Artificial Intelligence-based Muscle Motor Control and Recuperation using Surface Electromyography (sEMG): A Review on Datasets, Methods, Applications, and Future Directions

Dilliraj Ekambaram¹, Vijayakumar Ponnusamy¹, Emilija Kisić²

¹ Department of Electronics and Communication Engineering, SRM Institute of Science and Technology, Kattankulathur – 603203, Tamil Nadu, India.

² Faculty of Information Technology, Belgrade Metropolitan University. Serbia

de0642@srmist.edu.in

vijayakp@srmist.edu.in

emilija.kisic@metropolitan.ac.rs

DOI:  10.46793/BISEC25.358

ABSTRACT: Advancements in human-machine interaction are enabling prosthetic hand control for people with physical disabilities, achieved through surface electromyography (sEMG). The sEMG is an emerging, non-invasive, and versatile technique for recuperation and prosthetic applications. For classifying both discrete and continuous muscle movements on the human body, carried through advanced non-invasive sensors, high-density sEMG (HD-sEMG), and Artificial Intelligence (AI) learning models. The combination of sensors with AI models enables the recognition of precise hand gestures and body postures by extracting key signal features for muscle motor activities through the placement of electrodes on the skin surface. This systematic review outlines English-language articles from 2020 to 2025, focusing on the process of signal acquisition and processing for deep learning or machine learning models, in line with time and frequency methods for decomposing motor units. Surveyed challenges in the real-world applications, such as healthcare, artificial replacement of body parts, and sports medicine. To highlight the need for reproducibility and analyze the performance of various AI models, we discussed the open-source datasets and toolboxes used for software development with standardized benchmark datasets. Experimental challenges related to sEMG hardware, including electrode displacement on the skin surface, inter-individual variability, and cross-talk, were discussed. Ultimately, the pathway for future directions in the development of AI-based sEMG models, with a focus on explainable AI, multimodal systems, and diverse federated data, aims to bridge the gap between laboratory research and clinical impact

KEYWORDS: Surface Electromyography, Gesture Analysis, Prosthetic Control, Artificial Intelligence, Gait Analysis, Signal Processing

REFERENCES:

[1]        Poppler, L.H., Mackinnon, S.E. (2019). The Role of the Peripheral Nerve Surgeon in the Treatment of Pain. Neurotherapeutics 16, 9–25  https://doi.org/10.1007/s13311-018-00695-z.

[2]        Mathew, Franz, C.K. and Berger, M.J. (2024). Neuromuscular consequences of spinal cord injury: New mechanistic insights and clinical considerations. Muscle & nerve. doi:https://doi.org/10.1002/mus.28070.

[3]        Zhou, J., Xie, S., Xu, S., Zhang, Y., Li, Y., Sun, Q., Zhang, J. and Zhao, T. (2024). From Pain to Progress: Comprehensive Analysis of Musculoskeletal Disorders Worldwide. Journal of Pain Research, Volume 17, pp.3455–3472. doi:https://doi.org/10.2147/jpr.s488133.

[4]        Gill, T.K., Manasi Murthy Mittinty, March, L., Steinmetz, J.D., Culbreth, G.T., Cross, M., Kopeć, J.A., Woolf, A.D., Haile, L.M., Hagins, H., Ong, K., Kopansky-Giles, D., Dreinhoefer, K.E., Betteridge, N., Mohammadreza Abbasian, Mitra Abbasifard, Abedi, krishna, Miracle Ayomikun Adesina, Janardhana Aithala P and Mostafa Akbarzadeh-Khiavi (2023). Global, regional, and national burden of other musculoskeletal disorders, 1990–2020, and projections to 2050: a systematic analysis of the Global Burden of Disease Study 2021. The Lancet Rheumatology, 5(11), pp.e670–e682. doi:https://doi.org/10.1016/s2665-9913(23)00232-1.

[5]        Rasa, A.R. (2024). Artificial Intelligence and Its Revolutionary Role in Physical and Mental Rehabilitation: A Review of Recent Advancements. BioMed Research International, [online] 2024(1). doi:https://doi.org/10.1155/bmri/9554590.

