Mejorando la ortopedia y medicina deportiva con el control de exoesqueletos de miembros inferiores en rehabilitación utilizando la clasificación de señales de electromiografía basada en aprendizaje profundo (Enhancing orthopedics and sports medicine with lower limb exoskeleton control in rehabilitation using deep learning based electromyography signal classification)

Autores/as

  • Bekzat Amanov Joldasbekov Institute of Mechanics and Engineering
  • Sayat Ibrayev Joldasbekov Institute of Mechanics and Engineering

DOI:

https://doi.org/10.47197/retos.v61.109799

Palabras clave:

aprendizaje profundo, electromiografía (EMG), rehabilitación deportiva, exoesqueletos de extremidades inferiores, clasificación de movimientos, redes neuronales, robótica asistiva

Resumen

Este artículo de investigación explora la aplicación de técnicas de aprendizaje profundo para mejorar el control de exoesqueletos de extremidades inferiores mediante la clasificación de señales de electromiografía (EMG). Utilizando redes neuronales convolucionales (CNNs) y redes neuronales recurrentes (RNNs), este estudio tiene como objetivo mejorar la precisión y adaptabilidad de los exoesqueletos utilizados en la rehabilitación, particularmente en ortopedia y medicina deportiva. La metodología involucra la recolección de datos EMG de diversos movimientos de piernas, que luego se procesan utilizando técnicas avanzadas de preprocesamiento de señales para mejorar la precisión de la clasificación. Los modelos de aprendizaje profundo son entrenados y validados con estos datos, demostrando mejoras significativas en la detección de movimientos y la respuesta del dispositivo. Los resultados del estudio indican que la integración de modelos de aprendizaje profundo no solo ofrece un control mejorado de los exoesqueletos sino que también asegura interacciones más naturales y eficientes con los usuarios. Esta investigación resalta el potencial de integrar modelos computacionales sofisticados en dispositivos de rehabilitación, allanando el camino para futuros avances que podrían mejorar significativamente los resultados terapéuticos y la calidad de vida de individuos con discapacidades de movilidad. Los hallazgos subrayan la importancia de continuar la innovación en el campo de la tecnología asistiva, sugiriendo caminos para futuras investigaciones en la integración de múltiples sensores y sistemas de control adaptativos.

Palabras clave: aprendizaje profundo, electromiografía (EMG), rehabilitación deportiva, exoesqueletos de extremidades inferiores, clasificación de movimientos, redes neuronales, robótica asistiva.

Abstract. This research paper investigates the application of deep learning techniques for enhancing the control of lower limb exoskeletons through the classification of electromyography (EMG) signals. Utilizing convolutional neural networks (CNNs) and recurrent neural networks (RNNs), this study aims to improve the precision and adaptability of exoskeletons used in rehabilitation, particularly in orthopedics and sports medicine. The methodology involves collecting EMG data from various leg movements, which are then processed using advanced signal preprocessing techniques to enhance classification accuracy. The deep learning models are trained and validated with this data, demonstrating significant improvements in movement detection and device responsiveness. Results from the study indicate that the integration of deep learning models not only offers enhanced control over exoskeletons but also ensures more natural and efficient user interactions. This research highlights the potential of integrating sophisticated computational models into rehabilitative devices, paving the way for future advancements that could significantly improve therapeutic outcomes and quality of life for individuals with mobility impairments. The findings underscore the importance of continued innovation in the field of assistive technology, suggesting pathways for further research in multi-sensor integration and adaptive control systems.

Keywords: deep Learning, electromyography (EMG), sports rehabilitation, lower limb exoskeletons, movement classification, neural networks, assistive robotics.

Citas

Sun, Y., Tang, Y., Zheng, J., Dong, D., Chen, X., & Bai, L. (2022). From sensing to control of lower limb exoskeleton: A systematic review. Annual Reviews in Control, 53, 83-96.

