Multi-dataset benchmarking and preliminary transfer learning for lower-limb EMG classification toward adaptive prosthesis control.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος:	Multi-dataset benchmarking and preliminary transfer learning for lower-limb EMG classification toward adaptive prosthesis control.
Συγγραφείς:	Jafar J; Faculty of Power and Aeronautical Engineering, Institute of Aeronautics and Applied Mechanics, Warsaw University of Technology, Nowowiejska 24, 00-665 Warsaw, Poland., Rzymkowski C; Faculty of Power and Aeronautical Engineering, Institute of Aeronautics and Applied Mechanics, Warsaw University of Technology, Nowowiejska 24, 00-665 Warsaw, Poland.; Centre of Excellence for Health Technologies (HealthTEC), Warsaw University of Technology, Pl. Politechniki 1, 00-661 Warsaw, Poland., Kordecki A; Faculty of Power and Aeronautical Engineering, Institute of Aeronautics and Applied Mechanics, Warsaw University of Technology, Nowowiejska 24, 00-665 Warsaw, Poland.
Πηγή:	Acta of bioengineering and biomechanics [Acta Bioeng Biomech] 2026 Oct 16; Vol. 28 (2), pp. 109-120. Date of Electronic Publication: 2026 Oct 16 (Print Publication: 2026).
Τύπος έκδοσης:	Journal Article
Γλώσσα:	English
Στοιχεία περιοδικού:	Publisher: Sciendo Country of Publication: Poland NLM ID: 101194794 Publication Model: eCollection Cited Medium: Internet ISSN: 2450-6303 (Electronic) Linking ISSN: 1509409X NLM ISO Abbreviation: Acta Bioeng Biomech Subsets: MEDLINE
Imprint Name(s):	Publication: 2023- : Warsaw, Poland : Sciendo Original Publication: Wrocław : Oficyna Wydawnicza Politechniki Wrocławskiej, 1999-
Ιατρικοί όροι (MeSH):	Lower Extremity/physiology , Electromyography , Benchmarking* , Artificial Limbs* , Databases, Factual*, Humans ; Multilayer Perceptrons ; Male ; Random Forest ; Adult ; Classification Algorithms
Περίληψη:	Purpose: Reliable decoding of lower-limb motor intent from surface electromyography signals remains challenging due to electrode placement variability, muscle fatigue, inter-subject differences, and differences between able-bodied and amputee populations. This study evaluates the robustness of commonly used machine-learning approaches for lower-limb electromyography classification under these sources of variability. Methods: A unified benchmarking analysis was conducted across four lower-limb electromyography datasets: UCI lower limb electromyography, vastus medialis electromyography, K2MUSE, and the above-knee sit-to-stand (STS) amputee dataset. Three classification models - support vector machine, random forest, and multilayer perceptron - were evaluated using standardized preprocessing and feature extraction pipelines. Cross-subject robustness was assessed using leave-one-subject-out (LOSO) validation on the K2MUSE dataset. A preliminary transfer-learning experiment was also performed by fine-tuning a multilayer perceptron pretrained on able-bodied data using the amputee STS dataset. Results: The random forest model achieved the highest performance in datasets with lower variability, with macro F1 scores of 0.9033 ± 0.0048 on the UCI dataset and 0.6000 ± 0.0087 on the vastus dataset. Under cross-subject non-ideal acquisition conditions, performance decreased for all models. The multilayer perceptron showed competitive robustness in the K2MUSE ideal-versus-fatigue LOSO evaluation (0.476 ± 0.058 macro-F1), while random forest showed the most compact subject-wise distribution (median 0.476 [interquartile range 0.049]). In the transfer-learning experiment, fine-tuning improved performance on the above-knee STS dataset relative to training from scratch (macro-F1 0.5540 ± 0.0141 vs. 0.5203 ± 0.0371). Conclusions: These results highlight the different strengths of classical and neural machine-learning models under varying electromyography variability conditions and provide a foundation for more robust intention-decoding systems for adaptive lower-limb prosthetic control. (© 2026 Jafar Jafar et al., published by Wroclaw University of Science and Technology.)
