Stable Responsive EMG Sequence Prediction and Adaptive Reinforcement With Temporal Convolutional Networks
Open accessThe DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.
Abstract
Prediction of movement intentions from electromyographic (EMG) signals is typically performed with a pattern recognition approach, wherein a short dataframe of raw EMG is compressed into an instantaneous feature-encoding that is meaningful for classification. However, EMG signals are time-varying, implying that a frame-wise approach may not sufficiently incorporate temporal context into predictions, leading to erratic and unstable prediction behavior. OBJECTIVE: We demonstrate that sequential prediction models and, specifically, temporal convolutional networks are able to leverage useful temporal information from EMG to achieve superior predictive performance. METHODS: We compare this approach to other sequential and frame-wise models predicting 3 simultaneous hand and wrist degrees-of-freedom from 2 amputee and 13 non-amputee human subjects in a minimally constrained experiment. We also compare these models on the publicly available Ninapro and CapgMyo amputee and non-amputee datasets. RESULTS: Temporal convolutional networks yield predictions that are more accurate and stable than frame-wise models, especially during inter-class transitions, with an average response delay of 4.6 ms and simpler feature-encoding. Their performance can be further improved with adaptive reinforcement training. SIGNIFICANCE: Sequential models that incorporate temporal information from EMG achieve superior movement prediction performance and these models allow for novel types of interactive training. CONCLUSIONS: Addressing EMG decoding as a sequential modeling problem will lead to enhancements in the reliability, responsiveness, and movement complexity available from prosthesis control systems.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
“Representative algorithms such as LSTM and TCN typically achieve realtime prediction latency below 150-250 ms, while lightweight ML models (e.g., LDA, SVM) often operate below 50 ms with low computational demand 134 .”
From Recent advances in intelligent wearable systems: from multiscale biomechanical features towards human motion intent prediction (2026) · cites this paper as [134]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
SMOTE synthetic minority over-sampling technique
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002) · Journal of Artificial Intelligence Research · doi:10.1613/jair.953 · Cited by 32,865
Classification and Regression Trees.
Gordon, A. D., Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (1984) · Biometrics · doi:10.2307/2530946 · Cited by 23,522
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2644615 · Cited by 19,631
Nearest neighbor pattern classification
Cover, T., & Hart, P. (1967) · IEEE Transactions on Information Theory · doi:10.1109/tit.1967.1053964 · Cited by 16,936
Binary Codes capable of currecting deletions, insertions, and reversals
Levenshtein, V. I. (1965) · Soviet physics. Doklady · Cited by 14,803
Use of Ranks in One-Criterion Variance Analysis
Kruskal, W. H., & Wallis, W. A. (1952) · Journal of the American Statistical Association · doi:10.1080/01621459.1952.10483441 · Cited by 13,912 · cited 1×
“Performance distributions were not assumed to be Gaussian; therefore, all statistical p -values were computed with Kruskall-Wallis one-way variance analysis [44].”
MethodClassification and regression trees
Praagman, J. (1985) · European Journal of Operational Research · doi:10.1016/0377-2217(85)90321-2 · Cited by 10,053
Framewise phoneme classification with bidirectional LSTM and other neural network architectures
Graves, A., & Schmidhuber, J. (2005) · Neural Networks · doi:10.1016/j.neunet.2005.06.042 · Cited by 5,839
An introduction to hidden Markov models
Rabiner, L., & Juang, B. (1986) · IEEE ASSP Magazine · doi:10.1109/massp.1986.1165342 · Cited by 4,775
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
Bai, S., Kolter, J. Z., & Koltun, V. (2018) · arXiv · doi:10.48550/arxiv.1803.01271 · Cited by 4,655
Individual Choice Behavior: A Theoretical Analysis.
Cane, V., & Luce, R. D. (1960) · Journal of the Royal Statistical Society. Series A (General) · doi:10.2307/2343282 · Cited by 2,504
Use of Ranks in One-Criterion Variance Analysis
Kruskal, W., & Wallis, W. A. (1952) · Journal of the American Statistical Association · doi:10.2307/2280779 · Cited by 2,455
Temporal Convolutional Networks for Action Segmentation and Detection
Lea, C., Flynn, M. D., Vidal, R., Reiter, A., & Hager, G. D. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.113 · Cited by 2,238 · cited 5×
“Single-layer TCNs can learn hidden temporal patterns [24], smoothed via temporal-dimension convolution filters, and have demonstrated superior results on video recognition datasets [24], [26], [27] and our own prior work in EMG decoding [23].”
