{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T11:38:44Z","timestamp":1779881924323,"version":"3.53.1"},"reference-count":18,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T00:00:00Z","timestamp":1756425600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Defence Science &amp; Technology Laboratory"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Classifying human locomotor activities from wearable sensor data is an important high-level component of control schemes for many wearable robotic exoskeletons. In this study, we evaluated three machine learning models for classifying activity type (walking, running, jumping), speed, and surface incline using input data from body-worn inertial measurement units (IMUs) and e-textile insole pressure sensors. The IMUs were positioned on segments of the lower limb and pelvis during lab-based data collection from 16 healthy participants (11 men, 5 women), who walked and ran on a treadmill at a range of preset speeds and inclines. Logistic Regression (LR), Random Forest (RF), and Light Gradient-Boosting Machine (LGBM) models were trained, tuned, and scored on a validation data set (n = 14), and then evaluated on a test set (n = 2). The LGBM model consistently outperformed the other two, predicting activity and speed well, but not incline. Further analysis showed that LGBM performed equally well with data from a limited number of IMUs, and that speed prediction was challenged by inclusion of abnormally fast walking and slow running trials. Gyroscope data was most important to model performance. Overall, LGBM models show promise for implementing locomotor activity prediction from lower-limb-mounted IMU data recorded at different anatomical locations.<\/jats:p>","DOI":"10.3390\/s25175365","type":"journal-article","created":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T16:42:21Z","timestamp":1756485741000},"page":"5365","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Evaluating Machine Learning-Based Classification of Human Locomotor Activities for Exoskeleton Control Using Inertial Measurement Unit and Pressure Insole Data"],"prefix":"10.3390","volume":"25","author":[{"given":"Tom","family":"Wilson","sequence":"first","affiliation":[{"name":"Research Software & Analytics Group, University of Exeter, Exeter EX4 4PY, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samuel","family":"Wisdish","sequence":"additional","affiliation":[{"name":"Public Health & Sport Sciences, University of Exeter Medical School, University of Exeter, Exeter EX4 4PY, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8106-5339","authenticated-orcid":false,"given":"Josh","family":"Osofa","sequence":"additional","affiliation":[{"name":"Human Sciences Delivery Team, Defence Science and Technology Laboratory, Salisbury SP4 0JQ, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6720-1961","authenticated-orcid":false,"given":"Dominic J.","family":"Farris","sequence":"additional","affiliation":[{"name":"Public Health & Sport Sciences, University of Exeter Medical School, University of Exeter, Exeter EX4 4PY, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1186\/s12984-020-00663-9","article-title":"The exoskeleton expansion: Improving walking and running economy","volume":"17","author":"Sawicki","year":"2020","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1038\/s41586-022-05191-1","article-title":"Personalizing exoskeleton assistance while walking in the real world","volume":"610","author":"Slade","year":"2022","journal-title":"Nature"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1038\/nature14288","article-title":"Reducing the energy cost of human walking using an unpowered exoskeleton","volume":"522","author":"Collins","year":"2015","journal-title":"Nature"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1797","DOI":"10.1109\/TMECH.2023.3322269","article-title":"Real-Time Assistive Control via IMU Locomotion Mode Detection in a Soft Exosuit: An Effective Approach to Enhance Walking Metabolic Efficiency","volume":"29","author":"Zhang","year":"2024","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"668","DOI":"10.1126\/science.aav7536","article-title":"Reducing the metabolic rate of walking and running with a versatile, portable exosuit","volume":"365","author":"Kim","year":"2019","journal-title":"Science"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Labarriere, F., Thomas, E., Calistri, L., Optasanu, V., Gueugnon, M., Ornetti, P., and Laroche, D. (2020). Machine Learning Approaches for Activity Recognition and\/or Activity Prediction in Locomotion Assistive Devices-A Systematic Review. Sensors, 20.","DOI":"10.3390\/s20216345"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1080\/00140139.2022.2059106","article-title":"A systematic literature review of evidence for the use of assistive exoskeletons in defence and security use cases","volume":"66","author":"Farris","year":"2023","journal-title":"Ergonomics"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1154","DOI":"10.1016\/j.jsams.2018.05.016","article-title":"Consensus paper on testing and evaluation of military exoskeletons for the dismounted combatant","volume":"21","author":"Mudie","year":"2018","journal-title":"J. Sci. Med. Sport"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"eaay9108","DOI":"10.1126\/scirobotics.aay9108","article-title":"Improving the energy economy of human running with powered and unpowered ankle exoskeleton assistance","volume":"5","author":"Witte","year":"2020","journal-title":"Sci. Robot."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1743-0003-12-1","article-title":"Control strategies for active lower extremity prosthetics and orthotics: A review","volume":"12","author":"Tucker","year":"2015","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_11","unstructured":"Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017, January 4\u20139). LightGBM: A highly efficient gradient boosting decision tree. Proceedings of the of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_12","first-page":"1937","article-title":"A comparative analysis of gradient boosting algorithms","volume":"54","year":"2020","journal-title":"Artif. Intell. Rev."},{"key":"ref_13","first-page":"257","article-title":"Some Fundamental Aspects of the Biomechanics of Overground vs. Treadmill Locomotion","volume":"12","year":"1980","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_14","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pederegosa","year":"2011","journal-title":"J. Mach. Learn. Python"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Couronne, R., Probst, P., and Boulesteix, A.L. (2018). Random forest versus logistic regression: A large-scale benchmark experiment. BMC Bioinform., 19.","DOI":"10.1186\/s12859-018-2264-5"},{"key":"ref_16","unstructured":"Grinsztajn, L., Oyallon, O., and Varoquaux, G. (2022). Why do tree-based models still outperform deep learning on tabular data?. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Kadir, M.E., Akash, P.S., Sharmin, S., Ali, A.A., and Shoyaib, M. (2020, January 11\u201314). A Proximity Weighted Evidential k Nearest Neighbor Classifier for Imbalanced Data. Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining, Singapore.","DOI":"10.1007\/978-3-030-47436-2_6"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1038\/nature04113","article-title":"Computer optimization of a minimal biped model discovers walking and running","volume":"439","author":"Srinivasan","year":"2006","journal-title":"Nature"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/17\/5365\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:35:39Z","timestamp":1760034939000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/17\/5365"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,29]]},"references-count":18,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["s25175365"],"URL":"https:\/\/doi.org\/10.3390\/s25175365","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,29]]}}}