{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T16:43:33Z","timestamp":1792169013462,"version":"4.4.0"},"reference-count":24,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T00:00:00Z","timestamp":1724889600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Nurvv Ltd"},{"DOI":"10.13039\/501100000835","name":"University of Bath","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000835","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Ground reaction force (GRF) data is often collected for the biomechanical analysis of running, due to the performance and injury risk insights that GRF analysis can provide. Traditional methods typically limit GRF collection to controlled lab environments, recent studies have looked to combine the ease of use of wearable sensors with the statistical power of machine learning to estimate continuous GRF data outside of these restrictions. Before such systems can be deployed with confidence outside of the lab they must be shown to be a valid and accurate tool for a wide range of users. The aim of this study was to evaluate how accurately a consumer-priced sensor system could estimate GRFs whilst a heterogeneous group of runners completed a treadmill protocol with three different personalised running speeds and three gradients. Fifty runners (25 female, 25 male) wearing pressure insoles made up of 16 resistive sensors and an inertial measurement unit ran at various speeds and gradients on an instrumented treadmill. A long short term memory (LSTM) neural network was trained to estimate both vertical $(GRF_v)$ and anteroposterior $(GRF_{ap})$ force traces using leave one subject out validation. The average relative root mean squared error (rRMSE) was 3.2% and 3.1%, respectively. The mean $(GRF_v)$ rRMSE across the evaluated participants ranged from 0.8% to 8.8% and from 1.3% to 17.3% in the $(GRF_{ap})$ estimation. The findings from this study suggest that current consumer-priced sensors could be used to accurately estimate two-dimensional GRFs for a wide range of runners at a variety of running intensities. The estimated kinetics could be used to provide runners with individualised feedback as well as form the basis of data collection for running injury risk factor studies on a much larger scale than is currently possible with lab based methods.<\/jats:p>","DOI":"10.7717\/peerj.17896","type":"journal-article","created":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T08:15:23Z","timestamp":1724919323000},"page":"e17896","source":"Crossref","is-referenced-by-count":16,"title":["Consumer-priced wearable sensors combined with deep learning can be used to accurately predict ground reaction forces during various treadmill running conditions"],"prefix":"10.7717","volume":"12","author":[{"given":"Josh","family":"Carter","sequence":"first","affiliation":[{"name":"Department of Health, University of Bath, Bath, Somerset, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Bath, Bath, Somerset, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7877-6755","authenticated-orcid":true,"given":"Dario","family":"Cazzola","sequence":"additional","affiliation":[{"name":"Department of Health, University of Bath, Bath, Somerset, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9021-8956","authenticated-orcid":true,"given":"Grant","family":"Trewartha","sequence":"additional","affiliation":[{"name":"School of Health and Life Sciences, University of Teesside, Middlesbrough, North Yorkshire, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5383-7072","authenticated-orcid":true,"given":"Ezio","family":"Preatoni","sequence":"additional","affiliation":[{"name":"Department of Health, University of Bath, Bath, Somerset, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2024,8,29]]},"reference":[{"key":"10.7717\/peerj.17896\/ref-1","doi-asserted-by":"publisher","first-page":"e12752","DOI":"10.1101\/2021.03.17.435901","article-title":"Predicting continuous ground reaction forces from accelerometers during uphill and downhill running: a recurrent neural network solution","volume":"10","author":"Alcantara","year":"2021","journal-title":"PeerJ"},{"issue":"8","key":"10.7717\/peerj.17896\/ref-2","doi-asserted-by":"publisher","first-page":"2564","DOI":"10.3390\/s18082564","article-title":"Indirect measurement of ground reaction forces and moments by means of wearable inertial sensors: a systematic review","volume":"18","author":"Ancillao","year":"2018","journal-title":"Sensors (Basel)"},{"issue":"2","key":"10.7717\/peerj.17896\/ref-3","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.gaitpost.2018.04.047","article-title":"The use of wearable devices for walking and running gait analysis outside of the lab: a systematic review","volume":"63","author":"Benson","year":"2018","journal-title":"Gait & Posture"},{"issue":"7","key":"10.7717\/peerj.17896\/ref-4","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.3390\/s19071483","article-title":"Automated accelerometer-based gait event detection during multiple running conditions","volume":"19","author":"Benson","year":"2019","journal-title":"Sensors"},{"issue":"22","key":"10.7717\/peerj.17896\/ref-5","doi-asserted-by":"publisher","first-page":"7709","DOI":"10.3390\/s21227709","article-title":"Machine learning-based estimation of ground reaction forces and knee joint kinetics from inertial sensors while performing a vertical drop jump","volume":"21","author":"Cerfoglio","year":"2021","journal-title":"Sensors"},{"issue":"7","key":"10.7717\/peerj.17896\/ref-6","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.1007\/s40279-019-01110-z","article-title":"Biomechanical risk factors associated with running-related injuries: a systematic review","volume":"49","author":"Ceyssens","year":"2019","journal-title":"Sports