{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T15:47:38Z","timestamp":1753890458999,"version":"3.41.2"},"reference-count":56,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T00:00:00Z","timestamp":1750377600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2203144 2203143"],"award-info":[{"award-number":["2203144 2203143"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P20GM109090 P20GM152301"],"award-info":[{"award-number":["P20GM109090 P20GM152301"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Bioeng. Biotechnol."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Biomechanical changes due to aging increase the oxygen consumption of walking by over 30%. When this is coupled with reduced oxygen uptake capacity, the ability to sustain walking becomes compromised. This reduced physical activity and mobility can lead to further physical degeneration and mortality. Unfortunately, the underlying reasons for the increased metabolic cost are still inadequately understood. While motion capture systems can measure signals with high temporal resolution, it is impossible to directly characterize the fluctuation of metabolic cost throughout the gait cycle.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>To address this issue, this research focuses on computing the metabolic cost time series from the mean value using two neural-network-based approaches: autoencoders (AEs) and expanders. For the AEs, the encoders are designed to compress the input time series down to their mean value, and the decoder expands those values into the time series. After training, the decoder is extracted and applied to mean metabolic cost values to compute the time series. A second approach leverages an expander to map the mean values to the time series without an encoder. The networks are trained using ten different metabolic cost models generated by a computational walking model that simulates the gait cycle subjected to 35 different robotic perturbations without using experimental input data. The networks are validated using the estimated metabolic costs for the unperturbed gait cycle.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The investigation found that AEs without tied weights and the expanders performed best using nonlinear activation functions, while the AEs with tied weights performed best with linear activation functions. Unexpectedly, the results show that the expanders outperform the AEs.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>A limitation of this research is the reliance on time series for the initial training. Future efforts will focus on developing methods that overcome this issue. Improved methods for estimating within-stride fluctuations in metabolic cost have the potential of improving rehabilitation and assistive devices by targeting the gait phases with increased metabolic cost. This research could also be applied to expand sparse measurements to locations or times that were not measured explicitly. This application would reduce the number of measurement points required to capture the response of a system.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fbioe.2025.1579085","type":"journal-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T05:22:37Z","timestamp":1750396957000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Estimating within-stride metabolic cost from stride-average data using autoencoders and expander networks"],"prefix":"10.3389","volume":"13","author":[{"given":"Manal","family":"Mustafa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex C.","family":"Dzewaltowski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philippe","family":"Malcolm","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keegan J.","family":"Moore","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"eabh1925","DOI":"10.1126\/scirobotics.abh1925","article-title":"Metabolically efficient walking assistance using optimized timed forces at the waist","volume":"7","author":"Antonellis","year":"2022","journal-title":"Sci. Robot."},{"key":"B2","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1152\/jappl.1973.34.1.128","article-title":"On-line computer analysis and breath-by-breath graphical display of exercise function tests","volume":"34","author":"Beaver","year":"1973","journal-title":"J. Appl. Physiol."},{"key":"B3","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1249\/jes.0000000000000204","article-title":"Exoskeletons improve locomotion economy by reducing active muscle volume","volume":"47","author":"Beck","year":"2019","journal-title":"Exerc. Sport Sci. Rev."