{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T13:07:19Z","timestamp":1793452039227,"version":"4.5.0"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T00:00:00Z","timestamp":1770768000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Bioeng. Biotechnol."],"abstract":"\n Objective<\/jats:title>\n This study applies machine learning (ML) techniques to address this hardware limitation by determining the feasibility of reducing a high-dimensional 17-sensor network to a \u201cminimal-optimal\u201d subset without compromising measurement accuracy. Unlike previous studies focusing on activity classification, we systematically quantify the information redundancy in kinematic chains to optimize sensor fusion architectures.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n Twenty-five recreational runners performed treadmill protocols at three speeds (8, 10, and 12\u00a0km\/h) while wearing a gold-standard Xsens MVN system (17 IMUs). Raw accelerometer and gyroscope signals were programmatically subsetted to simulate minimal configurations. A Random Forest (RF) regression model was selected after benchmarking against baseline Linear Regression and deep learning (LSTM) models. A comprehensive vector of time-and frequency-domain features was extracted via sliding windows, and Recursive Feature Elimination (RFE) was applied to identify the most critical signal attributes.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Analysis revealed that a single lumbosacral IMU could successfully reconstruct global parameters (Cadence, Vertical Oscillation, Ground Contact Time) with high precision (\n \n \n \n \n R<\/mml:mi>\n 2<\/mml:mn>\n <\/mml:msup>\n ><\/mml:mo>\n 0.95<\/mml:mn>\n ,<\/mml:mo>\n M<\/mml:mi>\n A<\/mml:mi>\n P<\/mml:mi>\n E<\/mml:mi>\n <<\/mml:mo>\n 5<\/mml:mn>\n %<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n ), outperforming standard commercial benchmarks. However, this single-node setup failed to detect gait asymmetry (\n \n \n \n \n R<\/mml:mi>\n 2<\/mml:mn>\n <\/mml:msup>\n =<\/mml:mo>\n 0.52<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n ). A distributed three-sensor fusion configuration (Lumbosacral + Bilateral Ankles) resolved this limitation, achieving results comparable to the full-body system for all parameters (\n \n \n \n \n R<\/mml:mi>\n 2<\/mml:mn>\n <\/mml:msup>\n ><\/mml:mo>\n 0.91<\/mml:mn>\n ,<\/mml:mo>\n M<\/mml:mi>\n A<\/mml:mi>\n P<\/mml:mi>\n E<\/mml:mi>\n =<\/mml:mo>\n 7.12<\/mml:mn>\n %<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n ). Performance remained robust across all running speeds, with only a marginal accuracy drop at 12\u00a0km\/h.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusion<\/jats:title>\n This study validates a machine learning framework for optimizing sensor array design. The proposed three-sensor fusion offers a robust, low-cost architectural blueprint for next-generation wearable devices, proving that complex deep learning is not always required when sensor placement is biomechanically optimized.<\/jats:p>\n <\/jats:sec>","DOI":"10.3389\/fbioe.2026.1762919","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T06:51:49Z","timestamp":1770792709000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Optimizing wearable IMU configurations for running gait analysis: a machine learning-based sensor fusion approach"],"prefix":"10.3389","volume":"14","author":[{"given":"Ye","family":"Yuan","sequence":"first","affiliation":[{"name":"College of Physical Education, Xuzhou University of Technology","place":["Xuzhou, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaohui","family":"Yu","sequence":"additional","affiliation":[{"name":"Graduate School, Tianjin University of Traditional Chinese Medicine","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanshan","family":"Cai","sequence":"additional","affiliation":[{"name":"Faculty of Health and Medicine, Lancaster University","place":["Lancaster, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weidong","family":"Cheng","sequence":"additional","affiliation":[{"name":"General Education College, Cyberspace Security University of China","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1016\/s0021-9290(02)00008-8","article-title":"Spatio-temporal parameters of gait measured by an ambulatory system using miniature gyroscopes","volume":"35","author":"Aminian","year":"2002","journal-title":"J. Biomechanics"},{"key":"B2","first-page":"458","article-title":"Determining the minimal number of wearable sensors for the classification of running gait patterns","volume":"41","author":"Benson","year":"2023","journal-title":"J. Sports Sci."},{"key":"B3","volume-title":"Pattern recognition and machine learning","author":"Bishop","year":"2006"},{"key":"B4","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"B5","doi-asserted-by":"publisher","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":"B6","doi-asserted-by":"publisher","first-page":"A1","DOI":"10.2519\/jospt.2010.0302","article-title":"Patellofemoral pain syndrome: proximal, distal, and local factors","volume":"40","author":"Davis","year":"2010","journal-title":"J. Orthop. and Sports Phys. Ther."},{"key":"B7","first-page":"13351","article-title":"Gait event detection in running using a single wearable sensor: a deep learning approach","volume":"20","author":"Dutta","year":"2020","journal-title":"IEEE Sensors J."},{"key":"B15","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"B9","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1007\/s00779-010-0293-9","article-title":"Preprocessing techniques for activity recognition from accelerometer data","volume":"14","author":"Figo","year":"2010","journal-title":"Personal Ubiquitous Comput."