[6]        Alzahrani, A. and Ullah, A. (2024). Advanced biomechanical analytics: Wearable technologies for precision health monitoring in sports performance. Digital health, 10. doi:https://doi.org/10.1177/20552076241256745.

[7]        Farago, E., Macisaac, D., Suk, M. and Chan, A.D.C. (2022). A Review of Techniques for Surface Electromyography Signal Quality Analysis. IEEE Reviews in Biomedical Engineering, 16, pp.1–1. doi:https://doi.org/10.1109/rbme.2022.3164797.

[8]        Shin, J., Abu, Sota Konnai, Takahashi, I. and Koki Hirooka (2024). Hand gesture recognition using sEMG signals with a multi-stream time-varying feature enhancement approach. Scientific Reports, [online] 14(1). doi:https://doi.org/10.1038/s41598-024-72996-7.

[9]        Xia, Y., Qiu, D., Zhang, C. and Liu, J. (2025). sEMG-based gesture recognition using multi-stream adaptive CNNs with integrated residual modules. Frontiers in Bioengineering and Biotechnology, 13. doi:https://doi.org/10.3389/fbioe.2025.1487020.

[10]      Gan, Z., Bai, Y., Wu, P., Xiong, B., Zeng, N., Zou, F., Li, J., Guo, F. and He, D. (2024). SGRN: SEMG-based gesture recognition network with multi-dimensional feature extraction and multi-branch information fusion. Expert Systems with Applications, 259, pp.125302–125302. doi:https://doi.org/10.1016/j.eswa.2024.125302.

[11]      Zhang, M., Qu, L., Wu, W., Han, G. and Zhu, W. (2025). sEMG-Based Gesture Recognition Using Sigimg-GADF-MTF and Multi-Stream Convolutional Neural Network. Sensors, 25(11), pp.3506–3506. doi:https://doi.org/10.3390/s25113506.

[12]      Sharma, A.K., Liu, S.-H., Zhu, X. and Chen, W. (2024). Predicting Gait Parameters of Leg Movement with sEMG and Accelerometer Using CatBoost Machine Learning. Electronics, 13(9), pp.1791–1791. doi:https://doi.org/10.3390/electronics13091791.

[13]      Didier Pradon, Tong, L., Christos Chalitsios and Roche, N. (2024). Development of Surface EMG for Gait Analysis and Rehabilitation of Hemiparetic Patients. Sensors, 24(18), pp.5954–5954. doi:https://doi.org/10.3390/s24185954.

[14]      Alegria, M., Gomez-Correa, M., Cruz-Ortiz, D. and Ballesteros, M. (2024). Design of a wearable system for gait analysis based on IMU, sEMG and plantar load signals. pp.205–210. doi:https://doi.org/10.1109/iccma63715.2024.10843875.

[15]      Liu, S.-H., Sharma, A.K., Wu, B.-Y., Zhu, X., Chang, C.-J. and Wang, J.-J. (2025). Estimating gait parameters from sEMG signals using machine learning techniques under different power capacity of muscle. Scientific Reports, 15(1). doi:https://doi.org/10.1038/s41598-025-95973-0.

[16]      P Blanco-Giménez, J. Vicente-Mampel, P Gargallo, S Maroto-Izquierdo, J Martín-Ruíz, E Jaenada-Carrilero and Barrios, C. (2024). Effect of exercise and manual therapy or kinesiotaping on sEMG and pain perception in chronic low back pain: a randomized trial. BMC Musculoskeletal Disorders, 25(1). doi:https://doi.org/10.1186/s12891-024-07667-9.

[17]      Lohith Chatragadda, Fletcher, A., Zhong, S., Vargas, F.A., Bhagat, N., Kunal Mankodiya, Delmonico, M.J. and Solanki, D. (2025). Development and Assessment of a Soft Wearable for sEMG-Based Hand Grip Detection and Control of a Virtual Environment. Sensors, 25(8), pp.2431–2431. doi:https://doi.org/10.3390/s25082431.