References:	Ziegler-Graham, K., MacKenzie, E.J., Ephraim, P.L., Travison, T.G., Brookmeyer, R., Estimating the prevalence of limb loss in the United States: 2005 to 2050, Arch. Phys. Med. Rehabil., 2008, 89(3): 422–429, 10.1016/j.apmr.2007.11.005 . (PMID: 10.1016/j.apmr.2007.11.005) Highsmith, M.J., Kahle, J.T., Bongiorni, D.R., Sutton, B.S., Groer, S., Kaufman, K.R., Safety, energy efficiency, and cost efficacy of the C-Leg for transfemoral amputees: a review of the literature, Prosthet. Orthot. Int., 2010, 34(4): 362–377, 10.3109/03093646.2010.520054 . (PMID: 10.3109/03093646.2010.520054) De Luca, C.J., Surface electromyography: detection and recording, Delsys. Inc., 2002, 10(2): 1–10. Farina, D., Jiang, N., Rehbaum, H., Holobar, A., Graimann, B., Dietl, H., Aszmann, O.C., The extraction of neural information from the surface EMG for the control of upper-limb prostheses: emerging avenues and challenges, IEEE Trans. Neural. Syst. Rehabil. Eng., 2014, 22(4): 797–809, 10.1109/TNSRE.2014.2305111 . (PMID: 10.1109/TNSRE.2014.2305111) Clancy, E.A., Morin, E.L., Merletti, R., Sampling, noise-reduction and amplitude estimation issues in surface electromyography, J. Electromyogr. Kinesiol., 2002, 12(1): 1–16, 10.1016/S1050-6411(01)00033-5 . (PMID: 10.1016/S1050-6411(01)00033-5) Huang, H., Zhang, F., Hargrove, L.J., Dou, Z., Rogers, D.R., Englehart, K.B., Continuous locomotion-mode identification for prosthetic legs based on neuromuscular–mechanical fusion, IEEE Trans. Biomed. Eng, 2011, 58(10): 2867–2875, 10.1109/TBME.2011.2161671 . (PMID: 10.1109/TBME.2011.2161671) Scheme, E., Englehart, K., Electromyogram pattern recognition for control of powered upper-limb prostheses: state of the art and challenges for clinical use, J. Rehabil. Res. Dev., 2011, 48(6): 643–660, 10.1682/JRRD.2010.09.0177 . (PMID: 10.1682/JRRD.2010.09.0177) Young, A.J., Hargrove, L.J., Kuiken, T.A., The effects of electrode size and orientation on the sensitivity of myoelectric pattern recognition systems to electrode shift, IEEE Trans. Biomed. Eng., 2011, 58(9): 2537–2544, 10.1109/TBME.2011.2159216 . (PMID: 10.1109/TBME.2011.2159216) Cimolato, A., Driessen, J.J.M., Mattos, L.S., De Momi, E., Laffranchi, M., De Michieli, L., EMG-driven control in lower limb prostheses: a topic-based systematic review, J. Neuroeng. Rehabil., 2022, 19(1): 43. https://doi.org/10.1186/s12984-022-01019-1 . (PMID: 10.1186/s12984-022-01019-1) Ahkami, B., Ahmed, K., Thesleff, A., Hargrove, L., Ortiz-Catalan, M., Electromyography-based control of lower limb prostheses: a systematic review, IEEE Trans. Med. Robot. Bionics., 2023, 5(3): 547–562. https://doi.org/10.1109/TMRB.2023.3282325 . (PMID: 10.1109/TMRB.2023.3282325) Le, D., Cheng, S., Gregg, R.D., Ghaffari, M., Transfer learning for efficient intent prediction in lower-limb prosthetics: a strategy for limited datasets, IEEE Robot. Autom. Lett., 2024, 9(5): 4321–4328. https://doi.org/10.1109/LRA.2024.3379800 . (PMID: 10.1109/LRA.2024.3379800) He, J., Zhang, D., Jiang, N., Sheng, X., Farina, D., Zhu, X., User adaptation in long-term, open-loop myoelectric training: implications for EMG pattern recognition in prosthesis control, J. Neural. Eng., 2015, 12(4): 046005, 10.1088/1741-2560/12/4/046005 . (PMID: 10.1088/1741-2560/12/4/046005) Atzori, M., Cognolato, M., Müller, H., Deep learning with convolutional neural networks