{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T15:20:50Z","timestamp":1773156050429,"version":"3.50.1"},"reference-count":40,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2021,1,27]],"date-time":"2021-01-27T00:00:00Z","timestamp":1611705600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>A promising but still scarcely explored strategy for the estimation of gait parameters based on inertial sensors involves the adoption of machine learning techniques. However, existing approaches are reliable only for specific conditions, inertial measurements unit (IMU) placement on the body, protocols, or when combined with additional devices. In this paper, we tested an alternative gait-events estimation approach which is fully data-driven and does not rely on a priori models or assumptions. High-frequency (512 Hz) data from a commercial inertial unit were recorded during 500 steps performed by 40 healthy participants. Sensors\u2019 readings were synchronized with a reference ground reaction force system to determine initial\/terminal contacts. Then, we extracted a set of features from windowed data labeled according to the reference. Two gray-box approaches were evaluated: (1) classifiers (decision trees) returning the presence of a gait event in each time window and (2) a classifier discriminating between stance and swing phases. Both outputs were submitted to a deterministic algorithm correcting spurious clusters of predictions. The stance vs. swing approach estimated the stride time duration with an average error lower than 20 ms and confidence bounds between \u00b150 ms. These figures are suitable to detect clinically meaningful differences across different populations.<\/jats:p>","DOI":"10.3390\/s21030839","type":"journal-article","created":{"date-parts":[[2021,1,27]],"date-time":"2021-01-27T12:20:26Z","timestamp":1611750026000},"page":"839","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Machine-Learning Based Determination of Gait Events from Foot-Mounted Inertial Units"],"prefix":"10.3390","volume":"21","author":[{"given":"Matteo","family":"Zago","sequence":"first","affiliation":[{"name":"Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, 20133 Milano, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2640-1764","authenticated-orcid":false,"given":"Marco","family":"Tarabini","sequence":"additional","affiliation":[{"name":"Dipartimento di Meccanica, Politecnico di Milano, 20133 Milano, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martina","family":"Delfino Spiga","sequence":"additional","affiliation":[{"name":"Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, 20133 Milano, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3350-9829","authenticated-orcid":false,"given":"Cristina","family":"Ferrario","sequence":"additional","affiliation":[{"name":"Dipartimento di Meccanica, Politecnico di Milano, 20133 Milano, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2240-5394","authenticated-orcid":false,"given":"Filippo","family":"Bertozzi","sequence":"additional","affiliation":[{"name":"Dipartimento di Scienze Biomediche per la Salute, Universit\u00e0 degli Studi di Milano, 20133 Milano, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6532-6464","authenticated-orcid":false,"given":"Chiarella","family":"Sforza","sequence":"additional","affiliation":[{"name":"Dipartimento di Scienze Biomediche per la Salute, Universit\u00e0 degli Studi di Milano, 20133 Milano, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2772-4837","authenticated-orcid":false,"given":"Manuela","family":"Galli","sequence":"additional","affiliation":[{"name":"Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, 20133 Milano, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,1,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1016\/0167-9457(96)00006-1","article-title":"Clinical gait analysis: A review","volume":"15","author":"Whittle","year":"1996","journal-title":"Hum. Mov. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3759","DOI":"10.1016\/j.jbiomech.2016.10.033","article-title":"Gait biomechanics in the era of data science","volume":"49","author":"Ferber","year":"2016","journal-title":"J. Biomech."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1001\/jama.2010.1923","article-title":"Gait Speed and Survival in Older Adults","volume":"305","author":"Studenski","year":"2011","journal-title":"JAMA"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.jbiomech.2017.11.010","article-title":"A practical step length algorithm using lower limb angular velocities","volume":"66","author":"Allseits","year":"2018","journal-title":"J. Biomech."