A Comparison of Three Neural Network Approaches for Estimating Joint Angles and Moments from Inertial Measurement Units
Open accessAbstract
The application of artificial intelligence techniques to wearable sensor data may facilitate accurate analysis outside of controlled laboratory settings—the holy grail for gait clinicians and sports scientists looking to bridge the lab to field divide. Using these techniques, parameters that are difficult to directly measure in-the-wild, may be predicted using surrogate lower resolution inputs. One example is the prediction of joint kinematics and kinetics based on inputs from inertial measurement unit (IMU) sensors. Despite increased research, there is a paucity of information examining the most suitable artificial neural network (ANN) for predicting gait kinematics and kinetics from IMUs. This paper compares the performance of three commonly employed ANNs used to predict gait kinematics and kinetics: multilayer perceptron (MLP); long short-term memory (LSTM); and convolutional neural networks (CNN). Overall high correlations between ground truth and predicted kinematic and kinetic data were found across all investigated ANNs. However, the optimal ANN should be based on the prediction task and the intended use-case application. For the prediction of joint angles, CNNs appear favourable, however these ANNs do not show an advantage over an MLP network for the prediction of joint moments. If real-time joint angle and joint moment prediction is desirable an LSTM network should be utilised.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
LSTM resolves long-term dependencies through gated mechanisms, dynamically parses continuous motion trajectories, and is used for exoskeleton joint angle prediction.
“| LSTM | Resolve long-term dependencies through gated | Dynamically parse continuous motion | Exoskeleton joint angle prediction 148,244,245 |”
From Recent advances in intelligent wearable systems: from multiscale biomechanical features towards human motion intent prediction (2026) · cites this paper as [245]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Wu, G., Siegler, S., Allard, P., Kirtley, C., Leardini, A., Rosenbaum, D., Whittle, M., DʼLima, D. D., Cristofolini, L., Witte, H., et al. (2002) · Journal of Biomechanics · doi:10.1016/s0021-9290(01)00222-6 · Cited by 3,249 · see citing works
Research Methods in Biomechanics
Robertson, D. G. E., Caldwell, G. E., Hamill, J., Kamen, G., & Whittlesey, S. N. (2014) · Human Kinetics eBooks · doi:10.5040/9781492595809 · Cited by 1,233 · see citing works
Hyperband: a novel bandit-based approach to hyperparameter optimization
Li, L., Jamieson, K., DeSalvo, G., Rostamizadeh, A., & Talwalkar, A. (2017) · Journal of Machine Learning Research · Cited by 930 · see citing works
Kobsar, D., Charlton, J. M., Tse, C. T. F., Esculier, J.-F., Graffos, A., Krowchuk, N. M., Thatcher, D., & Hunt, M. A. (2020) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-020-00685-3 · Cited by 324 · see citing works
Exploring the Role of Wearable Technology in Sport Kinematics and Kinetics: A Systematic Review
Adesida, Y., Papi, E., & McGregor, A. H. (2019) · Sensors · doi:10.3390/s19071597 · Cited by 288 · see citing works
Ancillao, A., Tedesco, S. A., Barton, J. J., & O’Flynn, B. (2018) · Sensors · doi:10.3390/s18082564 · Cited by 244 · see citing works
Wouda, F. J., Giuberti, M., Bellusci, G., Maartens, E., Reenalda, J., van Beijnum, B.-J. F., & Veltink, P. H. (2018) · Frontiers in Physiology · doi:10.3389/fphys.2018.00218 · Cited by 210 · see citing works
Palermo, E., Rossi, S., Marini, F., Patanè, F., & Cappa, P. (2014) · Measurement · doi:10.1016/j.measurement.2014.03.004 · Cited by 183 · see citing works
Mundt, M., Koeppe, A., David, S., Witter, T., Bamer, F., Potthast, W., & Markert, B. A. (2020) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2020.00041 · Cited by 166 · see citing works
Self-citationLim, H., Kim, B. J., & Park, S. (2019) · Sensors · doi:10.3390/s20010130 · Cited by 155 · see citing works
Dorschky, E., Nitschke, M., Martindale, C. F., van den Bogert, A. J., Koelewijn, A. D., & Eskofier, B. M. (2020) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2020.00604 · Cited by 137 · see citing works
Prediction of lower limb joint angles and moments during gait using artificial neural networks
Mundt, M., Thomsen, W., Witter, T., Koeppe, A., David, S., Bamer, F., Potthast, W., & Markert, B. A. (2019) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-019-02061-3 · Cited by 133 · see citing works
Self-citationJohnson, W. R., Mian, A. S., Robinson, M. A., Verheul, J., Lloyd, D. G., & Alderson, J. A. (2020) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2020.3006158 · Cited by 126 · see citing works
Self-citationStetter, B. J., Krafft, F. C., Ringhof, S., et al. (2020) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2020.00009 · Cited by 118 · see citing works
Robert‐Lachaine, X., Mecheri, H., Larue, C., & Plamondon, A. (2017) · Gait & Posture · doi:10.1016/j.gaitpost.2017.02.029 · Cited by 108 · see citing works
Determining anatomical frames via inertial motion capture: A survey of methods
