A strain gauge based locomotion mode recognition method using convolutional neural network
Abstract
Locomotion mode recognition can contribute to precise control of active lower-limb prostheses in different environments. In this paper, we propose a novel locomotion mode recognition method based on convolutional neural network and strain gauge signals. The strain gauge only provides one-dimensional signals and is also used in the control strategy of the robotic prosthesis. The convolutional neural network takes the raw noisy signals as inputs. Three transtibial amputee subjects were recruited in the experiments, and three locomotion modes were recognized. The overall three-class locomotion mode recognition accuracy is 92.06±1.34% in the hold-out test and 92.53±1.61% in the 5-fold cross-validation. The results show that the strain gauge contains information of locomotion modes, and the convolutional neural network has the capacity of extracting features from raw signals.
Integrity signals
Registry
Cites
Statistics
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?
A majority of CNNs consist of five to nine layers, usually including two to three convolutional layers, two to three max-pooling layers, followed by one to two fully connected layers before the output layer.
“A majority of the CNNs consist of five to nine layers [23,63,64,113,114,165,166,167,168], usually including two to three convolutional layers, two to three max-pooling layers, followed by one to two fully connected layers before feeding the feature representation into the output layer (softmax layer in most cases).”
From Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances (2022) · cites this paper as [165]
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126 · see citing works
null (2016) · Philosophy Study · doi:10.17265/2159-5313/2016.09.003 · Cited by 28,317 · see citing works
Convolutional networks for images, speech, and time series
LeCun, Y., & Bengio, Y. (1998) · HAL · doi:10.5555/303568.303704 · Cited by 4,637 · see citing works
Human activity recognition with smartphone sensors using deep learning neural networks
Ronao, C. A., & Cho, S.-B. (2016) · Expert Systems with Applications · doi:10.1016/j.eswa.2016.04.032 · Cited by 1,215 · see citing works
Neptune, R. R., Kautz, S. A., & Zajac, F. E. (2001) · Journal of Biomechanics · doi:10.1016/s0021-9290(01)00105-1 · Cited by 1,138 · see citing works
Convolutional Neural Networks for Human Activity Recognition using Mobile Sensors
Zeng, M., Nguyen, L. T., Yu, B., Mengshoel, O. J., Zhu, J., Wu, P., & Zhang, J. (2014) · Proceedings of the 6th International Conference on Mobile Computing, Applications and Services · doi:10.4108/icst.mobicase.2014.257786 · Cited by 876 · see citing works
A Strategy for Identifying Locomotion Modes Using Surface Electromyography
Huang, H., Kuiken, T., & Lipschutz, R. D. (2008) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2008.2003293 · Cited by 517 · see citing works
Multiclass Real-Time Intent Recognition of a Powered Lower Limb Prosthesis
Varol, H. A., Sup, F. C., & Goldfarb, M. T. (2009) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2009.2034734 · Cited by 426 · see citing works
Dißelhorst-Klug, C., Schmitz‐Rode, T., & Rau, G. (2008) · Clinical Biomechanics · doi:10.1016/j.clinbiomech.2008.08.003 · Cited by 416 · see citing works
Reviews on Various Inertial Measurement Unit (IMU) Sensor Applications
Ahmad, N., Ghazilla, R. A. R., Khairi, N. M., & Kasi, V. (2013) · International Journal of Signal Processing Systems · doi:10.12720/ijsps.1.2.256-262 · Cited by 407 · see citing works
Exploring convolutional neural network structures and optimization techniques for speech recognition
Abdel‐Hamid, O., Deng, L., & Yu, D. (2013) · Interspeech (USB) · doi:10.21437/interspeech.2013-744 · Cited by 392 · see citing works
Human activity recognition from accelerometer data using Convolutional Neural Network
Lee, S.-M., Yoon, S. M., & Cho, H. (2017) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp.2017.7881728 · Cited by 356 · see citing works
The human ankle during walking: implications for design of biomimetic ankle prostheses
Hansen, A. H., Childress, D. S., Miff, S. C., et al. (2004) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2004.01.017 · Cited by 347 · see citing works
Jiménez-Fabián, R., & Verlinden, O. (2011) · Medical Engineering & Physics · doi:10.1016/j.medengphy.2011.11.018 · Cited by 315 · see citing works
Proprioception from a neurally controlled lower-extremity prosthesis
Clites, T. R., Carty, M. J., ULLAURI, J. G. B., Carney, M. E., Mooney, L. M., Duval, J.-F., Srinivasan, S. S., & Herr, H. (2018) · Science Translational Medicine · doi:10.1126/scitranslmed.aap8373 · Cited by 232 · see citing works