},{"key":"ref_5","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_6","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/j.gaitpost.2017.01.024","article-title":"What can gait tell us about dementia? Review of epidemiological and neuropsychological evidence","volume":"53","author":"Valkanova","year":"2017","journal-title":"Gait Posture"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.gaitpost.2019.05.026","article-title":"Gait analysis in patients after bilateral versus unilateral total hip arthroplasty","volume":"72","author":"Temporiti","year":"2019","journal-title":"Gait Posture"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1064","DOI":"10.1589\/jpts.28.1064","article-title":"Lower limbs kinematic assessment of the effect of a gym and hydrotherapy rehabilitation protocol after knee megaprosthesis: A case report","volume":"28","author":"Lovecchio","year":"2016","journal-title":"J. Phys. Ther. Sci."},{"key":"ref_9","unstructured":"Perry, J., and Burnfield, J.N. (2010). Gait Analysis: Normal and Pathological Function, SLACK Incorporated. [2nd ed.]."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1434","DOI":"10.1109\/TBME.2004.827933","article-title":"Gait assessment in Parkinson\u2019s disease: Toward an ambulatory system for long-term monitoring","volume":"51","author":"Salarian","year":"2004","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhou, L., Fischer, E., Tunca, C., Brahms, C.M., Ersoy, C., Granacher, U., and Arnrich, B. (2020). How we found our imu: Guidelines to IMU selection and a comparison of seven IMUs for pervasive healthcare applications. Sensors, 20.","DOI":"10.3390\/s20154090"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1080\/17434440.2016.1198694","article-title":"Wearable inertial sensors for human movement analysis","volume":"13","author":"Iosa","year":"2016","journal-title":"Expert Rev. Med. Devices"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fbioe.2020.00041","article-title":"Estimation of Gait Mechanics Based on Simulated and Measured IMU Data Using an Artificial Neural Network","volume":"8","author":"Mundt","year":"2020","journal-title":"Front. Bioeng. Biotechnol."},{"key":"ref_14","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_15","doi-asserted-by":"crossref","unstructured":"Wouda, F.J., Giuberti, M., Bellusci, G., and Veltink, P.H. (2016). Estimation of Full-Body Poses Using Only Five Inertial Sensors: An Eager or Lazy Learning Approach?. Sensors, 16.","DOI":"10.3390\/s16122138"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhou, L., Tunca, C., Fischer, E., Brahms, C.M., Ersoy, C., Granacher, U., and Arnrich, B. (2020, January 20\u201324). Validation of an IMU Gait Analysis Algorithm for Gait Monitoring in Daily Life Situations. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, QC, Canada.","DOI":"10.1109\/EMBC44109.2020.9176827"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1016\/j.jelekin.2018.06.009","article-title":"Gait evaluation using inertial measurement units in subjects with Parkinson\u2019s disease","volume":"42","author":"Zago","year":"2018","journal-title":"J. Electromyogr. Kinesiol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"7821","DOI":"10.1109\/JSEN.2016.2609392","article-title":"Wearable Inertial Sensors for Human Motion Analysis: A review","volume":"16","year":"2016","journal-title":"IEEE Sens. J."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1109\/TNSRE.2019.2958679","article-title":"Accurate Ambulatory Gait Analysis in Walking and Running Using Machine Learning Models","volume":"28","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"764","DOI":"10.1109\/TNSRE.2015.2457511","article-title":"A mobile Kalman-filter based solution for the real-time estimation of spatio-temporal gait parameters","volume":"24","author":"Ferrari","year":"2016","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"5614","DOI":"10.3390\/s130505614","article-title":"Inertial sensor-based two feet motion tracking for gait analysis","volume":"13","year":"2013","journal-title":"Sensors"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.gaitpost.2017.06.019","article-title":"Gait & Posture 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_23","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.cmpb.2012.02.003","article-title":"Estimation of spatial-temporal gait parameters in level walking based on a single accelerometer: Validation on normal subjects by standard gait analysis","volume":"108","author":"Benedetti","year":"2012","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1785","DOI":"10.1088\/0967-3334\/37\/10\/1785","article-title":"Measuring gait with an accelerometer-based wearable: Influence of device location, testing protocol and age","volume":"37","author":"Hickey","year":"2016","journal-title":"Physiol. Meas."