Mejorando el entrenamiento de peso muerto a través de un sistema de coaching personal impulsado por inteligencia artificial utilizando análisis esquelético (Enhancing deadlift training through an artificial intelligence-driven personal coaching system using skeletal analysis)

Autores/as

  • Bolganay Kaldarova South Kazakhstan State Pedagogical University
  • Aigerim Toktarova Khoja Akhmet Yassawi International Kazakh-Turkish University
  • Rustam Abdrakhmanov International University of Tourism and Hospitality

DOI:

https://doi.org/10.47197/retos.v60.109183

Palabras clave:

coaching impulsado por IA, entrenamiento de peso muerto, análisis esquelético, PoseNet, aprendizaje profundo, monitoreo de ejercicio, retroalimentación en tiempo real

Resumen

Este artículo presenta un innovador sistema de entrenamiento personal impulsado por inteligencia artificial diseñado para mejorar el entrenamiento de peso muerto mediante técnicas avanzadas de análisis esquelético y aprendizaje profundo. El sistema propuesto emplea el modelo PoseNet para capturar y analizar secuencias de video en tiempo real, extrayendo coordenadas de puntos clave y ángulos esqueléticos para monitorear con precisión la postura y los movimientos del usuario. Utilizando métodos de Histogramas Locales de Gradientes Orientados (LHOG) e Histogramas Locales de Flujo Óptico (LHOF), el sistema realiza una extracción de características integral, evaluando tanto los aspectos estáticos como dinámicos del ejercicio. El modelo de aprendizaje profundo, entrenado con un extenso conjunto de datos de ejecuciones correctas e incorrectas de peso muerto, clasifica la corrección del ejercicio con alta precisión, proporcionando retroalimentación en tiempo real y recomendaciones personalizadas a los usuarios. Esta retroalimentación correctiva inmediata facilita ajustes rápidos, reduce el riesgo de lesiones y promueve una técnica adecuada, mejorando la eficacia general del entrenamiento de fuerza. La capacidad del sistema para ofrecer retroalimentación específica para cada usuario, adaptada a estructuras corporales y patrones de movimiento individuales, asegura su relevancia y efectividad en diversos entornos de entrenamiento. Las aplicaciones prácticas de este sistema abarcan gimnasios, centros de rehabilitación y entornos domésticos, convirtiéndolo en una herramienta valiosa para entrenadores personales y fisioterapeutas. Aunque el estudio demuestra un potencial significativo, también identifica áreas para futuras investigaciones, incluyendo el refinamiento de algoritmos, la expansión del conjunto de datos y la integración de métricas y tecnologías adicionales. En conjunto, el sistema propuesto representa un avance sustancial en el monitoreo y mejora del ejercicio, contribuyendo al campo más amplio de las tecnologías de salud y fitness impulsadas por inteligencia artificial y allanando el camino para rutinas de entrenamiento de fuerza más seguras y efectivas.

Palabras clave: coaching impulsado por IA, entrenamiento de peso muerto, análisis esquelético, PoseNet, aprendizaje profundo, monitoreo de ejercicio, retroalimentación en tiempo real.

Abstract. This paper presents an innovative AI-driven personal coaching system designed to enhance deadlift training through advanced skeletal analysis and deep learning techniques. The proposed system employs the PoseNet model to capture and analyze real-time video feeds, extracting keypoint coordinates and skeletal angles to monitor user posture and movements accurately. Utilizing Local Histograms of Oriented Gradients (LHOG) and Local Histograms of Optical Flow (LHOF) methods, the system performs comprehensive feature extraction, assessing both static and dynamic aspects of the exercise. The deep learning model, trained on an extensive dataset of correctly and incorrectly performed deadlifts, classifies the correctness of the exercise with high accuracy, providing real-time feedback and personalized recommendations to users. This immediate corrective feedback facilitates prompt adjustments, reduces injury risk, and promotes proper technique, enhancing the overall efficacy of strength training. The system's ability to offer user-specific feedback, tailored to individual body structures and movement patterns, ensures relevance and effectiveness in diverse training environments. Practical applications of this system span gyms, rehabilitation centers, and home settings, making it a valuable tool for personal trainers and physiotherapists. While the study demonstrates significant potential, it also identifies areas for future research, including algorithm refinement, dataset expansion, and integration of additional metrics and technologies. Overall, the proposed system represents a substantial advancement in exercise monitoring and improvement, contributing to the broader field of AI-driven fitness and health technologies, and paving the way for safer and more effective strength training routines.

Keywords: AI-driven coaching, deadlift training, skeletal analysis, PoseNet, deep learning, exercise monitoring, real-time feedback.

Citas

Hart, R., Smith, H., & Zhang, Y. (2024). The development of an automated assessment system for resistance training movement. Sports Biomechanics, 1-33.

Washif, J., Pagaduan, J., James, C., Dergaa, I., & Beaven, C. (2024). Artificial intelligence in sport: Exploring the poten-tial of using ChatGPT in resistance training prescription. Biology of sport, 41(2), 209-220.