[18]      Alyanak, B., İnanır, M., Sade, S.I. and Kablanoğlu, S. (2025). Efficacy of Game-Based EMG-Biofeedback Therapy in Post-Stroke Dysphagia: A Randomized Controlled Trial. Dysphagia. doi:https://doi.org/10.1007/s00455-025-10819-1.

[19]      Marcos-Antón, S., Jardón-Huete, A., Oña-Simbaña, E.D., Blázquez-Fernández, A., Martínez-Rolando, L. and Cano-de-la-Cuerda, R. (2023). sEMG-controlled forearm bracelet and serious game-based rehabilitation for training manual dexterity in people with multiple sclerosis: a randomised controlled trial. Journal of NeuroEngineering and Rehabilitation, [online] 20, p.110. doi:https://doi.org/10.1186/s12984-023-01233-5.

[20]      Muhammad Al-Ayyad, Hamza Abu Owida, Roberto de Fazio, Bassam Al-Naami and Visconti, P. (2023). Electromyography Monitoring Systems in Rehabilitation: A Review of Clinical Applications, Wearable Devices and Signal Acquisition Methodologies. Electronics, 12(7), pp.1520–1520. doi:https://doi.org/10.3390/electronics12071520.

[21]      Dunai, L., Verdú, I.S., Dinu Turcanu and Viorel Bostan (2025). Prosthetic Hand Based on Human Hand Anatomy Controlled by Surface Electromyography and Artificial Neural Network. Technologies, 13(1), pp.21–21. doi:https://doi.org/10.3390/technologies13010021.

[22]      Chau, M.T. and Hung, B.D. (2024). SEMG-Based Prosthetic Hand with an Integrated Mobile Application. Lecture notes in computer science, pp.23–38. doi:https://doi.org/10.1007/978-3-031-65154-0_2.

[23]      Tchimino, J., Hansen, R.L., Jørgensen, P.H., Dideriksen, J. and Dosen, S. (2024). Application of EMG feedback for hand prosthesis control in high-level amputation: a case study. Scientific Reports, [online] 14(1). doi:https://doi.org/10.1038/s41598-024-80828-x.

[24]      Rafiq, A., Talukder, Z., Hamim, A., Firdous, J. and Uddin Ahmed, K.I. (2024). sEMG Signal-Based Prosthetic Hand Control Using Embedded Machine Learning with Deep Neural Network. 2024 6th International Conference on Electrical Engineering and Information & Communication Technology (ICEEICT), [online] pp.382–386. doi:https://doi.org/10.1109/iceeict62016.2024.10534475.

[25]      Umme Rumman, Arifa Ferdousi, Hossain, M.S., Islam, M.J. and Islam, M.R. (2024). FORS-EMG: A Novel sEMG Dataset for Hand Gesture Recognition Across Multiple Forearm Orientations. [online] doi:https://doi.org/10.48550/arXiv.2409.07484.

[26]      Zhang, M., Liu, S., Li, X., Qu, L., Zhuang, B. and Han, G. (2024). Improving sEMG-Based Hand Gesture Recognition through Optimizing Parameters and Sliding Voting Classifiers. Electronics, 13(7), pp.1322–1322. doi:https://doi.org/10.3390/electronics13071322.

[27]      Zhong, W., Zhang, Y., Fu, P., Xiong, W. and Zhang, M. (2023). A Spatio-Temporal Graph Convolutional Network for Gesture Recognition from High-Density Electromyography. arXiv (Cornell University). doi:https://doi.org/10.48550/arxiv.2312.00553.

[28]      Han, Y., Zhao, W., Gao, G., Chen, X., Yin, J., Wang, L., Meng, X., Yu, Y. and Zhang, T. (2025). DCSNN: An Efficient and High-speed sEMG-based Transient-state Micro-gesture Recognition Method on Wearable Devices. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies, 9(2), pp.1–34. doi:https://doi.org/10.1145/3729494.

