Hand gesture recognition using sEMG with LSTM
DOI:
https://doi.org/10.5281/zenodo.17395000Ключевые слова:
LSTM, sEMG, hand gestures recognition, NinaPro-DB5, augmentationЛицензия
Аннотация
Using electromyography (EMG) signals has spread in many fields. LSTM networks is one of the most suitable methods for processing EMG because of their structure. In this work, two LSTM models were build, one layer (1L-LSTM) and multi-layers ML-LSTM. They were trained using Ninapro-DB5 dataset after augmenting it by averaging. Different input sizes were tested. 1L-LSTM and ML-LSTM scored an accuracy of 98.5% and 99.7% respectively. Moreover, they needed low testing time in the range of [60,240] mcs. In addition, the signal length was did not have much effect when using multi layers.
Скачивания
Библиографические ссылки
1. Bois-Reymond, E. D. Untersuchungen über thierische Elektricität bd., 2. abth. III. Untersuchung (Fortsetzung) 1860-84 / E. D. Bois-Reymond. – Berlin: G. reimer, 1884. – 579 p.
2. Alter, R. Bioelectric control of prosthesis : technical report 446 / R. Alter. – Massachusetts institute of technology, 1966. – 86 p.
3. Bottomley, A. H. Myo-electric control of powered prostheses / A. H. Bottomley // The Journal of Bone & Joint Surgery British Volume. – 1965. – V. 47, No. 3. – P. 411-415.
4. The effectiveness of EMG biofeedback in the treatment of arm function after stroke / J. L. Crow [et al.] // International disability studies. – 1989. – V. 11, No. 4. – P. 155-160.
5. Di Girolamo, M. ost-stroke rehabilitation of hand function based on electromyography biofeedback: Doctoral dissertation / M Di Girolamo. – Italia: Politecnico di Torino, 2018. – 116 p.
6. Detecting motor unit abnormalities in amyotrophic lateral sclerosis using high-density surface EMG / Yu. Nishikawa, A. Holobar, K. Watanabe [et al.] // Clinical Neurophysiology. – 2022. – Vol. 142. – P. 262-272. – DOI 10.1016/j.clinph.2022.06.016. – EDN MOJLXD.
7. Visser, L. H High-resolution sonography versus EMG in the diagnosis of carpal tunnel syndrome / L. H. Visser, M. H. Smidt, M. L. Lee // Journal of Neurology, Neurosurgery, and Psychiatry. – 2008. – Vol. 79, No. 1. – P. 63-67. – DOI 10.1136/JNNP.2007.115337.
8. Quadriceps Muscle Fatigue Reduces Extension and Flexion Power During Maximal Cycling / S. J. O'bryan, Ja. L. Taylor, J. M. D'amico, D. M. Rouffet // Frontiers in Sports and Active Living. – 2022. – Vol. 3. – DOI 10.3389/fspor.2021.797288. – EDN MAEJHT.
9. Evaluating the Ability of Congenital Upper Extremity Amputees to Control a Multi-Degree of Freedom Myoelectric Prosthesis / B. Kaluf, M. S. Gart, B. J. Loeffler, G. Gaston // The Journal of Hand Surgery. – 2022. – Vol. 47, No. 10. – P. 1019.e1-1019.e9. – DOI 10.1016/j.jhsa.2021.08.011. – EDN ACZMJE.
10. Interaction with a Hand Rehabilitation Exoskeleton in EMG-Driven Bilateral Therapy: Influence of Visual Biofeedback on the Users’ Performance / A. Cisnal, P. Gordaliza, Ja. Pérez Turiel, Ju. C. Fraile // Sensors. – 2023. – Vol. 23, No. 4. – P. 2048. – DOI 10.3390/s23042048. – EDN CYSEGQ.
11. Surface EMG vs. High-Density EMG: Tradeoff Between Performance and Usability for Head Orientation Prediction in VR Application / T. Sugiarto, Ch. L. Hsu, Ch. T. Sun [et al.] // IEEE Access. – 2021. – Vol. 9. – P. 45418-45427. – DOI 10.1109/access.2021.3067030. – EDN LJBNJY.
12. The effects of channel number on classification performance for sEMG-based speech recognition / X. Wang, M. Zhu, H. Cui [et al.] // Proc. IEEE EMBC. – 2020. – P. 3102-3105.
13. The use of cranial electromyography in athletes / A. Palermo, G. Cazzato, I. Trilli [et al.] // Oral and Implantology. – 2024. – Vol. 16, No. 3.1suppl. – P. 506-521. – DOI 10.11138/oi163.1suppl506-521. – EDN KRHSGE.