},{"key":"B4","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/s0021-9290(03)00239-2","article-title":"A phenomenological model for estimating metabolic energy consumption in muscle contraction","volume":"37","author":"Bhargava","year":"2004","journal-title":"J. Biomechanics"},{"key":"B5","doi-asserted-by":"publisher","first-page":"7213","DOI":"10.1038\/srep07213","article-title":"Prosthetic ankle push-off work reduces metabolic rate but not collision work in non-amputee walking","volume":"4","author":"Caputo","year":"2014","journal-title":"Sci. Rep."},{"key":"B6","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1016\/j.asoc.2019.01.021","article-title":"A semi-supervised auto-encoder using label and sparse regularizations for classification","volume":"77","author":"Chai","year":"2019","journal-title":"Appl. Soft Comput."},{"volume-title":"Movement analysis with LSTM autoencoder for anomaly detection","year":"2024","author":"Diethelm","key":"B7"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1350135","DOI":"10.3389\/fbioe.2024.1350135","article-title":"Enhancing biomechanical machine learning with limited data: generating realistic synthetic posture data using generative artificial intelligence","volume":"12","author":"Dindorf","year":"2024","journal-title":"Front. Bioeng. Biotechnol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1097\/cm9.0000000000000095","article-title":"Artificial intelligence system of faster region-based convolutional neural network surpassing senior radiologists in evaluation of metastatic lymph nodes of rectal cancer","volume":"132","author":"Ding","year":"2019","journal-title":"Chin. Med. J. (Engl.)"},{"key":"B10","doi-asserted-by":"publisher","first-page":"2399","DOI":"10.1242\/jeb.006767","article-title":"Mechanics and energetics of swinging the human leg","volume":"210","author":"Doke","year":"2007","journal-title":"J. Exp. Biol."},{"key":"B11","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1186\/s12984-024-01424-8","article-title":"Perturbation-based estimation of within-stride cycle metabolic cost","volume":"21","author":"Dzewaltowski","year":"2024","journal-title":"J. Neuroeng. Rehabil."},{"key":"B12","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1249\/jes.0000000000000086","article-title":"The age-associated reduction in propulsive power generation in walking","volume":"44","author":"Franz","year":"2016","journal-title":"Exerc. Sport Sci. Rev."},{"key":"B13","doi-asserted-by":"publisher","first-page":"e1008280","DOI":"10.1371\/journal.pcbi.1008280","article-title":"Differences between joint-space and musculoskeletal estimations of metabolic rate time profiles","volume":"16","author":"Gonabadi","year":"2020","journal-title":"PLoS Comput. Biol."},{"key":"B14","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1152\/japplphysiol.01190.2004","article-title":"Energy cost and muscular activity required for leg swing during walking","volume":"99","author":"Gottschall","year":"2005","journal-title":"J. Appl. Physiol."},{"key":"B56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jbiomech.2018.09.009","article-title":"Machine learning in human movement biomechanics: Best practices, common pitfalls, and new opportunities","volume":"81","author":"Halilaj","year":"2018","journal-title":"J. Biomech."},{"key":"B15","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1007\/11007937_4","article-title":"The CMA evolution strategy: a comparing review","volume":"192","author":"Hansen","year":"2006","journal-title":"Stud. Fuzziness Soft Comput."},{"key":"B16","doi-asserted-by":"publisher","first-page":"020905","DOI":"10.1115\/1.4029304","article-title":"Is my model good enough? Best practices for verification and validation of musculoskeletal models and simulations of movement","volume":"137","author":"Hicks","year":"2015","journal-title":"J. Biomech. Eng."},{"key":"B17","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1016\/j.jbiomech.2004.11.033","article-title":"Evaluation of a Hill based muscle model for the energy cost and efficiency of muscular contraction","volume":"39","author":"Houdijk","year":"2006","journal-title":"J. Biomech."},{"key":"B18","doi-asserted-by":"publisher","first-page":"104046","DOI":"10.1016\/j.medengphy.2023.104046","article-title":"Three-dimensional lumbar spine generation using variational autoencoder","volume":"120","author":"Huang","year":"2023","journal-title":"Med. Eng. Phys."},{"key":"B19","doi-asserted-by":"publisher","first-page":"109093","DOI":"10.1016\/j.isci.2024.109093","article-title":"A contactless monitoring system for accurately predicting energy expenditure during treadmill walking based on an ensemble neural network","volume":"27","author":"Huang","year":"2024","journal-title":"iScience"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.6084\/M9.FIGSHARE.7473191","article-title":"Predicting energy cost from wearable sensors: a dataset of energetic and physiological wearable sensor data from healthy individuals performing multiple physical activities","author":"Ingraham","year":"2019"},{"key":"B21","doi-asserted-by":"publisher","first-page":"e02721","DOI":"10.1002\/cnm.2721","article-title":"A joint-space numerical model of metabolic energy expenditure for human multibody dynamic system","volume":"31","author":"Kim","year":"2015","journal-title":"Int. J. Numer. method. Biomed. Eng."