applied to electromyography data: a resource for the classification of movements for prosthetic hands, Front. Neurorobot., 2016, 10: 9, 10.3389/fnbot.2016.00009 . (PMID: 10.3389/fnbot.2016.00009) Chen, X., Zhang, D., Zhu, X., Application of a self-enhancing classification method to electromyography pattern recognition for multifunctional prosthesis control, J. Neuroeng. Rehabil., 2013, 10: 44. https://doi.org/10.1186/1743-0003-10-44 . (PMID: 10.1186/1743-0003-10-44) Côté-Allard, U., Fall, C.L., Drouin, A., Campeau-Lecours, A., Gosselin, C., Laviolette, F., et al., Deep learning for electromyographic hand gesture signal classification using transfer learning, IEEE Trans. Neural. Syst. Rehabil. Eng., 2019, 27(4): 760–771, 10.1109/TNSRE.2019.2896269 . (PMID: 10.1109/TNSRE.2019.2896269) Weiss, K., Khoshgoftaar, T.M., Wang, D., A survey of transfer learning, J. Big. Data., 2016, 3(1): 1–40, 10.1186/s40537-016-0043-6. (PMID: 10.1186/s40537-016-0043-6) Du, Y., Jin, W., Wei, W., Hu, Y., Geng, W., Surface EMG-based inter-session gesture recognition enhanced by deep domain adaptation, Sensors, 2017, 17(3): 458, 10.3390/s17030458 . (PMID: 10.3390/s17030458) Ameri, A., Akhaee, M.A., Scheme, E., Englehart, K., Regression convolutional neural network for improved simultaneous EMG control, J. Neural. Eng., 2019, 16(3): 036015, 10.1088/1741-2552/ab0e2e . (PMID: 10.1088/1741-2552/ab0e2e) Sanchez, O., Sotelo, J., EMG dataset in lower limb, UCI Machine Learning Repository, 2014. https://archive.ics.uci.edu/dataset/278/emg + dataset + in + lower + limb . [Accessed 2025]. Zhang, Y., Original EMG datasets, PLoS One, 2017. https://figshare.com/articles/dataset/Extracting_time-frequency_feature_of_single-channel_vastus_medialis_EMG_signals_for_knee_exercise_pattern_recognition/5191081? file = 8865790 . [Accessed 2025]. Li, J., Zhang, B., Tan, X., Chen, W., Liu, Z., Zhang, J., et al., K2MUSE: A human lower limb multimodal dataset, Kaggle Dataset, 2025. https://www.kaggle.com/datasets/98d67c253a7c820668aed0690cae20343481b8f8f8e0dafbe93b0c76d91f0ce6 . [Accessed 2025]. Hunt, G., Foreman, K.B., Lenzi, T., Gabert, L., Hansen, C., Transfemoral amputees stand-up and sit-down with their prescribed microprocessor prostheses, Figshare Dataset, 2024. https://figshare.com/articles/dataset/Transfemoral_amputees_stand-up_and_sit-down_with_their_prescribed_microprocessor_prosthesis_Full-body_motion_capture_and_intact-side_lower_limb_EMGs/26282872 . [Accessed 2025]. Jiang, X., Ma, C., Nazarpour, K., Posture-invariant myoelectric control with self-calibrating random forests, Front Neurorobot., 2024, 18: 1462023. https://doi.org/10.3389/fnbot.2024.1462023 . (PMID: 10.3389/fnbot.2024.1462023) Tanaka, T., Nambu, I., Wada, Y., Mitigating the impact of electrode shift on classification performance in electromyography applications using sliding-window normalization, Sensors, 2025, 25: 4119. https://doi.org/10.3390/s25134119 . (PMID: 10.3390/s25134119)
Contributed Indexing:	Keywords: Gait analysis; Lower-limb biomechanics; Neuromuscular control; Prosthesis control; Surface electromyography; Transfer learning
Entry Date(s):	Date Created: 20261017 Date Completed: 20261017 Latest Revision: 20261017
Update Code:	20261018
DOI:	10.37190/abb/221221
PMID:	42891512
Βάση Δεδομένων:	MEDLINE

Full Text Finder

Περιγραφή
ISSN:	2450-6303
DOI:	10.37190/abb/221221