BackgroundMethodResultInfluentialA new strategy for multifunction myoelectric control
Hudgins, B., Parker, P., & Scott, R. N. (1993) · IEEE Transactions on Biomedical Engineering · doi:10.1109/10.204774 · Cited by 2,149 · cited 4×
“T HE fundamental objective of myoelectric prosthesis control for upper-limb amputees is to determine a user’s intended arm and hand movement actions from the corresponding electromyographic (EMG) muscle activation signals [1].”
BackgroundMethodInfluentialA robust, real-time control scheme for multifunction myoelectric control
Englehart, K., & Hudgins, B. (2003) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2003.813539 · Cited by 1,743
Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit
Hahnloser, R. H. R., Sarpeshkar, R., Mahowald, M. A., Douglas, R. J., & Seung, H. S. (2000) · Nature · doi:10.1038/35016072 · Cited by 1,293
Individual choice behavior: A theoretical analysis.
Luce, R. D. (2005) · doi:10.1037/14396-000 · Cited by 1,157 · cited 1×
“The final decoder output is fed to a fullyconnected time-distributed layer with softmax activation [30] to produce C class probabilities, ŷt , at each time, t:”
MethodElectromyography data for non-invasive naturally-controlled robotic hand prostheses
Atzori, M., Gijsberts, A., Castellini, C., Caputo, B., Hager, A.-G. M., Elsig, S., Giatsidis, G., Bassetto, F., & Müller, H. (2014) · Scientific Data · doi:10.1038/sdata.2014.53 · Cited by 969
Improving support vector machine classifiers by modifying kernel functions
Amari, S., & Wu, S. (1999) · Neural Networks · doi:10.1016/s0893-6080(99)00032-5 · Cited by 936
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks
Kim, T. S., & Reiter, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.207 · Cited by 691
Atzori, M., Cognolato, M., & Müller, H. (2016) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2016.00009 · Cited by 684 · cited 1×
“In ideal cases, such as during steady-state muscle contractions, prediction models like linear discriminant analysis [2], support vector machines [3], and spatial convolutional networks [4] can reliably decode many movement class patterns from EMG feature representations [5].”
BackgroundNeural Manifolds for the Control of Movement
Gallego, J. A., Perich, M. G., Miller, L. E., & Solla, S. A. (2017) · Neuron · doi:10.1016/j.neuron.2017.05.025 · Cited by 674
Gesture recognition by instantaneous surface EMG images
Geng, W., Du, Y., Jin, W., Wei, W., Hu, Y., & Li, J. (2016) · Scientific Reports · doi:10.1038/srep36571 · Cited by 595
Smith, L. H., Hargrove, L. J., Lock, B. A., & Kuiken, T. A. (2011) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2010.2100828 · Cited by 443
The optimal controller delay for myoelectric prostheses
Farrell, T. R., & Weir, R. F. (2007) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2007.891391 · Cited by 438
Comparison of six electromyography acquisition setups on hand movement classification tasks
Pizzolato, S., Tagliapietra, L., Cognolato, M., Reggiani, M., Müller, H., & Atzori, M. (2017) · PLOS ONE · doi:10.1371/journal.pone.0186132 · Cited by 421
Continuous Myoelectric Control for Powered Prostheses Using Hidden Markov Models
Chan, A. D. C., & Englehart, K. B. (2005) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2004.836492 · Cited by 343
Segmental Spatiotemporal CNNs for Fine-Grained Action Segmentation
Lea, C., Reiter, A., Vidal, R., & Hager, G. D. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46487-9_3 · Cited by 246 · cited 6×
“Single-layer TCNs can learn hidden temporal patterns [24], smoothed via temporal-dimension convolution filters, and have demonstrated superior results on video recognition datasets [24], [26], [27] and our own prior work in EMG decoding [23].”