Balsalobre-Fernández, C., Xu, J., Jarvis, P., Thompson, S., Tannion, K., & Bishop, C. (2023). Validity of a Smartphone App Using Artificial Intelligence for the Real-Time Measurement of Barbell Velocity in the Bench Press Exercise. The Journal of Strength & Conditioning Research, 37(12), e640-e645.

Chariar, M., Rao, S., Irani, A., Suresh, S., & Asha, C. S. (2023). AI trainer: Autoencoder based approach for squat anal-ysis and correction. IEEE Access.

Chen, C. H., Wu, S. H., Shiu, Y. J., Yu, S. Y., & Chiu, C. H. (2023). Acute enhancement of Romanian deadlift perfor-mance after consumption of caffeinated chewing gum. Scientific Reports, 13(1), 22016.

Mahmoud, S. E. H., & Taha, Z. A. E. H. (2023, July). AI Personal Trainer for Lateral Raises and Shoulder Presses Exer-cises. In 2023 Intelligent Methods, Systems, and Applications (IMSA) (pp. 118-123). IEEE.

Omarov, B., Suliman, A., & Tsoy, A. (2016). Parallel backpropagation neural network training for face recognition. Far East Journal of Electronics and Communications, 16(4), 801-808.

Omarov, B., Narynov, S., Zhumanov, Z., Gumar, A., Khassanova, M. (2022). A skeleton-based approach for campus violence detection. Computers, Materials & Continua, 72(1), 315-331. https://doi.org/10.32604/cmc.2022.024566

Støve, M. P., & Hansen, E. C. K. (2022). Accuracy of the Apple Watch Series 6 and the Whoop Band 3.0 for assessing heart rate during resistance exercises. Journal of Sports Sciences, 40(23), 2639-2644.

Kumar, G. K., Bangare, M. L., Bangare, P. M., Kumar, C. R., Raj, R., Arias-Gonzáles, J. L., ... & Mia, M. S. (2024). Internet of things sensors and support vector machine integrated intelligent irrigation system for agriculture industry. Discover Sustainability, 5(1), 6.

Tursynova, A., Omarov, B., Sakhipov, A., & Tukenova, N. (2022). Brain Stroke Lesion Segmentation Using Computed Tomography Images based on Modified U-Net Model with ResNet Blocks. International Journal of Online & Biomed-ical Engineering, 18(13).

Babu, A. H., Shanthakumar, S., & Malarselvi, G. (2024, July). Live gym tracker using artificial intelligence. In AIP Con-ference Proceedings (Vol. 3075, No. 1). AIP Publishing.

Ho, I. M. K., Weldon, A., Yong, J. T. H., Lam, C. T. T., & Sampaio, J. (2023). Using machine learning algorithms to pool data from meta-analysis for the prediction of countermovement jump improvement. International Journal of En-vironmental Research and Public Health, 20(10), 5881.

Farrokhi, A., Rezazadeh, J., Farahbakhsh, R., & Ayoade, J. (2022). A decision tree-based smart fitness framework in IoT. SN Computer Science, 3(1), 2.

Garg, B. (2023). Deep Learning Approach to Skeletal Performance Evaluation of Physical Therapy Exercises. University of California, San Diego.

Ishida, A., Bazyler, C. D., Suarez, D. G., Slaton, J. A., White, J. B., & Stone, M. H. (2023). The difference between several neuromuscular tests for monitoring resistance-training induced fatigue. Journal of Sports Sciences, 41(3), 209-216.

Steele, J., Fisher, J. P., Giessing, J., Androulakis-Korakakis, P., Wolf, M., Kroeske, B., & Reuters, R. (2023). Long-term time-course of strength adaptation to minimal dose resistance training through retrospective longitudinal growth modeling. Research Quarterly for Exercise and Sport, 94(4), 913-930.

Omarov, B., Narynov, S., & Zhumanov, Z. (2023). Artificial intelligence-enabled chatbots in mental health: a systematic review. Comput. Mater. Continua 74, 5105–5122 (2022).

Morán-Navarro, R., Martínez-Cava, A., Escribano-Peñas, P., & Courel-Ibáñez, J. (2021). Load-velocity relationship of the deadlift exercise. European journal of sport science, 21(5), 678-684.

Tursynova, A., & Omarov, B. (2021, November). 3D U-Net for brain stroke lesion segmentation on ISLES 2018 dataset. In 2021 16th International Conference on Electronics Computer and Computation (ICECCO) (pp. 1-4). IEEE.

Aasa, U., Bengtsson, V., Berglund, L., & Öhberg, F. (2022). Variability of lumbar spinal alignment among power-and weightlifters during the deadlift and barbell back squat. Sports biomechanics, 21(6), 701-717.

Enes, A., Leonel, D. F., Oneda, G., Alves, R. C., Zandoná-Schmidt, B. A., Ferreira, L. H. B., ... & Souza-Junior, T. P. (2023). Muscular adaptations and psychophysiological responses in resistance training systems. Research Quarterly for Exercise and Sport, 94(4), 982-989.

Lee, S., Lim, Y., & Lim, K. (2024). Multimodal sensor fusion models for real-time exercise repetition counting with IMU sensors and respiration data. Information Fusion, 104, 102153.