},{"key":"B22","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 [cs.LG]"},{"key":"B23","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0222037","volume-title":"Metabolic cost calculations of gait using musculoskeletal energy models, a comparison study","author":"Koelewijn","year":"2019"},{"key":"B24","doi-asserted-by":"publisher","first-page":"2831","DOI":"10.1242\/jeb.01709","article-title":"A modified Hill muscle model that predicts muscle power output and efficiency during sinusoidal length changes","volume":"208","author":"Lichtwark","year":"2005","journal-title":"J. Exp. Biol."},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2208.09197","article-title":"EAA-Net: rethinking the autoencoder architecture with intra-class features for medical image segmentation","author":"Ma","year":"2022","journal-title":"arXiv [cs.CV]"},{"key":"B26","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1007\/bf00699624","article-title":"Positive and negative work performances and their efficiencies in human locomotion","volume":"25","author":"Margaria","year":"1968","journal-title":"Int. Z. f\u00fcr Angew. Physiol. Einschlie\u00dflich Arbeitsphysiologie"},{"key":"B27","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1126\/science.1090704","article-title":"Partitioning the energetics of walking and running: swinging the limbs is expensive","volume":"303","author":"Marsh","year":"2004","journal-title":"Science"},{"key":"B28","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1152\/jappl.1992.73.1.200","article-title":"Effects of age and physical activity status on the speed-aerobic demand relationship of walking","volume":"73","author":"Martin","year":"1992","journal-title":"J. Appl. Physiol."},{"key":"B29","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1111\/j.1748-1716.2006.01522.x","article-title":"Metabolic cost, mechanical work, and efficiency during walking in young and older men","volume":"186","author":"Mian","year":"2006","journal-title":"Acta Physiol. (Oxf.)"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1373","DOI":"10.1016\/j.jbiomech.2014.01.049","article-title":"A comparison of muscle energy models for simulating human walking in three dimensions","volume":"47","author":"Miller","year":"2014","journal-title":"J. Biomech."},{"key":"B31","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1006\/jtbi.1997.0407","article-title":"A theory of metabolic costs for bipedal gaits","volume":"186","author":"Minetti","year":"1997","journal-title":"J. Theor. Biol."},{"key":"B32","doi-asserted-by":"publisher","first-page":"306","DOI":"10.2165\/00007256-199723050-00004","article-title":"Walking to health","volume":"23","author":"Morris","year":"1997","journal-title":"Sports Med."},{"key":"B33","unstructured":"3D MRI brain tumor segmentation using autoencoder regularization\n          \n          \n            \n              Myronenko\n              A.\n            \n          \n          \n          2018"},{"key":"B34","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1162\/neco.1992.4.4.473","article-title":"Simplifying neural networks by soft weight-sharing","volume":"4","author":"Nowlan","year":"1992","journal-title":"Neural comput."},{"key":"B35","doi-asserted-by":"publisher","first-page":"3303","DOI":"10.1016\/j.jbiomech.2008.06.039","article-title":"Effects of aging and arm swing on the metabolic cost of stability in human walking","volume":"41","author":"Ortega","year":"2008","journal-title":"J. Biomech."},{"key":"B36","doi-asserted-by":"publisher","first-page":"3073","DOI":"10.1162\/neco_a_01435","article-title":"Expansion of information in the binary autoencoder with random binary weights","volume":"33","author":"Osaulenko","year":"2021","journal-title":"Neural comput."},{"key":"B37","doi-asserted-by":"publisher","first-page":"1552","DOI":"10.1080\/10255842.2021.1900134","article-title":"Muscle metabolic energy costs while modifying propulsive force generation during walking","volume":"24","author":"Pimentel","year":"2021","journal-title":"Comput. Methods Biomech. Biomed. Engin."},{"key":"B38","doi-asserted-by":"publisher","first-page":"1041","DOI":"10.1249\/01.mss.0000222829.34111.9c","article-title":"Metabolic cost of over ground gait in younger stroke patients and healthy controls","volume":"38","author":"Platts","year":"2006","journal-title":"Med. Sci. Sports Exerc."},{"key":"B39","doi-asserted-by":"publisher","first-page":"1134135","DOI":"10.3389\/fbioe.2023.1134135","article-title":"Autoencoder-based myoelectric controller for prosthetic hands","volume":"11","author":"Portnova-Fahreeva","year":"2023","journal-title":"Front. Bioeng. Biotechnol."