BackgroundResultInfluentialXia, P., Hu, J., & Peng, Y. (2018) · Artificial Organs · doi:10.1111/aor.13004 · Cited by 224
Self-Correcting Pattern Recognition System of Surface EMG Signals for Upper Limb Prosthesis Control
Amsuss, S., Goebel, P. M., Jiang, N., Graimann, B., Paredes, L., & Farina, D. (2014) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2013.2296274 · Cited by 202
Selective Classification for Improved Robustness of Myoelectric Control Under Nonideal Conditions
Scheme, E. J., Englehart, K. B., & Hudgins, B. S. (2011) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2011.2113182 · Cited by 172
Lorrain, T., Jiang, N., & Farina, D. (2011) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/1743-0003-8-25 · Cited by 165
Confidence-Based Rejection for Improved Pattern Recognition Myoelectric Control
Scheme, E. J., Hudgins, B. S., & Englehart, K. B. (2013) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2013.2238939 · Cited by 136
Simon, A. M., Hargrove, L. J., Lock, B. A., & Kuiken, T. A. (2011) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2011.2155063 · Cited by 120
Betthauser, J., Hunt, C. L., Osborn, L. E., Masters, M. R., Lévay, G., Kaliki, R. R., & Thakor, N. V. (2017) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2017.2719400 · Cited by 110
Self-citationLearning convolutional action primitives for fine-grained action recognition
Lea, C., Vidal, R., & Hager, G. D. (2016) · 2016 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2016.7487305 · Cited by 106
Ortiz-Catalan, M., Rouhani, F., Branemark, R., & Hakansson, B. (2015) · 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2015.7318567 · Cited by 89
Robertson, J. W., Englehart, K. B., & Scheme, E. (2018) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2018.2878907 · Cited by 69
Classification of Transient Myoelectric Signals for the Control of Multi-Grasp Hand Prostheses
Kanitz, G., Cipriani, C., & Edin, B. B. (2018) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2018.2861465 · Cited by 65
DYNAMIC HAND MOTION RECOGNITION BASED ON TRANSIENT AND STEADY-STATE EMG SIGNALS
Yang, D., Zhao, J., Jiang, L., & Liu, H. (2012) · International Journal of Humanoid Robotics · doi:10.1142/s0219843612500077 · Cited by 62
Pattern classification of time-series EMG signals using neural networks
Tsuji, T., Fukuda, O., Kaneko, M., et al. (2000) · International Journal of Adaptive Control and Signal Processing · doi:10.1002/1099-1115(200012)14:8<829::aid-acs623>3.0.co;2-l · Cited by 58
Cascaded Adaptation Framework for Fast Calibration of Myoelectric Control
Zhu, X., Liu, J., Zhang, D., Sheng, X., & Jiang, N. (2016) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2016.2562180 · Cited by 51
Betthauser, J. L., Krall, J. T., Kaliki, R. R., Fifer, M. S., & Thakor, N. V. (2019) · International IEEE/EMBS Conference on Neural Engineering · doi:10.1109/ner.2019.8717169 · Cited by 36
Self-citationEVALUATION OF CLASSIFIERS PERFORMANCE USING THE MYO ARMBAND
Mendez, I. G., Pálsdóttir, Á. A., Eiríksdóttir, D. H., et al. (2017) · VBN Forskningsportal (Aalborg Universitet) · Cited by 3
Research works printed but not linked: 1
- ravitz, 2013, Revolutionizing prosthetics–Phase 3, Johns Hopkins APL Tech Dig, 31, 366
Cited by
Leveraging High-Density EMG to Investigate Bipolar Electrode Placement for Gait Prediction Models
Hodossy, B. K., Guez, A. S., Jing, S., Huo, W., Vaidyanathan, R., & Farina, D. (2024) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2024.3371099 · Cited by 10
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
Metadata
- Authors
- Betthauser, J. L., Krall, J. T., Bannowsky, S. G., Levay, G., Kaliki, R. R., Fifer, M. S., & Thakor, N. V.
- Affiliations
- Johns Hopkins University (US)
- Infinite Biomedical Technologies (United States) (US)
- Venue
- IEEE Transactions on Biomedical Engineering
- Published
- 2020-06
- Volume
- 67
- Issue
- 6
- Pages
- 1707-1717
- ISSN
- 0018-9294 (ISSN-L)
- 1558-2531
- PMC
- PMC10497232
- OpenAlex
- W2977057839
- Cited by
- 73
- References
- 46
- Citations by year
- 2026: 4 · 2025: 18 · 2024: 9 · 2023: 13 · 2022: 14 · 2021: 13 · 2020: 2
- FWCI
- 2.55
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Licence
- Locations
- IEEE Transactions on Biomedical Engineering (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- Funders
- Johns Hopkins University Applied Physics Laboratory Graduate Research Fellowship
- Topics
- Physical Sciences › Engineering › Biomedical Engineering › Muscle activation and electromyography studies
- Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
- Life Sciences › Neuroscience › Cellular and Molecular Neuroscience › Neuroscience and Neural Engineering
- Keywords
- electromyography, temporal convolutional network, adaptive reinforcement learning, response latency, Ninapro dataset, temporal context
- MeSH terms
- Amputees, Artificial Limbs, Electromyography, Hand, Humans, Movement, Reproducibility of Results
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
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.