Journal: IPSI Transactions on Internet Research

Motion Intention Prediction
Using Wireless Surface EMG Sensors

Authors: L’ach, Jakub Ferenčík, Norbert Steingartner, William Bednarčíková, Lucia Bálint, Tomáš and Hudák, Radovan


View PDF Cite this article

Abstract

This paper investigates the prediction of finger motion intention using surface electromyography (sEMG) signals and supervised machine learning models. sEMG sensors provide a noninvasive means of capturing muscle activity, enabling applications in prosthetics, rehabilitation, and human-computer interface. The study explores signal preprocessing techniques, time-frequency domain transformations, and machine learning algorithms including SVM, Random Forest, and XGBoost. The results highlight the challenges posed by noise and variability in sEMG signals, and suggest strategies for improving prediction accuracy and real-world applicability.

Keywords

finger motion intention, human–computer interface, prosthetics, signal preprocessing, surface electromyography, time–frequency domain


Published in: IPSI Transaction on Internet Research (Volume: 22, Issue: 2)
Publisher: IPSI, Belgrade

Date of Publication: April 1, 2026

Open Access: CC-BY-NC-ND
DOI: 10.58245/ipsi.tir.2602.02Corr

Pages: 5 - 12

ISSN: 1820 - 4503

References

1. BOYER, M., BOUYER, L., ROY, J.-S., AND CAMPEAULECOURS, A. Reducing noise, artifacts and interference in single-channel emg signals: A review. Sensors 23, 6 (2023), 2927.

2. CHEN, T., AND GUESTRIN, C. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ’16) (2016), ACM, pp. 785– 794.

3. FARINA, D., FOSCI, M., AND MERLETTI, R. Motor unit recruitment strategies investigated by surface emg variables. Journal of Applied Physiology 92 (2002), 235–247.

4. FARINA, D., STEGEMAN, D. F., AND MERLETTI, R. Biophysics of the generation of emg signals. In Surface Electromyography: Physiology, Engineering, and Applications. John Wiley and Sons Ltd., 2016.

5. GÉRON, A. Hands-On Machine Learning with ScikitLearn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, 2 ed. O’Reilly Media, 2019.

6. GOHEL, V., AND MEHENDALE, N. Review on electromyography signal acquisition and processing. Biophysical Reviews 12 (2020), 1361–1367.

7. GOOGLE AI. Mediapipe hand landmarker. https://ai.google.dev/edge/mediapipe/solutions/vision/ hand_landmarker, 2025. Accessed: Mar. 11, 2025.

8. HACKADAY.IO. umyo wearable emg sensor with wet/dry electrodes. https://hackaday.io/project/ 186038-umyo-wearable-emg-sensor-with-wetdry-electrodes. Accessed: Oct. 9, 2024.

9. HANSON, J., AND PERSSON, A. Changes in the action potential and contraction of isolated frog muscle after repetitive stimulation. Acta Physiologica Scandinavica 81 (1971), 340–348.

...

15. L’ACH, J. Motion intention prediction using wireless surface emg sensors, 2025. Central Register of Theses and Dissertations (CRZP), ID: 103404.

×

L’ach, Jakub

Jakub L’ach is a graduate of Biomedical Engineering and Measurement at the Faculty of Mechanical Engineering, Technical University of Košice. During his engineering (MSc) studies, his research focused on the prediction of finger motion intention using surface electromyography (sEMG) signals and supervised machine learning methods. His work investigated noninvasive sEMG-based sensing of muscle activity for applications in prosthetics, rehabilitation, and human–computer interaction. The research explored signal preprocessing techniques, timeand frequency-domain feature extraction, and machine learning algorithms including Support Vector Machines, Random Forest, and XGBoost. The results highlighted key challenges related to noise and inter-subject variability in sEMG signals and proposed strategies to improve prediction accuracy and real-world applicability of sEMG-based control systems.
email: jakub.lach@student.tuke.sk

