Comparison Evaluation of Machine Learning Regression Models for EMG-Based Hand Grip Prediction across Multiple MVC Levels

Electromyography–based force prediction provides an intuitive control strategy for assistive and rehabilitation hand systems. This study investigates an EMG-based hand grip force prediction framework using machine learning techniques by modeling the relationship between forearm muscle activation and grip force at varying contraction levels. sEMG signals were obtained from the FDS and FCR muscles of ten healthy female participants (aged 20–25 years) during controlled grip tasks performed at five MVC levels ranging from 20% to 100%. The recorded signals were filtered, processed using RMS feature extraction, and normalized to MVC prior to regression modeling. LR, GPR, SVR, and kNN models were evaluated using offline analysis. Performance was evaluated using RMSE and prediction accuracy, defined relative to the measured grip force. The results indicate that GPR demonstrates the most consistent performance, achieving the highest average accuracy (85.84%) and the lowest average RMSE (10.54). In contrast, SVR and kNN exhibit higher prediction errors, particularly at higher MVC levels.

Had Grip Force Prediction, Comparative Evaluation, Regression Models

1. Suppiah, R., Sharma, A., Kim, N., Abidi, K., & Alkaff, A. (2020, November). An electromyography-aided robotics hand for rehabilitation: A proof-of-concept study. In Proceedings of the IEEE Region 10 Conference (TENCON) (pp. 361–366). https://doi.org/10.1109/TENCON50793.2020.9293940 [Google Scholar] [Crossref]

2. Vredenbregt, J., & Rau, G. (2015). Surface electromyography in relation to force, muscle length and endurance. In New concepts in motor unit neuromuscular disorders: Electromyography and kinesiology (Vol. 1, pp. 607–622). https://doi.org/10.1159/000394062 [Google Scholar] [Crossref]

3. McManus, L., De Vito, G., & Lowery, M. M. (2021). Analysis and biophysical interpretation of surface electromyography in progressing Parkinson’s disease. Frontiers in Neurology, 12, 654484. https://doi.org/10.3389/fneur.2021.654484 [Google Scholar] [Crossref]

4. Nguyen, T. M., Takagi, M., Nguyen, T. T., Tran, H. H., & Dao, K. V. T. (2025). Research on the application of artificial intelligence in hand rehabilitation by estimating hand grip force using EMG data. International Journal of Artificial Intelligence Research, 9(1). [Google Scholar] [Crossref]

5. https://doi.org/10.29099/ijair.v9i1.1381 [Google Scholar] [Crossref]

6. Simão, M., Mendes, N., Gibaru, O., & Neto, P. (2019). A review on electromyography decoding and pattern recognition for human–machine interaction. IEEE Access, 7, 39564–39582. [Google Scholar] [Crossref]

7. https://doi.org/10.1109/ACCESS.2019.2906584 [Google Scholar] [Crossref]

8. Secciani, N., Bianchi, M., Meli, E., Volpe, Y., & Ridolfi, A. (2019). A novel application of a surface EMG-based control strategy for a hand exoskeleton system: A single-case study. International Journal of Advanced Robotic Systems, 16(1), 1–13. https://doi.org/10.1177/1729881419828197 [Google Scholar] [Crossref]

9. Sade, J. (2026). Predicting fetal health using ANFIS: A comparative study with machine learning models. Turkish Journal of Engineering, 10(1), 187–196. https://doi.org/10.31127/tuje.1711661 [Google Scholar] [Crossref]

10. Sittiruk, T., Sengchuai, K., Booranawong, A., & Phukpattaranont, P. (2025). Implementation of a real-time force prediction system based on sEMG signals and Gaussian process regression: Human–robot interaction in rehabilitation. IEEE Access, 13, 13731–13745. [Google Scholar] [Crossref]

11. https://doi.org/10.1109/ACCESS.2025.3529986 [Google Scholar] [Crossref]

12. Li, S., Zhang, L., Meng, Q., & Yu, H. (2023). A real-time control method for upper limb exoskeleton based on active torque prediction model. Bioengineering, 10(12), 1441. [Google Scholar] [Crossref]