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1016\/j.medengphy.2015.02.003","article-title":"Instrumenting gait with an accelerometer: A system and algorithm examination","volume":"47","author":"Godfrey","year":"2015","journal-title":"Med. Eng. Phys."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1016\/j.gaitpost.2013.08.025","article-title":"Validation of a protocol for the estimation of three-dimensional body center of mass kinematics in sport","volume":"39","author":"Mapelli","year":"2014","journal-title":"Gait Posture"},{"key":"ref_27","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_28","doi-asserted-by":"crossref","unstructured":"Keloth, S.M., Viswanathan, R., Jelfs, B., Arjunan, S., Raghav, S., and Kumar, D. (2019). Which gait parameters and walking patterns show the significant differences between Parkinson\u2019s disease and healthy participants?. Biosensors, 9.","DOI":"10.3390\/bios9020059"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Yeo, S.S., and Park, G.Y. (2020). Accuracy Verification of Spatio-Temporal and. Sensors, 20.","DOI":"10.3390\/s20051343"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5121\/ijcses.2014.5201","article-title":"Time Alignment Techniques for Experimental Sensor Data","volume":"5","author":"Rhudy","year":"2014","journal-title":"Int. J. Comput. Sci. Eng. Surv."},{"key":"ref_31","first-page":"45","article-title":"Measuring uncertainty of ultrasonic longitudinal phase velocity estimation using different time-delay estimation methods based on cross-correlation: Computational simulation and experiments","volume":"122","author":"Cortela","year":"2018","journal-title":"Meas. J. Int. Meas. Confed."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1123\/jab.19.2.178","article-title":"Identifying heel contact and toe-off using forceplate thresholds with a range of digital-filter cutoff frequencies","volume":"19","author":"Tirosh","year":"2003","journal-title":"J. Appl. Biomech."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Zago, M., Sforza, C., Dolci, C., Tarabini, M., and Galli, M. (2019). Use of machine learning and wearable sensors to predict energetics and kinematics of cutting maneuvers. Sensors, 19.","DOI":"10.3390\/s19143094"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"353","DOI":"10.3389\/fnhum.2017.00353","article-title":"Guidelines for assessment of gait and reference values for spatiotemporal gait parameters in older adults: The biomathics and canadian gait consortiums initiative","volume":"11","author":"Beauchet","year":"2017","journal-title":"Front. Hum. Neurosci."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.gaitpost.2011.03.024","article-title":"Normative spatiotemporal gait parameters in older adults","volume":"34","author":"Hollman","year":"2011","journal-title":"Gait Posture"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1186\/s11556-017-0188-0","article-title":"Study of the association between gait variability and physical activity","volume":"14","author":"Ciprandi","year":"2017","journal-title":"Eur. Rev. Aging Phys. Act."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1186\/1743-0003-8-37","article-title":"Test-retest reliability of stride time variability while dual tasking in healthy and demented adults with frontotemporal degeneration","volume":"8","author":"Beauchet","year":"2011","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/j.gaitpost.2009.06.003","article-title":"Effects of Down syndrome on three-dimensional motion during walking at different speeds","volume":"30","author":"Agiovlasitis","year":"2009","journal-title":"Gait Posture"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Carbajales-Lopez, J., Becerro-de-Bengoa-Vallejo, R., Losa-Iglesias, M.E., Casado-Hern\u00e1ndez, I., Benito-De Pedro, M., Rodr\u00edguez-Sanz, D., Calvo-Lobo, C., and Antol\u00edn, M.S. (2020). The optogait motion analysis system for clinical assessment of 2D spatio-temporal gait parameters in young adults: A reliability and repeatability observational study. Appl. Sci., 10.","DOI":"10.3390\/app10113726"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Coviello, G., Avitabile, G., and Florio, A. (2020). A synchronized multi-unit wireless platform for long-term activity monitoring. Electronics, 9.","DOI":"10.3390\/electronics9071118"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/3\/839\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:16:15Z","timestamp":1760159775000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/3\/839"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,27]]},"references-count":40,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,2]]}},"alternative-id":["s21030839"],"URL":"https:\/\/doi.org\/10.3390\/s21030839","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,27]]}}}