14. Electromyography, Wavelet Analysis and Muscle Co-Activation as Comprehensive Tools of Movement Pattern Assessment for Injury Prevention in Wheelchair Fencing / Z. Borysiuk, M. Błaszczyszyn, K. Piechota, W. J. Cynarski // Applied Sciences (Switzerland). – 2022. – Vol. 12, No. 5. – P. 2430. – DOI 10.3390/app12052430. – EDN RJDLUP.
15. EMG-Driven Machine Learning Control of a Soft Glove for Grasping Assistance and Rehabilitation / M. Sierotowicz, N. Lotti, L. Nell [et al.] // IEEE Robotics and Automation Letters. – 2022. – Vol. 7, No. 2. – P. 1566-1573. – DOI 10.1109/lra.2021.3140055. – EDN EBEPBD.
16. American Sign Language Translation Using Wearable Inertial and Electromyography Sensors for Tracking Hand Movements and Facial Expressions / Yu. Gu, Ch. Zheng, M. Todoh, F. Zha // Frontiers in Neuroscience. – 2022. – Vol. 16. – DOI 10.3389/fnins.2022.962141. – EDN XSUIEM.
17. Temporal Dilation of Deep LSTM for Agile Decoding of sEMG: Application in Prediction of Upper-Limb Motor Intention in NeuroRobotics / T. Sun, Q. Hu, P. Gulati, S. Farokh Atashzar // IEEE Robotics and Automation Letters. – 2021. – Vol. 6, No. 4. – P. 6212-6219. – DOI 10.1109/LRA.2021.3091698. – EDN INUTXP.
18. EMGHandNet: A hybrid CNN and Bi-LSTM architecture for hand activity classification using surface EMG signals / N. K. Karnam, A. C. Turlapaty, S. R. Dubey, B. Gokaraju // Biocybernetics and Biomedical Engineering. – 2022. – Vol. 42, No. 1. – P. 325-340. – DOI 10.1016/j.bbe.2022.02.005. – EDN FOWTST.
19. Gesture Recognition of sEMG Signals based on Deep Learning Framework / Ch. Yang, Ch. Zhang // WSEAS Transactions on Signal Processing. – 2024. – Vol. 20. – P. 78-84. – DOI 10.37394/232014.2024.20.9. – EDN JKZUIE.
20. MS-CLSTM: Myoelectric Manipulator Gesture Recognition Based on Multi-Scale Feature Fusion CNN-LSTM Network / Z. Wang, W. Huang, Z. Qi, Sh. Yin // Biomimetics. – 2024. – Vol. 9, No. 12. – P. 784. – DOI 10.3390/biomimetics9120784. – EDN OZKMXQ.
21. Enhanced EMG-based Gesture Recognition using Hybrid CNN-BiLSTM Architecture with Channel Attention / T. Kishore, S. S. Remabai, Ch. Retnaswamy, E. S. Paul // Biomedical and Pharmacology Journal. – 2025. – Vol. 18, No. December Spl Edition. – P. 315-329. – DOI 10.13005/bpj/3090. – EDN OLFBIQ.
22. Potekhin, V. V. Raspoznavanie zhestov ruk s ispolzovaniem SEMG s Xgboost i usrednenie dlia uvelicheniia / V. V. Potekhin, L. Assalama // Sistemnyi analiz v proektirovanii i upravlenii : Sbornik nauchnykh trudov XXVI Mezhdunarodnoi nauchno-prakticheskoi konferentsii. V 3-kh chastiakh, Sankt-Peterburg, 13–14 oktiabria 2022 goda. Tom Chast 2. – Sankt-Peterburg: Federalnoe gosudarstvennoe avtonomnoe obrazovatelnoe uchrezhdenie vysshego obrazovaniia Sankt-Peterburgskii politekhnicheskii universitet Petra Velikogo, 2023. – S. 74-88. – DOI 10.18720/SPBPU/2/id23-83. – EDN QRGNBC.
23. WaveFormer: A Lightweight Transformer Model for sEMG-based Gesture Recognition / Y. Chen, M. Orlandi, P. M. Rapa [et al.] // CoRR. – 2025. – V. Abs/2506.11168. – DOI 10.48550/arXiv.2506.11168.
24. A CNN-Transformer Hybrid Network for Hand Gesture Classification based on High-Density sEMG / M. Chen, Z. Li, H. Yang, Z. G. Hou // 2024 17th International Convention on Rehabilitation Engineering and Assistive Technology, i-CREATe 2024 and World Rehabilitation Robot Convention, WRRC 2024 - Proceedings. – 2024. – DOI 10.1109/I-CREATE62067.2024.10776082.
25. Transformer-based hand gesture recognition from instantaneous to fused neural decomposition of high-density EMG signals / M. Montazerin, E. Rahimian, F. Naderkhani [et al.] // Scientific Reports. – 2023. – Vol. 13, No. 1. – P. 11000. – DOI 10.1038/s41598-023-36490-w. – EDN HPPBQV.