Vitali, R. V., & Perkins, N. C. (2020) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2020.109832 · Cited by 100 · see citing works
Predicting Athlete Ground Reaction Forces and Moments From Spatio-Temporal Driven CNN Models
Johnson, W. R., Alderson, J. A., Lloyd, D. G., & Mian, A. S. (2018) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2018.2854632 · Cited by 93 · see citing works
Self-citationCaruso, M., Sabatini, A. M., Laidig, D., Seel, T., Knaflitz, M., Croce, U. D., & Cereatti, A. (2021) · Sensors · doi:10.3390/s21072543 · Cited by 87 · see citing works
Gurchiek, R. D., Cheney, N., & McGinnis, R. S. (2019) · Sensors · doi:10.3390/s19235227 · Cited by 85 · see citing works
Mundt, M., Koeppe, A., David, S., et al. (2020) · Medical Engineering & Physics · doi:10.1016/j.medengphy.2020.10.001 · Cited by 73 · see citing works
Self-citationRapp, E., Shin, S., Thomsen, W., Ferber, R., & Halilaj, E. (2021) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2021.110229 · Cited by 71 · see citing works
On-field player workload exposure and knee injury risk monitoring via deep learning
Johnson, W. R., Mian, A., Lloyd, D. G., & Alderson, J. A. (2019) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2019.07.002 · Cited by 69 · see citing works
Self-citationAn efficient Monte Carlo strategy for elasto-plastic structures based on recurrent neural networks
Koeppe, A., Bamer, F., & Markert, B. A. (2019) · Acta Mechanica · doi:10.1007/s00707-019-02436-5 · Cited by 55 · see citing works
Self-citationAssessment of the measurement accuracy of inertial sensors during different tasks of daily living
Mundt, M., Thomsen, W., David, S., Dupré, T., Bamer, F., Potthast, W., & Markert, B. A. (2018) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2018.12.023 · Cited by 45 · see citing works
Self-citationMundt, M., Koeppe, A., Bamer, F., David, S., & Markert, B. A. (2020) · Sensors · doi:10.3390/s20164581 · Cited by 35 · see citing works
Self-citationKomnik, I., Peters, M., Funken, J., David, S., Weiss, S., & Potthast, W. (2016) · PLoS ONE · doi:10.1371/journal.pone.0168566 · Cited by 28 · see citing works
Self-citationDupré, T., Dietzsch, M., Komnik, I., Potthast, W., & David, S. (2018) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2018.12.013 · Cited by 26 · see citing works
Self-citationGurchiek, R. D., Cheney, N., & McGinnis, R. S. (2019) · Preprints.org · doi:10.20944/preprints201911.0006.v1 · Cited by 20 · see citing works
Determination of gait parameters in real‐world environment using low‐cost inertial sensors
Mundt, M., Thomsen, W., Bamer, F., et al. (2018) · PAMM · doi:10.1002/pamm.201800014 · Cited by 6 · see citing works
Self-citationMcGeown, J. P., Hume, P. A., Theadom, A., Kara, S., & Russell, B. K. (2022) · Journal of science and medicine in sport · doi:10.1016/j.jsams.2021.11.017 · Cited by 2 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- [16]Goodfellow I. Bengio Y. Courville A. Deep Learning MIT Press Cambridge, MA, USA 2016 Available online: http://www.deeplearningbook.org (accessed on 1 October 2020)
Cited by
Sorted by citations
Task-agnostic exoskeleton control via biological joint moment estimation
Molinaro, D. D., Scherpereel, K. L., Schonhaut, E. B., Evangelopoulos, G., Shepherd, M. K., & Young, A. J. (2024) · Nature · doi:10.1038/s41586-024-08157-7 · Cited by 107 · see citing works
Chen, S., Peng, C., Yang, B., Lin, J., Zhou, L., Jiang, Z., Liu, Z., Liu, Y., & Tang, L. (2026) · npj Artificial Intelligence · doi:10.1038/s44387-026-00083-5 · Cited by 9 · see citing works
- Authors
- Mundt, M., Johnson, W. R., Potthast, W., Markert, B., Mian, A., & Alderson, J.
- Affiliations
- The University of Western Australia (AU)
- Houston Astros Baseball Club, Houston, TX 77001, USA
- German Sport University Cologne (DE)
- RWTH Aachen University (DE)
- Corresponding author
- Mundt, Marion
- ORCID
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2021-07-01
- Volume
- 21
- Issue
- 13
- Pages
- 4535
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC8271391
- OpenAlex
- W3175585004
- Cited by
- 95
- References
- 30
- Citations by year
- 2026: 15 · 2025: 21 · 2024: 24 · 2023: 22 · 2022: 9 · 2021: 4
- FWCI
- 4.48
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- UWA Profiles and Research Repository (UWA) (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- RWTH Publications (RWTH Aachen) (submittedVersion, other-oa)
- Topics
- Physical Sciences › Engineering › Biomedical Engineering › Gait Recognition and Analysis
- Physical Sciences › Engineering › Biomedical Engineering › Lower Extremity Biomechanics and Pathologies
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Keywords
- joint angle estimation, joint moment estimation, inertial measurement unit, wearable sensors, gait kinematics, gait kinetics, artificial neural networks, multilayer perceptron, long short-term memory, convolutional neural networks, real-time prediction, model comparison
- MeSH terms
- Artificial Intelligence, Biomechanical Phenomena, Gait, Kinetics, Neural Networks, Computer
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