},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_2","article-title":"Deep Expander networks: efficient deep networks from graph theory","author":"Prabhu","year":"2017","journal-title":"arXiv [cs.CV]"},{"key":"B41","doi-asserted-by":"publisher","first-page":"e0168070","DOI":"10.1371\/journal.pone.0168070","article-title":"Instantaneous metabolic cost of walking: joint-space dynamic model with subject-specific heat rate","volume":"11","author":"Roberts","year":"2016","journal-title":"PLoS One"},{"key":"B42","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1111\/j.1469-8749.1990.tb16945.x","article-title":"Energy expenditure index of walking for normal children and for children with cerebral palsy","volume":"32","author":"Rose","year":"1990","journal-title":"Dev. Med. Child. Neurol."},{"key":"B43","doi-asserted-by":"publisher","first-page":"1406","DOI":"10.1152\/japplphysiol.00445.2014","article-title":"Estimating instantaneous energetic cost during non-steady-state gait","volume":"117","author":"Selinger","year":"2014","journal-title":"J. Appl. Physiol."},{"key":"B44","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1186\/s12984-019-0535-7","article-title":"Rapid energy expenditure estimation for ankle assisted and inclined loaded walking","volume":"16","author":"Slade","year":"2019","journal-title":"J. Neuroeng. Rehabil."},{"key":"B45","doi-asserted-by":"publisher","first-page":"3493","DOI":"10.1113\/jp270228","article-title":"A neural circuitry that emphasizes spinal feedback generates diverse behaviours of human locomotion","volume":"593","author":"Song","year":"2015","journal-title":"J. Physiol."},{"key":"B46","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.1113\/jp275166","article-title":"Predictive neuromechanical simulations indicate why walking performance declines with ageing","volume":"596","author":"Song","year":"2018","journal-title":"J. Physiol."},{"key":"B47","doi-asserted-by":"publisher","first-page":"1329","DOI":"10.1098\/rsif.2010.0084","article-title":"Stance and swing phase costs in human walking","volume":"7","author":"Umberger","year":"2010","journal-title":"J. R. Soc. Interface"},{"key":"B48","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1080\/1025584031000091678","article-title":"A model of human muscle energy expenditure","volume":"6","author":"Umberger","year":"2003","journal-title":"Comput. Methods Biomech. Biomed. Engin."},{"key":"B49","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1097\/jes.0b013e31820d7bc5","article-title":"Understanding muscle energetics in locomotion","volume":"39","author":"Umberger","year":"2011","journal-title":"Exerc. Sport Sci. Rev."},{"key":"B50","first-page":"3371","article-title":"Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"B51","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1249\/00005768-199002000-00011","article-title":"Physiological determinants of pulmonary gas exchange kinetics during exercise","volume":"22","author":"Whipp","year":"1990","journal-title":"Med. Sci. Sports Exerc."},{"key":"B52","doi-asserted-by":"publisher","first-page":"1506","DOI":"10.1152\/jappl.1982.52.6.1506","article-title":"Parameters of ventilatory and gas exchange dynamics during exercise","volume":"52","author":"Whipp","year":"1982","journal-title":"J. Appl. Physiol."},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1511.06335","article-title":"Unsupervised deep embedding for clustering analysis","author":"Xie","year":"2015","journal-title":"arXiv [cs.LG]"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1610.04794","article-title":"Towards K-means-friendly spaces: simultaneous deep learning and clustering","author":"Yang","year":"2016","journal-title":"arXiv [cs.LG]"},{"key":"B55","doi-asserted-by":"publisher","first-page":"108648","DOI":"10.1016\/j.cmpb.2025.108648","article-title":"Machine learning based finite element analysis for personalized prediction of pressure injury risk in patients with spinal cord injury","volume":"261","author":"Zhang","year":"2025","journal-title":"Comput. Methods Programs Biomed."}],"container-title":["Frontiers in Bioengineering and Biotechnology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2025.1579085\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T05:22:39Z","timestamp":1750396959000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2025.1579085\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":56,"alternative-id":["10.3389\/fbioe.2025.1579085"],"URL":"https:\/\/doi.org\/10.3389\/fbioe.2025.1579085","relation":{},"ISSN":["2296-4185"],"issn-type":[{"type":"electronic","value":"2296-4185"}],"subject":[],"published":{"date-parts":[[2025,6,20]]},"article-number":"1579085"}}