×

Ferenčík, Norbert

Norbert Ferenčík is a graduate of Cybernetics (BSc, 2014) and Artificial Intelligence and Intelligent Systems (MSc, 2016) at the Faculty of Electrical Engineering and Informatics, Technical University of Košice. During his PhD studies, he completed a six-month research stay at University of California, Berkeley. After defending his PhD in Artificial Intelligence (2020), he has been working as a postdoctoral researcher at the Department of Cybernetics and Artificial Intelligence, focusing on 3D printing in medicine and engineering and bioreactors. He is a co-author of several peer-reviewed publications and currently serves as Deputy Head of the Department for Research and Development.
email: norbert.ferencik@tuke.sk, ORCID 0000-0002-9648-5799

×

Steingartner, William

William Steingartner works as Associate Professor of Computer Science at the Department of Computers and Informatics of the Faculty of Electrical Engineering and Informatics, Technical University of Košice, Slovakia. He defended his PhD thesis “The Rôle of Toposes in Computer Science” in 2008. His main fields of research are theoretical computer science and software engineering. He also works in cybersecurity and applied computer science.
email: william.steingartner@tuke.sk, ORCID 0000-0002-2852-9403

×

Bednarčíková, Lucia

Lucia Bednarčíková is an Assistant Professor at the Technical University of Košice, Faculty of Mechanical Engineering, Department of Biomedical Engineering and Measurement. Her professional and research activities focus on biomechanics in prosthetics and orthotics, movement biomechanics, and the development and design of individualized prosthetic and orthotic devices. In her work, she integrates engineering approaches with clinical practice and utilizes digital technologies, particularly 3D surface scanning, for objective assessment, individualized treatment planning, and support of functional outcome evaluation.
email: lucia.bednarcikova@tuke.sk, ORCID 0000-0001-5045-3268

×

Bálint, Tomáš

Tomáš Balint works as a research scientist at the Department of Biomedical Engineering and Measurements, Faculty of Mechanical Engineering, Technical University of Košice (TUKE). In his research activities, he has long focused on the development and production of medically certified materials using extrusion technologies, as well as on additive manufacturing (3D printing) of experimental samples intended for subsequent mechanical, physical andbiodegradation testing. His professional interests include the application of advanced manufacturing technologies in biomedical engineering, optimization of material properties for medical use and evaluation of their behavior in conditions simulating the biological environment. He publishes the results of his research work in renowned scientific journals and actively participates in solving domestic and international research projects. His publication activities also include an article registered in the Current Contents database in a journal with an impact factor of 18, which confirms the high professional level and international reach of his scientific work.
email: tomas.balint@tuke.sk, ORCID 0000-0002-1944-2867

×

Hudák, Radovan

Radovan Hudák is a professor and Head of the Department of Special Engineering Processes as well as the Department of Biomedical Engineering and Measurement at the Faculty of Mechanical Engineering, Technical University of Košice. His research focuses on additive manufacturing in medicine, human biomechanics, and medical thermography. He has completed international research stays at the University of Ghent (Belgium), the University of Illinois at Chicago (USA), the Technical University of Białystok (Poland), and the Czech Technical University in Prague. He is a member of ASTM committees F42 and E20, a member of the editorial board of ProIN, a cofounder of the YBERC conference, and the author of over 350 publications, including scientific monographs, university textbooks, and patented works.
email: radovan.hudak@tuke.sk, ORCID 0000-0003-1060-0539

×

Cite this article

L’ach, Jakub; Ferencík, Norbert; Steingartner, William; Bednrčíková, Lucia; Bálint, Tomáš; and Hudák, Radovan
"Motion Intention Prediction Using Wireless Surface EMG Sensors",
IPSI Transactions on Internet Research, vol. 22(2), pp. 5-12, 2026, https://doi.org/10.58245/ipsi.tir.2602.02Corr