynamic Stability and Risk of Tripping during the Timed Up and Go Test in Hemiparetic and Healthy Subjects. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0140317"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Tunca, C., Pehlivan, N., Ak, N., Arnrich, B., Salur, G., and Ersoy, C. (2017). Inertial Sensor-Based Robust Gait Analysis in Non-Hospital Settings for Neurological Disorders. Sensors, 17.","DOI":"10.3390\/s17040825"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"108102","DOI":"10.1016\/j.patcog.2021.108102","article-title":"Explainable deep learning for efficient and robust pattern recognition: A survey of recent developments","volume":"120","author":"Bai","year":"2021","journal-title":"Pattern Recognit."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"12364","DOI":"10.1109\/ACCESS.2020.2966142","article-title":"Data Augmentation for Inertial Sensor-Based Gait Deep Neural Network","volume":"8","author":"Tran","year":"2020","journal-title":"IEEE Access"},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1080\/10255842.2020.1789971","article-title":"Automated gap-filling for marker-based biomechanical motion capture data","volume":"23","author":"Camargo","year":"2020","journal-title":"Comput. Methods Biomech. Biomed. Eng."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Meyer, J., Kuderer, M., Muller, J., and Burgard, W. (June, January 31). Online marker labeling for fully automatic skeleton tracking in optical motion capture. Proceedings of the 2014 IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, China.","DOI":"10.1109\/ICRA.2014.6907690"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/22\/7517\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:29:09Z","timestamp":1760167749000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/22\/7517"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,12]]},"references-count":58,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2021,11]]}},"alternative-id":["s21227517"],"URL":"https:\/\/doi.org\/10.3390\/s21227517","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,12]]}}}