Identification of electromyographic signals using machine learning techniques and low-cost technologies

Autores/as

DOI:

https://doi.org/10.47734/regrasp.v10.03.p18-31

Palabras clave:

Electromyographic Signals, Gesture Recognition, Machine Learning, Human-Robot Interface

Resumen

A interface humano-robô (IHR) é um tópico de pesquisa muito estudado recentemente. Este tópico se trata da aquisição, processamento e interpretação de sinais eletrobiológicos provenientes de diferentes partes do corpo humano e aplicação desses sinais para o controle de sistemas robóticos. A IHR torna-se necessária em aplicações para pessoas com deficiências, profissionais que trabalham em ambientes perigosos ou até mesmo na cirurgia robótica. O enfoque deste trabalho é a identificação de sinais eletromiográficos (EMGs). Sensores EMGs foram colocados em regiões específicas do braço de uma pessoa e a identificação gestual foi realizada. Inicialmente, foram determinados os sensores EMGs e o microcontrolador utilizando tecnologias de baixo custo. Posteriormente, foram aplicadas técnicas de aprendizado de máquina para identificação gestual. As principais contribuições do trabalho foram a utilização de um sensor EMG disponível comercialmente no Brasil e em diversos países, de fácil acessibilidade e pouco explorado na literatura, além da utilização dos aplicativos de extração de características (features) e técnicas de aprendizado de máquina do software Matlab, que são ferramentas práticas, eficientes, e também pouco exploradas na literatura. O modelo de aprendizado de máquina obtido foi bastante preciso e pode ser aplicado futuramente para o controle de sistemas robóticos.

Biografía del autor/a

Jhenifer July Sousa De Almeida, IFSP/Campus São Paulo

Undergraduate Student in Production Engineering - IFSP/Campus São Paulo

Caio Igor Gonçalves Chinelato, Federal University of ABC (UFABC) - Center of Engineering

Professor and researcher at Federal University of ABC (UFABC) - Center of Engineering, Modeling and Applied Social Sciences (CECS), Santo André, Brazil. Mechatronics Technician graduated from ETEC Jorge Street, São Caetano do Sul, Brazil. B.Sc. Degree in Science and Technology, B.Sc. Degree in Instrumentation, Automation and Robotics Engineering, and M.Sc. Degree in Mechanical Engineering from the UFABC. Ph.D. Degree in Electrical Engineering from the Polytechnic School of University of São Paulo (EPUSP), São Paulo, Brazil. The research interests include Robotics, Control Systems, Mechatronics, Automation, and Engineering Education.

Citas

Abayasiri, R. A. M., Jayasekara, A. G. B. P., Gopura, R. A. R. C., & Kiguchi, K (2021). EMG based controller for a wheelchair with robotic manipulator. Proceedings of the 3rd International Conference on Electrical Engineering (EECon), Colombo, Sri Lanka, 125-130. https://doi.org/10.1109/EECon52960.2021.9580949

Ali, M., Riaz, A., Usmani, W. U., & Naseer, N. EMG based control of a quadcopter (2020). Proceedings of the International Conference on Mechanical, Electronics, Computer, and Industrial Technology (MECnIT), Medan, Indonesia, 250-253. https://doi.org/10.1109/MECnIT48290.2020.9166603

Barsotti, M., Dupan, S., Vujaklija, I., Dosen, S., Frisoli, A., & Farina, D (2019). Online finger control using high-density EMG and minimal training data for robotic applications. IEEE Robotics and Automation Letters, 4(2), 217-223. https://doi.org/10.1109/LRA.2018.2885753

Bisi, S., De Luca, L., Shrestha, B., Yang, Z., & Ghandi, V (2018). Development of an EMG-controlled mobile robot. Robotics, 7(3), 1-13. https://doi.org/10.3390/robotics7030036

Chen, X., Li, Y., Hu, R., Zhang, X., & Chen, X (2021). Hand gesture recognition based on surface electromyography using convolution neural network with transfer learning method. IEEE Journal of Biomedical and Health Informatics, 25(4), 1292-1304. https://doi.org/10.1109/JBHI.2020.3009383

Coppeliasim (2025, August 28). CoppeliaSim Simulator. https://www.coppeliarobotics.com

Eletrogate (2025, August 28). EMG sensor. https://www.eletrogate.com/modulo-sensor-eletromiografico-de-sinal-muscular-emg

Ferreira, A., Celeste, W. C., Cheein, F. A., Bastos-Filho, T. F., Sarcinelli-Filho, M., & Carelli, R (2008). Human-Machine interfaces based on EMG and EEG applied to robotic systems. Journal of Neuroengineering and Rehabilitation, 5(10), 1-15. https://doi.org/10.1186/1743-0003-5-10