Medicine"},{"key":"10.7717\/peerj.17896\/ref-7","doi-asserted-by":"publisher","first-page":"78","DOI":"10.3389\/fbioe.2020.00604","article-title":"CNN-based estimation of sagittal plane walking and running biomechanics from measured and simulated inertial sensor data","volume":"8","author":"Dorschky","year":"2020","journal-title":"Frontiers in Bioengineering and Biotechnology"},{"issue":"6","key":"10.7717\/peerj.17896\/ref-8","doi-asserted-by":"publisher","first-page":"1217","DOI":"10.1109\/TNSRE.2019.2916476","article-title":"Insole-based estimation of vertical ground reaction force using one-step learning with probabilistic regression and data augmentation","volume":"27","author":"Eguchi","year":"2019","journal-title":"IEEE Transactions on Neural Systems and Rehabilitation Engineering"},{"issue":"7","key":"10.7717\/peerj.17896\/ref-9","doi-asserted-by":"publisher","first-page":"1588","DOI":"10.1016\/j.jbiomech.2014.03.002","article-title":"A simple field method to identify foot strike pattern during running","volume":"47","author":"Giandolini","year":"2014","journal-title":"Journal of Biomechanics"},{"issue":"23","key":"10.7717\/peerj.17896\/ref-10","doi-asserted-by":"publisher","first-page":"5227","DOI":"10.3390\/s19235227","article-title":"Estimating biomechanical time-series with wearable sensors: a systematic review of machine learning techniques","volume":"19","author":"Gurchiek","year":"2019","journal-title":"Sensors"},{"issue":"8","key":"10.7717\/peerj.17896\/ref-11","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"issue":"9","key":"10.7717\/peerj.17896\/ref-12","doi-asserted-by":"publisher","first-page":"3338","DOI":"10.3390\/s22093338","article-title":"Estimating running ground reaction forces from plantar pressure during graded running","volume":"22","author":"Honert","year":"2022","journal-title":"Sensors"},{"issue":"23","key":"10.7717\/peerj.17896\/ref-13","doi-asserted-by":"publisher","first-page":"26470","DOI":"10.1109\/JSEN.2021.3119658","article-title":"Recent advances in quantitative gait analysis using wearable sensors: a review","volume":"21","author":"Hutabarat","year":"2021","journal-title":"IEEE Sensors Journal"},{"issue":"1","key":"10.7717\/peerj.17896\/ref-14","doi-asserted-by":"publisher","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":"2021","journal-title":"IEEE Transactions on Biomedical Engineering"},{"issue":"4","key":"10.7717\/peerj.17896\/ref-15","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1080\/02640419608727717","article-title":"A 1% treadmill grade most accurately reflects the energetic cost of outdoor running","volume":"14","author":"Jones","year":"1996","journal-title":"Journal of Sports Sciences"},{"issue":"7","key":"10.7717\/peerj.17896\/ref-16","doi-asserted-by":"publisher","DOI":"10.3390\/s23073428","article-title":"A deep learning model for 3d ground reaction force estimation using shoes with three uniaxial load cells","volume":"23","author":"Kim","year":"2023","journal-title":"Sensors"},{"key":"10.7717\/peerj.17896\/ref-17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6980","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"ArXiv preprint"},{"issue":"1","key":"10.7717\/peerj.17896\/ref-18","doi-asserted-by":"publisher","first-page":"e0210000","DOI":"10.1371\/journal.pone.0210000","article-title":"Ground reaction force metrics are not strongly correlated with tibial bone load when running across speeds and slopes: implications for science, sport and wearable tech","volume":"14","author":"Matijevich","year":"2019","journal-title":"PLOS ONE"},{"key":"10.7717\/peerj.17896\/ref-19","doi-asserted-by":"publisher","first-page":"102690","DOI":"10.1016\/j.humov.2020.102690","article-title":"Combining wearable sensor signals, machine learning and biomechanics to estimate tibial bone force and damage during running","volume":"74","author":"Matijevich","year":"2020","journal-title":"Human Movement Science"},{"key":"10.7717\/peerj.17896\/ref-20","volume-title":"Interpretable machine learning: a guide for making black box models explainable","author":"Molnar","year":"2020"},{"key":"10.7717\/peerj.17896\/ref-21","first-page":"8026","article-title":"Pytorch: an imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"12","key":"10.7717\/peerj.17896\/ref-22","doi-asserted-by":"publisher","first-page":"121006","DOI":"10.1115\/1.4055238","article-title":"A feature-encoded physics-informed parameter identification neural network for musculoskeletal systems","volume":"144","author":"Taneja","year":"2022","journal-title":"Journal of Biomechanical Engineering"},{"key":"10.7717\/peerj.17896\/ref-23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.48550\/arXiv.1706.03762","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.7717\/peerj.17896\/ref-24","doi-asserted-by":"publisher","first-page":"e0203839","DOI":"10.3389\/fnbot.2022.913052","article-title":"Recent machine learning progress in lower limb running biomechanics with wearable technology: a systematic review","volume":"16","author":"Xiang","year":"2022","journal-title":"Frontiers in Neurorobotics"}],"container-title":["PeerJ"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/17896.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/17896.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/17896.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/17896.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T08:15:39Z","timestamp":1724919339000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/17896"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,29]]},"references-count":24,"alternative-id":["10.7717\/peerj.17896"],"URL":"https:\/\/doi.org\/10.7717\/peerj.17896","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2167-8359"],"issn-type":[{"value":"2167-8359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,29]]},"article-number":"e17896"}}