Tortora, S., Tonin, L., Sieghartsleitner, S., Ortner, R., Guger, C., Lennon, O., ... & Del Felice, A. (2023). Effect of lower limb exoskeleton on the modulation of neural activity and gait classification. IEEE Transactions on Neural Sys-tems and Rehabilitation Engineering.

Altayeva, A. B., Omarov, B. S., Aitmagambetov, A. Z., Kendzhaeva, B. B., & Burkitbayeva, M. A. (2014). Modeling and exploring base station characteristics of LTE mobile networks. Life Science Journal, 11(6), 227-233.

Zhang, P., Zhang, J., & Elsabbagh, A. (2022). Lower limb motion intention recognition based on sEMG fusion features. IEEE Sensors Journal, 22(7), 7005-7014.

Omarov, B., & Altayeva, A. (2018, January). Towards intelligent IoT smart city platform based on OneM2M guideline: smart grid case study. In 2018 IEEE International Conference on Big Data and Smart Computing (BigComp) (pp. 701-704). IEEE.

Zongxing, L., Jie, Z., Ligang, Y., Jinshui, C., & Hongbin, L. (2024). The Human-Machine Interaction Methods and Strategies for Upper and Lower Extremity Rehabilitation Robots: A Review. IEEE Sensors Journal.

Chen, B., Zhou, Y., Chen, C., Sayeed, Z., Hu, J., Qi, J., ... & Palacio, C. (2023). Volitional control of upper-limb exo-skeleton empowered by EMG sensors and machine learning computing. Array, 17, 100277.

Huang, G. S., Yen, M. H., Chang, C. C., Lai, C. L., & Chen, C. C. (2024). Development of an individualized stable and force-reducing lower-limb exoskeleton. Biomedical Physics & Engineering Express, 10(5), 055039.

Balcázar, A., Carballo, N. G., & Jaimes, D. A. R. (2024). La educación física, el currículo y las expresiones motrices. Retos: nuevas tendencias en educación física, deporte y recreación, (55), 650-658.

Pérez-Bahena, M. H., Niño-Suarez, P. A., Avilés Sánchez, O. F., Beleño, R. H., Caldas, O. I., & Pellico-Sánchez, O. I. (2024). Trends in robotic systems for lower limb rehabilitation. IETE Technical Review, 41(1), 98-109.

Carvalho, C. R., Fernández, J. M., Del-Ama, A. J., Oliveira Barroso, F., & Moreno, J. C. (2023). Review of electromy-ography onset detection methods for real-time control of robotic exoskeletons. Journal of NeuroEngineering and Re-habilitation, 20(1), 141.

Asghar, A., Jawaid Khan, S., Azim, F., Shakeel, C. S., Hussain, A., & Niazi, I. K. (2022). Review on electromyography based intention for upper limb control using pattern recognition for human-machine interaction. Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine, 236(5), 628-645.

Sánchez-Manchola, M., Arciniegas-Mayag, L., Múnera, M., Bourgain, M., Provot, T., & Cifuentes, C. A. (2023). Effects of stance control via hidden Markov model-based gait phase detection on healthy users of an active hip-knee exo-skeleton. Frontiers in Bioengineering and Biotechnology, 11, 1021525.

Chen, L., Yan, X., & Hu, D. (2023). A deep learning control strategy of IMU-based joint angle estimation for hip pow-er-assisted swimming exoskeleton. IEEE Sensors Journal, 23(13), 15058-15070.

Anam, K., Setiowati, A., Nurrachmad, L., Indardi, N., Azmi, D. A. N., Aditia, E. A., ... & Kozina, Z. (2024). Injury Risk Analysis of Soccer Academy Students: Review of Functional Movement Screen Scores and Demographic Data. Retos: nuevas tendencias en educación física, deporte y recreación, (55), 900-907.

Khader, A., Zyout, A. A., & Al Fahoum, A. (2024). Combining enhanced spectral resolution of EMG and a deep learn-ing approach for knee pathology diagnosis. Plos one, 19(5), e0302707.