[29]      Hellara, H., Barioul, R., Sahnoun, S., Fakhfakh, A., Kanoun, O.: Compar-ative study of semg feature evaluation methods based on the hand gesture classification performance. Sensors 24(11) (2024), https://www.mdpi.com/1424- 8220/24/11/3638

[30]      Cheng, L., Li, J., Guo, A., Zhang, J.: Recent advances in flexible noninvasive electrodes for surface electromyography acquisition. npj Flexible Electronics 7(1), 39 (2023)

[31]      Zhao, K., Zhang, Z., Wen, H., Scano, A.: Intra-subject and inter-subject movement variability quantified with muscle synergies in upper-limb reaching movements. Biomimetics 6(4) (2021), https://www.mdpi.com/2313-7673/6/4/63

[32]      Chopra, S., Emran, T.B.: Advances in ai-based prosthetics development. Interna-tional Journal of Surgery 110(8), 4538–4542 (2024)

[33]      Chen, Z., Min, H., Wang, D., Xia, Z., Sun, F., Fang, B.: A review of my-oelectric control for prosthetic hand manipulation. Biomimetics 8(3) (2023), https://www.mdpi.com/2313-7673/8/3/328

[34]      Wang, S., Wu, X., Lai, W., Yao, J., Gou, X., Ye, H., Yi, J., Cao, D.: Rehabilitation evaluation method and application for upper limb post-stroke based on improved dtw. Biomedical Signal Processing and Control 106, 107775 (2025)

[35]      Hodossy, B.K., Guez, A.S., Jing, S., Huo, W., Vaidyanathan, R., Farina, D.: Lever-aging high-density emg to investigate bipolar electrode placement for gait pre-diction models. IEEE Transactions on Human-Machine Systems 54(2), 192–201 (2024)

[36]      Li, Y., Ma, L., Yue, W., Chen, F.: Design of an arm posture recognition system and adaptive tens therapeutic device based on semg signals. In: 2024 8th International Conference on Electrical, Mechanical and Computer Engineering (ICEMCE). pp. 1171–1174. IEEE (2024)

[37]      Lim, G., Youn, H., Kim, H., Jeong, H., Cho, J., Lee, S., Pak, C., Kwon, S.: Impact of mixed reality-based rehabilitation on muscle activity in lower-limb amputees: An emg analysis. IEEE Access 12, 106415–106431 (2024).

[38]      Buteau, É., Gagné, G., Bonilla, W., Boukadoum, M., Fortier, P., Gosselin, B.: Tinyml for real-time embedded hd-emg hand gesture recognition with on-device fine-tuning. In: 2024 46th Annual International Conference of the IEEE Engineer-ing in Medicine and Biology Society (EMBC). pp. 1–6. IEEE (2024).

[39]      Salerno, A., Barraud, S.: Evaluation and implementation of high-dimensionnal computing for gesture recognition using semg signals. In: 2024 International Con-ference on Control, Automation and Diagnosis (ICCAD). pp. 1–6. IEEE (2024).

[40]      Chaves, G.S., Vieira, A.S., Lima, M.V.: semg-based gesture classifier through dtw and enhanced muscle activity detection. IEEE Access 12, 117595–117607 (2024).

[41]      Jiang, N., Wang, L., Wang, D., Fang, P., Wu, X., Li, G.: Loading recognition for lumbar exoskeleton based on multi-channel surface electromyography from low back muscles. IEEE Transactions on Biomedical Engineering 71(7), 2154–2162 (2024).

[42]      Akhil, V., Satheesh, R., Ashmi, M., Tawk, C.D.: Lower limb emg signal analysis using scattering transform and support vector machine for various walking condi-tions. IEEE Access 11, 129566–129575 (2023).

[43]      Zou, Y., Cheng, L., Han, L., Li, Z., Song, L.: Decoding electromyographic signal with multiple labels for hand gesture recognition. IEEE Signal Processing Letters 30, 483–487 (2023).

[44]      Erazo, A., Ko, S.B.: A long short-term memory-based interconnected architec-ture for classification of grasp types using surface-electromyography signals. IEEE Transactions on Artificial Intelligence 5(1), 434–445 (2023).