Fu, M., Xue, J., Huang, P., Chen, Z., Wei, W., Li, G., & Chen, S (2018). Research on recognition of forearm sEMG signal based on different motion modes. Proceedings of the IEEE International Conference on Cyborg and Bionic Systems (CBS), Shenzhen, China, 581-584. https://doi.org/10.1109/CBS.2018.8612195

Godoy, R. V., Dwivedi, A., Guan, B., Turner, A., Shieff, D., & Liarokapis, M (2022). On EMG based dexterous robotic telemanipulation: assessing machine learning techniques, feature extraction methods, and shared control schemes. IEEE Access, 10, 99661-99674. https://doi.org/10.1109/ACCESS.2022.3206436

Godoy, R. V., Lahr, G. J. G., Dwivedi, A., Reis, T. J. S., Polegato, P. H., Becker, M., Caurin, G. A. P., & Liarokapis, M (2022). Electromyography-Based, robust hand motion classification employing temporal multi-channel vision transformers. IEEE Robotics and Automation Letters, 7(4), 10200-10207. https://doi.org/10.1109/LRA.2022.3192623

Jun, J., Zhao, B., Zhang, P., Guo, W., & Fang, P (2021). UAV formation flight control by using the surface electromyography signals. Proceedings of the 33rd Chinese Control and Decision Conference (CCDC), Kunming, China, 3287-3291. https://doi.org/10.1109/CCDC52312.2021.9602378

Liao, L. Z., Tseng, Y. L., Chiang, H. H., & Wang, W. Y (2018). EMG-Based control scheme with SVM classifier for assistive robot arm. Proceedings of the International Automatic Control Conference (CACS), Taoyuan, Taiwan. https://doi.org/10.1109/CACS.2018.8606762

Luo, J., Lin, Z., Li, Y., & Yang, C (2020). A teleoperation framework for mobile robots based on shared control. IEEE Robotics and Automation Letters, 5(2), 377-384. https://doi.org/10.1109/LRA.2019.2959442

Maeda, Y., & Ishibashi, S (2017). Operating instruction method based on EMG for omnidirectional wheelchair robot. Proceedings of the 17th World Congress of International Fuzzy Systems Association and International Conference on Soft Computing and Intelligent Systems (IFSA - SCIS), Otsu, Japan. https://doi.org/10.1109/IFSA-SCIS.2017.8023339

Marcheix, B., Gardiner, B., & Coleman, S (2019). Adaptive gesture recognition system for robotic control using surface EMG sensors. Proceedings of the IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), Ajman, United Arab Emirates. https://doi.org/10.1109/ISSPIT47144.2019.9001765

Meattini, R., Benatti, S., Scarcia, U., De Gregorio, D., Benini, L., & Melchiori, C (2018). An SEMG-based human-robot interface for robotic hands using machine learning and synergies. IEEE Transactions on Components, Packaging and Manufacturing Technology, 8(7), 1149-1158. https://doi.org/10.1109/TCPMT.2018.2799987

Montoya, B. N., Añazco, M. V., Avila, A. S., Loayza, F. R., Añazco, E. V., & Teran, E (2022). Supervised machine learning applied to non-invasive EMG signal classification for an anthropomorphic robotic hand. Proceedings of the IEEE Andean Conference (ANDESCON), Barranquilla, Colombia. https://doi.org/10.1109/ANDESCON56260.2022.9989874

Morais, G. D., Neves, L. C., Masiero, A. A., & Castro, M. C. F (2016). Application of Myo Armband system to control a robot interface. Proceedings of the 9th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC), Rome, Italy, 227-231. https://doi.org/10.5220/0005706302270231

Myoware (2025, August 28). Myoware 2.0. https://www.sparkfun.com/myoware

Pololu (2025, August 28). Muscle sensor V3. https://www.pololu.com/file/0J745/Muscle_Sensor_v3_users_manual.pdf

Tello (2025, August 28). Tello quadcopter. https://www.ryzerobotics.com/tello

Yánez, A. J., Benalcázar, M. E., & Maldonado, E. M (2020). Real-Time hand gesture recognition using surface electromyography and machine learning: a systematic literature review. Sensors, 20(9), 1-36. https://doi.org/10.3390/s20092467

Descargas

Publicado

2025-08-28

Cómo citar

De Almeida, J. J. S., & Chinelato, C. I. G. (2025). Identification of electromyographic signals using machine learning techniques and low-cost technologies. Revista Para Graduandos Instituto Federal De Educação, Ciência E Tecnologia De São Paulo - Campus São Paulo - REGRASP, 10(3), 18–31. https://doi.org/10.47734/regrasp.v10.03.p18-31