Park, H., Han, S., Sung, J., Hwang, S., Youn, I., & Kim, S. J. (2023). Classification of gait phases based on a machine learning approach using muscle synergy. Frontiers in Human Neuroscience, 17, 1201935.

Low, W. S., Goh, K. Y., Goh, S. K., Yeow, C. H., Lai, K. W., Goh, S. L., ... & Chan, C. K. (2023). Lower extremity kinematics walking speed classification using long short-term memory neural frameworks. Multimedia Tools and Ap-plications, 82(7), 9745-9760.

Katmah, R., Al Shehhi, A., Jelinek, H. F., Hulleck, A. A., & Khalaf, K. (2023). A Systematic Review of Gait Analysis in the Context of Multimodal Sensing Fusion and AI. IEEE Transactions on Neural Systems and Rehabilitation Engineer-ing.

Siegel, F., Buj, C., Merfort, R., Hein, A., & Müller-von Aschwege, F. (2024). Evaluating the Viability of Neural Net-works for Analysing Electromyography Data in Home Rehabilitation: Estimating Foot Progression Angle. In BIO-STEC (2) (pp. 132-141).

Wang, T., Song, Z., Wen, H., & Liu, C. (2024). Lower-Extremity Exoskeleton for Human Spinal Cord Injury: A Com-prehensive Review. IEEE Open Journal of the Industrial Electronics Society.

Mobarak, R., Mengarelli, A., Verdini, F., Al-Timemy, A. H., Fioretti, S., Burattini, L., & Tigrini, A. (2024, June). Neu-romechanical-Driven Ankle Angular Position Control During Gait Using Minimal Setup and LSTM Model. In 2024 IEEE International Symposium on Medical Measurements and Applications (MeMeA) (pp. 1-6). IEEE.

Hussain, I., Kim, S. E., Kwon, C., Hoon, S. K., Kim, H. C., Ku, Y., & Ro, D. H. (2024). Estimation of patient-reported outcome measures based on features of knee joint muscle co-activation in advanced knee osteoarthritis. Sci-entific Reports, 14(1), 12428.

Evans, S. (2024). Sacroiliac Joint Dysfunction in Endurance Runners Using Wearable Technology as a Clinical Monitor-ing Tool: Systematic Review. JMIR Biomedical Engineering, 9, e46067.

Porras, V. A., Pedersini, P., Fernández, A. P., Morales, C. R., Bermejo, P. G., Costa, I. R., & Villafañe, H. (2024). Exploring the impact of cervical multifidus muscle morphology on postural balance in post-stroke patients: A pilot study. Retos: nuevas tendencias en educación física, deporte y recreación, (54), 216-223.

Wang, X., Yu, H., Kold, S., Rahbek, O., & Bai, S. (2023). Wearable sensors for activity monitoring and motion control: A review. Biomimetic Intelligence and Robotics, 3(1), 100089.

Cheng, X., Fong, J., Tan, Y., & Oetomo, D. (2022, July). Investigating User Volitional Influence on Step Length in Powered Exoskeleton Designed for Users with SCI. In 2022 International Conference on Rehabilitation Robotics (ICORR) (pp. 1-6). IEEE.

Dong, M., Fang, B., Li, J., Sun, F., & Liu, H. (2021). Wearable sensing devices for upper limbs: A systematic review. Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine, 235(1), 117-130.

Khan, A., Galarraga, O., Garcia-Salicetti, S., & Vigneron, V. (2024). Deep Learning for Quantified Gait Analysis: A Systematic Literature Review. IEEE Access.

Di Nardo, F., Cucchiarelli, A., Scalise, L., & Morbidoni, C. (2022). Measurement of stride time by machine learning: sensitivity analysis for the simplification of the experimental protocol. IEEE Transactions on Instrumentation and Measurement, 71, 1-9.

Hodossy, B. K., & Farina, D. (2023). Shared Autonomy Locomotion Synthesis With a Virtual Powered Prosthetic Ankle. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 31, 4738-4748.