Young, A. J., Kuiken, T., & Hargrove, L. J. (2014) · Journal of Neural Engineering · doi:10.1088/1741-2560/11/5/056021 · Cited by 203 · see citing works
Discrimination of walking patterns using wavelet-based fractal analysis
Sekine, M., TAMURA, T., Akay, M., Fujimoto, T., Togawa, T., & Fukui, Y. (2002) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2002.802879 · Cited by 201 · see citing works
Bu, N., Okamoto, M., & Tsuji, T. (2009) · IEEE Transactions on Robotics · doi:10.1109/tro.2009.2019782 · Cited by 159 · see citing works
Liu, M., Wang, D., & Huang, H. (2015) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2015.2420539 · Cited by 145 · see citing works
Robotic transtibial prosthesis with biomechanical energy regeneration
Hitt, J. K., Sugar, T. G., Holgate, M. A., et al. (2009) · Industrial Robot the international journal of robotics research and application · doi:10.1108/01439910910980169 · Cited by 115 · see citing works
Walk the Walk: A Lightweight Active Transtibial Prosthesis
Wang, Q., Yuan, K., Zhu, J., & Wang, L. (2015) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2015.2408791 · Cited by 95 · see citing works
Self-citationFuzzy-Logic-Based Terrain Identification with Multisensor Fusion for Transtibial Amputees
Yuan, K., Wang, Q., & Wang, L. (2014) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2014.2309708 · Cited by 94 · see citing works
Self-citationGait mode recognition and control for a portable-powered ankle-foot orthosis
Li, Y. D., & Hsiao‐Wecksler, E. T. (2013) · International Conference on Rehabilitation Robotics · doi:10.1109/icorr.2013.6650373 · Cited by 88 · see citing works
A powered prosthetic ankle joint for walking and running
Grimmer, M., Holgate, M. A., Holgate, R., Boehler, A., Ward, J. A., Hollander, K. W., Sugar, T. G., & Andre Seyfarth, A. (2016) · BioMedical Engineering OnLine · doi:10.1186/s12938-016-0286-7 · Cited by 74 · see citing works
Translational Motion Tracking of Leg Joints for Enhanced Prediction of Walking Tasks
Stolyarov, R., Burnett, G., & Herr, H. (2017) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2017.2718528 · Cited by 66 · see citing works
Varol, H. A., Sup, F. C., & Goldfarb, M. T. (2008) · IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob) · doi:10.1109/biorob.2008.4762860 · Cited by 54 · see citing works
Feng, Y., & Wang, Q. (2017) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2017.2766205 · Cited by 54 · see citing works
Self-citationSpanias, J. A., Simon, A. M., Ingraham, K. A., & Hargrove, L. J. (2015) · International IEEE/EMBS Conference on Neural Engineering · doi:10.1109/ner.2015.7146704 · Cited by 46 · see citing works
Terrain identification for prosthetic knees based on electromyographic signal features
Jin, D., Yang, J., Zhang, R., Wang, R., & Zhang, J. (2006) · Tsinghua Science & Technology · doi:10.1016/s1007-0214(06)70157-2 · Cited by 46 · see citing works
Zheng, E., Chen, B., Wang, X., Huang, Y. Q., & Wang, Q. (2014) · International Journal of Advanced Robotic Systems · doi:10.5772/57788 · Cited by 31 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances
Zhang, S., Li, Y., Zhang, S., Shahabi, F., Xia, S., Deng, Y., & Alshurafa, N. (2022) · Sensors · doi:10.3390/s22041476 · Cited by 625 · see citing works
“A majority of the CNNs consist of 5 to 9 layers [67, 91, 193, 232, 272, 300, 313], [130], [96], usually including 2 to 3 convolutional layers, 2 to 3 max pooling layers, followed by 1 to 2 fully connected layers before feeding the feature representation into the output layer (softmax layer in most cases).”
Background
- Authors
- Feng, Y., Chen, W., & Wang, Q.
- Affiliations
- Peking University (CN)
- Corresponding author
- Wang, Qining
- Venue
- Advanced Robotics
- Publisher
- Informa UK Limited
- Published
- 2019-01-24
- Volume
- 33
- Issue
- 5
- Pages
- 254-263
- ISSN
- 0169-1864 (ISSN-L)
- 1568-5535
- OpenAlex
- W2912182936
- Cited by
- 28
- References
- 30
- Citations by year
- 2025: 2 · 2024: 4 · 2023: 7 · 2022: 7 · 2021: 3 · 2020: 4 · 2019: 1
- FWCI
- 1.32
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Advanced Robotics (publishedVersion)
- Funders
- National Natural Science Foundation of China (91648207)
- National Key R&D Program of China (2018YFF0300606, 18L2040)
- Beijing Municipal Science and Technology Project (Z181100009218007)
- National Program for Support of Top-notch Young Professionals
- Natural Science Foundation of Beijing Municipality
- Topics
- Physical Sciences › Engineering › Biomedical Engineering › Prosthetics and Rehabilitation Robotics
- Physical Sciences › Engineering › Biomedical Engineering › Muscle activation and electromyography studies
- Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
- Keywords
- locomotion mode recognition, transtibial amputees, convolutional neural networks
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