},{"key":"B14","doi-asserted-by":"publisher","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":"B12","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1016\/j.gaitpost.2009.11.014","article-title":"Real-time gait event detection for normal subjects from lower trunk accelerations","volume":"31","author":"Gonz\u00e1lez","year":"2010","journal-title":"Gait Posture"},{"key":"B10","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1249\/01.mss.0000126803.66636.dd","article-title":"Impact and overuse injuries in runners","volume":"36","author":"Hreljac","year":"2004","journal-title":"Med. and Sci. Sports and Exerc."},{"key":"B28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3272127.3275108","article-title":"Deep inertial poser: Learning to reconstruct human pose from sparse inertial measurements in real time","volume":"37","author":"Huang","year":"2018","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"B13","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1016\/j.jacc.2014.04.058","article-title":"Leisure-time running reduces all-cause and cardiovascular mortality risk","volume":"64","author":"Lee","year":"2014","journal-title":"J. Am. Coll. Cardiol."},{"key":"B17","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal."},{"key":"B18","first-page":"813","article-title":"Kinetic risk factors of running-related injuries in female recreational runners","volume":"25","author":"Napier","year":"2015","journal-title":"Scand. J. Med. Sci. Sports"},{"key":"B8","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1177\/1754337113502472","article-title":"Method analysis of accelerometers and gyroscopes in running gait: A systematic review","volume":"228","author":"Norris","year":"2014","journal-title":"Proc. Inst. Mech. Eng. Pt. P J. Sports Eng. Tech."},{"key":"B29","doi-asserted-by":"publisher","first-page":"115","DOI":"10.3390\/s16010115","article-title":"Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition","volume":"16","author":"Ord\u00f3\u00f1ez","year":"2016","journal-title":"Sensors"},{"key":"B16","doi-asserted-by":"publisher","first-page":"260","DOI":"10.3390\/s19071555","article-title":"Validation of the xsens MVN awinda system for 3D running analysis","volume":"68","author":"Poitras","year":"2019","journal-title":"Gait and Posture"},{"key":"B27","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1016\/j.eswa.2016.04.032","article-title":"Human activity recognition with smartphone sensors using deep learning neural networks","volume":"59","author":"Ronao","year":"2016","journal-title":"Expert Syst. Appl."},{"key":"B30","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/S0966-6362(00)00070-9","article-title":"Symmetry and limb dominance in able-bodied gait: a review","volume":"12","author":"Sadeghi","year":"2000","journal-title":"Gait Posture"},{"key":"B19","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1136\/bjsm.36.2.95","article-title":"A retrospective study of running injuries","volume":"36","author":"Taunton","year":"2002","journal-title":"Br. J. Sports Med."},{"key":"B20","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1136\/bjsm.2006.033548","article-title":"Incidence and determinants of lower extremity running injuries in long distance runners: a systematic review","volume":"41","author":"van Gent","year":"2007","journal-title":"Br. J. Sports Med."},{"key":"B31","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1007\/s40279-019-01237-z","article-title":"Is motorized treadmill running biomechanically comparable to overground running? A systematic review and meta-analysis of cross-over studies","volume":"50","author":"Van Hooren","year":"2020","journal-title":"Sports Med."},{"key":"B21","doi-asserted-by":"publisher","first-page":"481","DOI":"10.2519\/jospt.2011.3470","article-title":"The effect of a single-session biofeedback intervention on running mechanics and injury-related variables","volume":"41","author":"Willy","year":"2011","journal-title":"J. Orthop. and Sports Phys. Ther."},{"key":"B22","doi-asserted-by":"crossref","DOI":"10.1002\/9780470549148","volume-title":"Biomechanics and motor control of human movement","author":"Winter","year":"2009"},{"key":"B23","first-page":"1","article-title":"Estimating spatio-temporal gait parameters from a single inertial sensor at the trunk: a machine learning approach","volume":"74","author":"Wouda","year":"2018","journal-title":"J. Biomechanics"},{"key":"B58","doi-asserted-by":"publisher","first-page":"2981","DOI":"10.1038\/s41598-022-07054-1","article-title":"Explaining the differences of gait patterns between high and low mileage runners with machine learning","volume":"12","author":"Xu","year":"2022","journal-title":"Sci. Rep."},{"key":"B26","doi-asserted-by":"publisher","first-page":"110519","DOI":"10.1016\/j.ijmecsci.2025.110519","article-title":"Data-driven deep learning for predicting ligament fatigue failure risk mechanisms","volume":"301","author":"Xu","year":"2025","journal-title":"Int. J. Mech. Sci."}],"container-title":["Frontiers in Bioengineering and Biotechnology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2026.1762919\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T10:23:07Z","timestamp":1771928587000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2026.1762919\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,11]]},"references-count":29,"alternative-id":["10.3389\/fbioe.2026.1762919"],"URL":"https:\/\/doi.org\/10.3389\/fbioe.2026.1762919","relation":{},"ISSN":["2296-4185"],"issn-type":[{"value":"2296-4185","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,11]]},"article-number":"1762919"}}