Real-Time Intended Knee Joint Motion Prediction by Deep-Recurrent Neural Networks
The DOI matches its Crossref record; 28 of the 29 references it cites were found in a registry or an index.
Abstract
Human-assisting intelligent systems demand certain methods to precisely predict motorized limb joint angles. This paper presents the application of deep-recurrent neural networks (RNNs), which is a type of neural network for processing sequential data, for predicting the knee joint angle in real-time. This model is created based on a combination of electromyographic (EMG) signals, (with electrodes being placed on three leg muscles), and inertial measurements of the upper and lower legs. The data collected from different subjects when they performed different gaits were used to construct the model, which was evaluated in a real-time setting. The proposed RNN model based on fusion information contains a balance between computational complexity and prediction accuracy. Results on a microcontroller show that, within a predicted horizon of 50 ms, the model has a low prediction error of ±2.93 degrees.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“| RNN | Process sequential data via recurrent structures | Simple temporal analysis, low latency | Basic motion recognition (e.g., arm |”
From Recent advances in intelligent wearable systems: from multiscale biomechanical features towards human motion intent prediction (2026) · cites this paper as [110]
In the citing paper
“| Standing and gait | Contraction of leg muscle groups | sEMG | 110 |”
From Recent advances in intelligent wearable systems: from multiscale biomechanical features towards human motion intent prediction (2026) · cites this paper as [110]
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“GRU and other forms of neural network layers [23], [24], are”
BackgroundAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 3×
“Several RNNs are trained and fine-tuned in a TensorFlow [15] deep learning framework with the Adam Optimizer [16].”
MethodScikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
Matplotlib: a 2D graphics environment
Hunter, J. D. (2007) · Computing in Science & Engineering · doi:10.1109/mcse.2007.55 · Cited by 39,249 · cited 1×
“Data is visualized with Matplotlib [25].”
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545 · cited 1×
“GRU and other forms of neural network layers [23], [24], are”
BackgroundTensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., et al. (2016) · arXiv · doi:10.48550/arxiv.1603.04467 · Cited by 9,408 · cited 1×
“Flow [15] deep learning framework with the Adam Optimizer [16].”
MethodA Practical Guide to Support Vector Classication
Hsu, C., Chang, C.-C., & Lin, C. (2008) · Cited by 5,083
Estimating the Prevalence of Limb Loss in the United States: 2005 to 2050
Ziegler-Graham, K., MacKenzie, E. J., Ephraim, P. L., Travison, T. G., & Brookmeyer, R. (2008) · Archives of Physical Medicine and Rehabilitation · doi:10.1016/j.apmr.2007.11.005 · Cited by 2,816 · cited 2×
“I. INTRODUCTION BY 2020 it is estimated that there will be over 879,000people living with a major lower limb amputation in the United States [1].”
BackgroundSurface Electromyography Signal Processing and Classification Techniques
Chowdhury, R., Reaz, M., Ali, M., Bakar, A., Chellappan, K., & Chang, T. (2013) · Sensors · doi:10.3390/s130912431 · Cited by 1,000 · cited 1×
“‘[29], fully connected neural networks can be applied to the sensor integration problem.”
Background(2014) · International Conference on Learning Representations · Cited by 634
Research works printed but not linked: 2
- ng, 2017, Why is deep learning taking off?
- 2018, Getting started with the Keras functional API
Cited by
Deep Learning for EMG-based Human-Machine Interaction: A Review
Xiong, D., Zhang, D., Zhao, X., & Zhao, Y. (2021) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2021.1003865 · Cited by 395
“[109] estimate the angle of the shoulder and elbow using the CNN consecutively combined with the RNN.”
MethodZhang, J., Zhao, Y., Shone, F., Li, Z., Frangi, A. F., Xie, S. Q., & Zhang, Z.-Q. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2022.3226860 · Cited by 172
“Similar ideas were also reported in [24], [25], [26], [27].”
ResultGautam, A., Panwar, M., Biswas, D., & Acharyya, A. (2020) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2020.2972523 · Cited by 142
“Based on the aforementioned observations, it can be noted that the state-of-the-art methodologies used a combination of sEMG signal with inertial sensor data and goniometers for joint angle prediction [2], [6], [18]–[20], whereas for movement classification only sEMG signal is being preferred.”
BackgroundJeong, H., Lee, J. Y., Lee, K., Kang, Y. J., Kim, J.-T., Avila, R., Tzavelis, A., Kim, J., Ryu, H., Kwak, S. S., et al. (2021) · Science Advances · doi:10.1126/sciadv.abg3092 · Cited by 121
Self-citationAn IMU-Based Real-Time Gait Detection Method for Intelligent Control of Knee Assistive Devices
Lu, Y., Zhu, J., Chen, W., & Ma, X. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3329222 · Cited by 99
“Inertial measurement units (IMUs) combined with algorithms, such as machine learning [12], [13], [14], [15] and rule-based [16] approaches, have been proposed to overcome the above limitations [14], [17].”
Background
Metadata
- Authors
- Huang, Y., He, Z., Liu, Y., Yang, R., Zhang, X., Cheng, G., Yi, J., Ferreira, J. P., & Liu, T.
- Affiliations
- State Key Laboratory Fluid Power and Mechatronic Systems (CN)
- Ministry of Civil Affairs (CN)
- Beijing Union University (CN)
- Rutgers, The State University of New Jersey (US)
- Venue
- IEEE Sensors Journal
- Published
- 2019-12-01
- Volume
- 19
- Issue
- 23
- Pages
- 11503-11509
- ISSN
- 1530-437X (ISSN-L)
- 1558-1748
- 2379-9153
- OpenAlex
- W2965100371
- Cited by
- 105
- References
- 29
- Citations by year
- 2026: 6 · 2025: 21 · 2024: 19 · 2023: 20 · 2022: 16 · 2021: 17 · 2020: 5 · 2019: 1
- FWCI
- 3.44
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Sensors Journal (publishedVersion)
- Funders
- National Natural Science Foundation of China (51775485, U1613203)
- Beijing Municipal Commission of Education (KZ201811417048)
- Northwestern Polytechnical University (2018QNA4004)
- Fundação para a Ciência e a Tecnologia
- COMPETE 2020 Program Automatic Adaptation of a Humanoid Robot Gait to Different Floor-Robot Friction Coefficients (PTDC/EEI-AUT/5141/2014)
- Topics
- Physical Sciences › Engineering › Biomedical Engineering › Muscle activation and electromyography studies
- Physical Sciences › Engineering › Biomedical Engineering › Prosthetics and Rehabilitation Robotics
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Human Motion and Animation
- Keywords
- deep recurrent neural networks, electromyography, inertial measurement unit, gait, real-time prediction, sensor fusion, microcontroller implementation
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Real-Time Intended Knee Joint Motion Prediction by Deep-Recurrent Neural Networks. https://app.cochat.ai/papers/10.1109/jsen.2019.2933603
- The paper
- Huang, Y., He, Z., Liu, Y., Yang, R., Zhang, X., Cheng, G., Yi, J., Ferreira, J. P., & Liu, T. (2019). Real-Time Intended Knee Joint Motion Prediction by Deep-Recurrent Neural Networks. IEEE Sensors Journal. https://doi.org/10.1109/jsen.2019.2933603
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.