26. Han, Y. Lower Limb Movement Recognition Based on a Hybrid Deep Learning Model Using Surface Electromyography / Y. Han, Q. Tao // IEEE Access. – 2025. – DOI 10.1109/ACCESS.2025.3571395.
СПИСОК ИСТОЧНИКОВ
1. Bois-Reymond, E. D. Untersuchungen über thierische Elektricität bd., 2. abth. III. Untersuchung (Fortsetzung) 1860-84 / E. D. Bois-Reymond. – Berlin: G. reimer, 1884. – 579 p.
2. Alter, R. Bioelectric control of prosthesis : technical report 446 / R. Alter. – Massachusetts institute of technology, 1966. – 86 p.
3. Bottomley, A. H. Myo-electric control of powered prostheses / A. H. Bottomley // The Journal of Bone & Joint Surgery British Volume. – 1965. – V. 47, No. 3. – P. 411-415.
4. The effectiveness of EMG biofeedback in the treatment of arm function after stroke / J. L. Crow [et al.] // International disability studies. – 1989. – V. 11, No. 4. – P. 155-160.
5. Di Girolamo, M. ost-stroke rehabilitation of hand function based on electromyography biofeedback: Doctoral dissertation / M Di Girolamo. – Italia: Politecnico di Torino, 2018. – 116 p.
6. Detecting motor unit abnormalities in amyotrophic lateral sclerosis using high-density surface EMG / Yu. Nishikawa, A. Holobar, K. Watanabe [et al.] // Clinical Neurophysiology. – 2022. – Vol. 142. – P. 262-272. – DOI 10.1016/j.clinph.2022.06.016. – EDN MOJLXD.
7. Visser, L. H High-resolution sonography versus EMG in the diagnosis of carpal tunnel syndrome / L. H. Visser, M. H. Smidt, M. L. Lee // Journal of Neurology, Neurosurgery, and Psychiatry. – 2008. – Vol. 79, No. 1. – P. 63-67. – DOI 10.1136/JNNP.2007.115337.
8. Quadriceps Muscle Fatigue Reduces Extension and Flexion Power During Maximal Cycling / S. J. O'bryan, Ja. L. Taylor, J. M. D'amico, D. M. Rouffet // Frontiers in Sports and Active Living. – 2022. – Vol. 3. – DOI 10.3389/fspor.2021.797288. – EDN MAEJHT.
9. Evaluating the Ability of Congenital Upper Extremity Amputees to Control a Multi-Degree of Freedom Myoelectric Prosthesis / B. Kaluf, M. S. Gart, B. J. Loeffler, G. Gaston // The Journal of Hand Surgery. – 2022. – Vol. 47, No. 10. – P. 1019.e1-1019.e9. – DOI 10.1016/j.jhsa.2021.08.011. – EDN ACZMJE.
10. Interaction with a Hand Rehabilitation Exoskeleton in EMG-Driven Bilateral Therapy: Influence of Visual Biofeedback on the Users’ Performance / A. Cisnal, P. Gordaliza, Ja. Pérez Turiel, Ju. C. Fraile // Sensors. – 2023. – Vol. 23, No. 4. – P. 2048. – DOI 10.3390/s23042048. – EDN CYSEGQ.
11. Surface EMG vs. High-Density EMG: Tradeoff Between Performance and Usability for Head Orientation Prediction in VR Application / T. Sugiarto, Ch. L. Hsu, Ch. T. Sun [et al.] // IEEE Access. – 2021. – Vol. 9. – P. 45418-45427. – DOI 10.1109/access.2021.3067030. – EDN LJBNJY.
12. The effects of channel number on classification performance for sEMG-based speech recognition / X. Wang, M. Zhu, H. Cui [et al.] // Proc. IEEE EMBC. – 2020. – P. 3102-3105.
13. The use of cranial electromyography in athletes / A. Palermo, G. Cazzato, I. Trilli [et al.] // Oral and Implantology. – 2024. – Vol. 16, No. 3.1suppl. – P. 506-521. – DOI 10.11138/oi163.1suppl506-521. – EDN KRHSGE.
14. Electromyography, Wavelet Analysis and Muscle Co-Activation as Comprehensive Tools of Movement Pattern Assessment for Injury Prevention in Wheelchair Fencing / Z. Borysiuk, M. Błaszczyszyn, K. Piechota, W. J. Cynarski // Applied Sciences (Switzerland). – 2022. – Vol. 12, No. 5. – P. 2430. – DOI 10.3390/app12052430. – EDN RJDLUP.
15. EMG-Driven Machine Learning Control of a Soft Glove for Grasping Assistance and Rehabilitation / M. Sierotowicz, N. Lotti, L. Nell [et al.] // IEEE Robotics and Automation Letters. – 2022. – Vol. 7, No. 2. – P. 1566-1573. – DOI 10.1109/lra.2021.3140055. – EDN EBEPBD.