13. https://doi.org/10.3390/bioengineering10121441 [Google Scholar] [Crossref]

14. Singh, S., Kumar, K., Kumar, B., Kumar, R., & Singh, N. (2025). A comparative analysis of deep learning techniques for sentiment analysis using social media content. Turkish Journal of Engineering, 9(3), 754–767. https://doi.org/10.31127/tuje.1698748 [Google Scholar] [Crossref]

15. Özbek, M. E., & Soyak, E. G. (2025). Understanding machine learning model behavior for intrusion detection across attacks. Turkish Journal of Engineering, 9(3), 768–778. [Google Scholar] [Crossref]

16. https://doi.org/10.31127/tuje.1613468 [Google Scholar] [Crossref]

17. Bhadauria, A. P. S., Singh, M., Kumar, R., & Kumar, A. (2025). Real-time intrusion detection in edge computing using machine learning techniques. Turkish Journal of Engineering, 9(2), 385–393. https://doi.org/10.31127/tuje.1516046 [Google Scholar] [Crossref]

18. Kizyte, A., Lei, Y., & Wang, R. (2023). Influence of input features and EMG type on ankle joint torque prediction with support vector regression. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 31, 4286–4295. https://doi.org/10.1109/TNSRE.2023.3323364 [Google Scholar] [Crossref]

19. Martinez, I. J. R., Mannini, A., Clemente, F., & Cipriani, C. (2020). Online grasp force prediction from transient EMG. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 28(10), 2333–2341. https://doi.org/10.1109/TNSRE.2020.3022587 [Google Scholar] [Crossref]

20. Bardizbanian, B., et al. (2020). Efficiently training two-DoF hand–wrist EMG-force models. In Proceedings of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 369–373). https://doi.org/10.1109/EMBC44109.2020.9175675 [Google Scholar] [Crossref]

21. Manickaraj, N., Kavanagh, J. J., & Bisset, L. M. (2025). Altered anconeus muscle activation characteristics during isometric gripping in individuals with lateral elbow tendinopathy compared with age- and sex-matched control. Journal of Shoulder and Elbow Surgery, 34, 1730–1740. [Google Scholar] [Crossref]

22. https://doi.org/10.1016/j.jse.2024.11.001 [Google Scholar] [Crossref]

23. Zhang, X., Wang, K., Wu, D., Zhang, X., & Chen, X. (2025). Feasibility study on the application of HD-sEMG-based force prediction technology in the assessment of hand dysfunction in cerebral palsy. Frontiers in Bioengineering and Biotechnology, 13, 1580098. [Google Scholar] [Crossref]

24. https://doi.org/10.3389/fbioe.2025.1580098 [Google Scholar] [Crossref]

25. Boka, T., Eskandari, A., Moosavian, S. A. A., & Sharbatdar, M. (2024). Using machine learning algorithms for grasp strength recognition in rehabilitation planning. Results in Engineering, 21, 101660. https://doi.org/10.1016/j.rineng.2023.101660 [Google Scholar] [Crossref]

26. Çelik, A., & Kaptan, D. (2025). Text classification by machine learning algorithms using a new text feature extraction method based on image processing. Turkish Journal of Engineering, 9(4), 712–724. https://doi.org/10.31127/tuje.1718023 [Google Scholar] [Crossref]

27. Wang, M., et al. (2023). Lower limb joint torque prediction using long short-term memory network and Gaussian process regression. Sensors, 23(23), 9576. https://doi.org/10.3390/s23239576 [Google Scholar] [Crossref]

• A Machine Learning Model for Predicting the Risk of Developing Diabetes - T2DM Using Real-World Data from Kilifi, Kenya
• AI-Powered Facial Recognition Attendance System Using Deep Learning and Computer Vision
• A Comprehensive Review on Brain Tumour Segmentation Using Deep Learning Approach
• A Scalable Retrieval-Augmented Generation Pipeline for Domain-Specific Knowledge Applications
• Predictive Maintenance in Semiconductor Manufacturing Using Machine Learning on Imbalanced Dataset