[45]      Zhang, W., Zhao, T., Zhang, J., Wang, Y.: Lst-emg-net: Long short-term trans-former feature fusion network for semg gesture recognition. Frontiers in Neuro-robotics 17, 1127338 (2023).

[46]      Hye, N.M., Hany, U., Chakravarty, S., Akter, L., Ahmed, I.: Artificial intelligence for semg-based muscular movement recognition for hand prosthesis. IEEE Access 11, 38850–38863 (2023).

[47]      Li, J., Wei, L., Wen, Y., Liu, X., Wang, H.: An approach to continuous hand movement recognition using semg based on features fusion. The Visual Computer 39(5), 2065–2079 (2023).

[48]      Vijayvargiya, A., Singh, P., Kumar, R., Dey, N.: Hardware implementation for lower limb surface emg measurement and analysis using explainable ai for activity recognition. IEEE Transactions on Instrumentation and Measurement 71, 1–9 (2022)

[49]      Abdolahnezhad, P., Yousefi-Koma, A., Zakerzadeh, M.R., Rezaeian, S., Farsad, M., Aboumasoudi, S.S.: Identification of locomotion modes based on artificial intelli-gence algorithms using surface electromyography signals. In: 2021 9th RSI Inter-national Conference on Robotics and Mechatronics (ICRoM). pp. 198–202. IEEE (2021).

[50]      Coskun, M., Yildirim, O., Demir, Y., Acharya, U.R.: Efficient deep neural net-work model for classification of grasp types using semg signals. Journal of ambient intelligence and humanized computing 13(9), 4437–4450 (2022)

[51]      Su, C., Chen, S., Jiang, H., Chen, Y.: Ankle joint torque prediction based on surface electromyographic and angular velocity signals. IEEE access 8, 217681–217687 (2020).

[52]      Roland, T.: Motion artifact suppression for insulated emg to control myoelectric prostheses. Sensors 20(4) (2020), https://www.mdpi.com/1424-8220/20/4/1031.

[53]      Tam, S., Boukadoum, M., Campeau-Lecours, A., Gosselin, B.: A fully embedded adaptive real-time hand gesture classifier leveraging hd-semg and deep learning. IEEE Transactions on Biomedical Circuits and Systems 14(2), 232–243 (2020).

[54]      Secciani, N., Topini, A., Ridolfi, A., Meli, E., Allotta, B.: A novel point-in-polygon-based semg classifier for hand exoskeleton systems. IEEE Transactions on Neural Systems and Rehabilitation Engineering 28(12), 3158–3166 (2020).

[55]      Gomez-Correa, M., Cruz-Ortiz, D. and Ballesteros, M. (2025). Wearable and wireless sEMG acquisition system based on the Internet of Medical Things. Sensing and Bio-Sensing Research, pp.100828–100828. doi:https://doi.org/10.1016/j.sbsr.2025.100828.

[56]      Yang, S., Cheng, J., Shang, J., Hang, C., Qi, J., Zhong, L., Rao, Q., He, L., Liu, C., Ding, L., Zhang, M., Chakrabarty, S. and Jiang, X. (2023). Stretchable surface electromyography electrode array patch for tendon location and muscle injury prevention. Nature Communications, [online] 14(1), p.6494. doi:https://doi.org/10.1038/s41467-023-42149-x.

[57]      Wang, Z., Wan, H., Meng, L., Zeng, Z., Akay, M., Chen, C. and Chen, W. (2024). Optimization of inter-subject sEMG-based hand gesture recognition tasks using unsupervised domain adaptation techniques. Biomedical Signal Processing and Control, 92, p.106086. doi:https://doi.org/10.1016/j.bspc.2024.106086.

[58]      Lee, H., Jiang, M. and Zhao, Q. (2024). FedAssist: Federated Learning in AI-Powered Prosthetics for Sustainable and Collaborative Learning. PubMed, [online] pp.1–5. doi:https://doi.org/10.1109/embc53108.2024.10781961.

IZVOR: Proceedings of the 16th International Conference on Business Information Security BISEC’2025