16. American Sign Language Translation Using Wearable Inertial and Electromyography Sensors for Tracking Hand Movements and Facial Expressions / Yu. Gu, Ch. Zheng, M. Todoh, F. Zha // Frontiers in Neuroscience. – 2022. – Vol. 16. – DOI 10.3389/fnins.2022.962141. – EDN XSUIEM.
17. Temporal Dilation of Deep LSTM for Agile Decoding of sEMG: Application in Prediction of Upper-Limb Motor Intention in NeuroRobotics / T. Sun, Q. Hu, P. Gulati, S. Farokh Atashzar // IEEE Robotics and Automation Letters. – 2021. – Vol. 6, No. 4. – P. 6212-6219. – DOI 10.1109/LRA.2021.3091698. – EDN INUTXP.
18. EMGHandNet: A hybrid CNN and Bi-LSTM architecture for hand activity classification using surface EMG signals / N. K. Karnam, A. C. Turlapaty, S. R. Dubey, B. Gokaraju // Biocybernetics and Biomedical Engineering. – 2022. – Vol. 42, No. 1. – P. 325-340. – DOI 10.1016/j.bbe.2022.02.005. – EDN FOWTST.
19. Gesture Recognition of sEMG Signals based on Deep Learning Framework / Ch. Yang, Ch. Zhang // WSEAS Transactions on Signal Processing. – 2024. – Vol. 20. – P. 78-84. – DOI 10.37394/232014.2024.20.9. – EDN JKZUIE.
20. MS-CLSTM: Myoelectric Manipulator Gesture Recognition Based on Multi-Scale Feature Fusion CNN-LSTM Network / Z. Wang, W. Huang, Z. Qi, Sh. Yin // Biomimetics. – 2024. – Vol. 9, No. 12. – P. 784. – DOI 10.3390/biomimetics9120784. – EDN OZKMXQ.
21. Enhanced EMG-based Gesture Recognition using Hybrid CNN-BiLSTM Architecture with Channel Attention / T. Kishore, S. S. Remabai, Ch. Retnaswamy, E. S. Paul // Biomedical and Pharmacology Journal. – 2025. – Vol. 18, No. December Spl Edition. – P. 315-329. – DOI 10.13005/bpj/3090. – EDN OLFBIQ.
22. Потехин, В. В. Распознавание жестов рук с использованием SEMG с Xgboost и усреднение для увеличения / В. В. Потехин, Л. Ассалама // Системный анализ в проектировании и управлении : Сборник научных трудов XXVI Международной научно-практической конференции. В 3-х частях, Санкт-Петербург, 13–14 октября 2022 года. Том Часть 2. – Санкт-Петербург: Федеральное государственное автономное образовательное учреждение высшего образования "Санкт-Петербургский политехнический университет Петра Великого", 2023. – С. 74-88. – DOI 10.18720/SPBPU/2/id23-83. – EDN QRGNBC.
23. WaveFormer: A Lightweight Transformer Model for sEMG-based Gesture Recognition / Y. Chen, M. Orlandi, P. M. Rapa [et al.] // CoRR. – 2025. – V. Abs/2506.11168. – DOI 10.48550/arXiv.2506.11168.
24. A CNN-Transformer Hybrid Network for Hand Gesture Classification based on High-Density sEMG / M. Chen, Z. Li, H. Yang, Z. G. Hou // 2024 17th International Convention on Rehabilitation Engineering and Assistive Technology, i-CREATe 2024 and World Rehabilitation Robot Convention, WRRC 2024 - Proceedings. – 2024. – DOI 10.1109/I-CREATE62067.2024.10776082.
25. Transformer-based hand gesture recognition from instantaneous to fused neural decomposition of high-density EMG signals / M. Montazerin, E. Rahimian, F. Naderkhani [et al.] // Scientific Reports. – 2023. – Vol. 13, No. 1. – P. 11000. – DOI 10.1038/s41598-023-36490-w. – EDN HPPBQV.
26. Han, Y. Lower Limb Movement Recognition Based on a Hybrid Deep Learning Model Using Surface Electromyography / Y. Han, Q. Tao // IEEE Access. – 2025. – DOI 10.1109/ACCESS.2025.3571395.
Загрузки
Опубликован
Выпуск
Раздел
Лицензия
Это произведение доступно по лицензии Creative Commons «Attribution-NonCommercial» («Атрибуция — Некоммерческое использование») 4.0 Всемирная.
Статьи журнала «Вестник Донецкого университета. Серия 04. Технические науки» находятся в открытом доступе и распространяются в соответствии с условиями Лицензионного Договора с Донецким Государственным университетом, который бесплатно предоставляет авторам неограниченное распространение и самостоятельное архивирование.