Hao, Y., Zhang, C., Lu, Y., Zhang, L., Lei, Z., & Li, Z. (2024). A novel autoencoder modeling method for intelligent assessment of bearing health based on Short-Time Fourier Transform and ensemble strategy. Precision Engineering, 85, 89-101.

Palacio, C., Hovorka, M., Acosta, M., Bautista, R., Chen, C., & Hovorka, J. (2024). Predicting Factors for Extremity Fracture among Border-Fall Patients Using Machine Learning Computing. Heliyon.

Omarov, B., Suliman, A., Kushibar, K. (2016). Face recognition using artificial neural networks in parallel architecture. Journal of Theoretical and Applied Information Technology 91 (2), pp. 238-248. Open Access.

Nguyen, T., Tran, K. D., Raza, A., Nguyen, Q. T., Bui, H. M., & Tran, K. P. (2023). Wearable technology for smart manufacturing in industry 5.0. In Artificial Intelligence for Smart Manufacturing: Methods, Applications, and Chal-lenges (pp. 225-254). Cham: Springer International Publishing.

Kendzhaeva, B., Omarov, B., Abdiyeva, G., Anarbayev, A., Dauletbek, Y., & Omarov, B. (2021). Providing safety for citizens and tourists in cities: a system for detecting anomalous sounds. In Advanced Informatics for Computing Re-search: 4th International Conference, ICAICR 2020, Gurugram, India, December 26–27, 2020, Revised Selected Papers, Part I 4 (pp. 264-273). Springer Singapore.

Lu, C., Qi, Q., Liu, Y., Li, D., Xian, W., Wang, Y., ... & Xu, X. (2024). Exoskeleton Recognition of Human Move-ment Intent Based on Surface Electromyographic Signals. IEEE Access.

Omarov, B., Omarov, N., Mamutov, Q., Kissebaev, Z., Anarbayev, A., Tastanov, A., & Yessirkepov, Z. (2024). Exami-nation of the augmented reality exercise monitoring system as an adjunct tool for prospective teacher trainers. Retos: nuevas tendencias en educación física, deporte y recreación, (58), 85-94.

Liu, J., Wang, C., He, B., Li, P., & Wu, X. (2022). Metric learning for robust gait phase recognition for a lower limb exoskeleton robot based on sEMG. IEEE Transactions on Medical Robotics and Bionics, 4(2), 472-479.

Khiabani, H., & Ahmadi, M. (2021, August). A classical machine learning approach for emg-based lower limb intention detection for human-robot interaction systems. In 2021 IEEE International Conference on Autonomous Systems (ICAS) (pp. 1-5). IEEE.

Sedighi, P., Li, X., & Tavakoli, M. (2023). Emg-based intention detection using deep learning for shared control in up-per-limb assistive exoskeletons. IEEE Robotics and Automation Letters.

Tursynova, A., Omarov, B., Tukenova, N., Salgozha, I., Khaaval, O., Ramazanov, R., & Ospanov, B. (2023). Deep learning-enabled brain stroke classification on computed tomography images. Computers, Materials & Continua, 75(1), 1431-1446.

Blanco-Diaz, C. F., Guerrero-Mendez, C. D., de Andrade, R. M., Badue, C., De Souza, A. F., Delisle-Rodriguez, D., & Bastos-Filho, T. (2024). Decoding lower-limb kinematic parameters during pedaling tasks using deep learning ap-proaches and EEG. Medical & Biological Engineering & Computing, 1-17.

Descargas

Publicado

2024-12-01

Cómo citar

Amanov, B., & Ibrayev, S. (2024). Mejorando la ortopedia y medicina deportiva con el control de exoesqueletos de miembros inferiores en rehabilitación utilizando la clasificación de señales de electromiografía basada en aprendizaje profundo (Enhancing orthopedics and sports medicine with lower limb exoskeleton control in rehabilitation using deep learning based electromyography signal classification). Retos, 61, 616–625. https://doi.org/10.47197/retos.v61.109799

Número

Sección

Artículos de carácter científico: trabajos de investigaciones básicas y/o aplicadas