Rahman, A., Saji, A., Teresa, A., Nair, D. R., & Saritha, S. (2024, June). Physical Exercise Classification from Body Keypoints Using Machine Learning Techniques. In 2024 3rd International Conference on Applied Artificial Intelli-gence and Computing (ICAAIC) (pp. 504-510). IEEE.

Romdhani, A., Sahli, F., Trabelsi, O., Rebhi, M., Ghouili, H., Sahli, H., ... & Zghibi, M. (2024). Peer Verbal Encour-agement Is More Effective than Coach Encouragement in Enhancing CrossFit-Specific 1-RM Strength, Functional En-durance, and Psychophysiological Assessment Performance. Sports, 12(3), 64.

Lester, M., Peeling, P., Girard, O., Murphy, A., Armstrong, C., & Reid, M. (2023). From The Ground Up: Expert Perceptions of Lower Limb Activity Monitoring in Tennis. Journal of Sports Science & Medicine, 22(1), 133.

Rethinam, P., Manoharan, S., Kirupakaran, A. M., Srinivasan, R., Hegde, R. S., & Srinivasan, B. (2023, September). Olympic Weightlifters' Performance Assessment Module Using Computer Vision. In 2023 IEEE International Work-shop on Sport, Technology and Research (STAR) (pp. 8-12). IEEE.

Masel, S., & Maciejczyk, M. (2023). Post-activation effects of accommodating resistance and different rest intervals on vertical jump performance in strength trained males. BMC Sports Science, Medicine and Rehabilitation, 15(1), 65.

Choi, W., Choi, T., & Heo, S. (2023). A Comparative Study of Automated Machine Learning Platforms for Exercise Anthropometry-Based Typology Analysis: Performance Evaluation of AWS SageMaker, GCP VertexAI, and MS Az-ure. Bioengineering, 10(8), 891.

Yang, T. J., Shiu, Y. J., Chen, C. H., Yu, S. Y., Hsu, Y. Y., & Chiu, C. H. (2024). Carbohydrate Mouth Rinses before Exercise Improve Performance of Romanian Deadlift Exercise: A Randomized Crossover Study. Nutrients, 16(8), 1248.

Schlegel, P., & Polívka, T. (2024). Beyond the intensity: A systematic review of rhabdomyolysis following high-intensity functional training. Apunts Sports Medicine, 59(223), 100447.

Sisinni, E., Depari, A., Bellagente, P., Ferrari, P., Flammini, A., Pasetti, M., & Rinaldi, S. (2022, August). On feature selection in automatic detection of fitness exercises using LSTM models. In 2022 IEEE Sensors Applications Symposi-um (SAS) (pp. 1-6). IEEE.

Balaji, A. N., & Peh, L. S. (2023). AI-On-Skin: Towards Enabling Fast and Scalable On-body AI Inference for Wearable On-Skin Interfaces. Proceedings of the ACM on Human-Computer Interaction, 7(EICS), 1-34.

Pekas, D., Radaš, J., Baić, M., Barković, I., & Čolakovac, I. (2023). The use of wearable monitoring devices in sports sciences in COVID years (2020–2022): a systematic review. Applied Sciences, 13(22), 12212.

Külkamp, W., Bishop, C., Kons, R., Antunes, L., Carmo, E., Hizume-Kunzler, D., & Dal Pupo, J. (2024). Concurrent validity and technological error-based reliability of a novel device for velocity-based training. Measurement in Physi-cal Education and Exercise Science, 28(1), 15-26.

Vargas-Molina, S., García-Sillero, M., Bonilla, D. A., Petro, J. L., García-Romero, J., & Benítez-Porres, J. (2024). The effect of the ketogenic diet on resistance training load management: a repeated-measures clinical trial in trained par-ticipants. Journal of the International Society of Sports Nutrition, 21(1), 2306308.

Kons, R. L., Detanico, D., Costa, F. E., Franchini, E., Dopico-Calvo, X., Morales Aznar, J., ... & Weldon, A. (2024). Strength and conditioning practices of judo coaches. International Journal of Sports Science & Coaching, 19(2), 573-585.

Omarov, B., Batyrbekov, A., Suliman, A., Omarov, B., Sabdenbekov, Y., & Aknazarov, S. (2020, November). Electron-ic stethoscope for detecting heart abnormalities in athletes. In 2020 21st International Arab Conference on Infor-mation Technology (ACIT) (pp. 1-5). IEEE.

Champ, C. E., Peluso, C., Carenter, D. J., Rosenberg, J., Velasquez, F., Annichine, A., ... & Hilton, C. (2024). EX-ERT-BC: Prospective Study of an Exercise Regimen After Treatment for Breast Cancer. Sports Medicine Interna-tional Open, 8(continuous publication).

Omarov, B., Narynov, S., Zhumanov, Z., Gumar, A., & Khassanova, M. (2022). State-of-the-art violence detection techniques in video surveillance security systems: a systematic review. PeerJ Computer Science, 8, e920.

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.

Widodo, A., Irianto, J. P., Graha, A. S., Yudanto, Y., Hardianto, D., Sutapa, P., ... & Pratama, K. W. (2024). The Per-sonalized System of E-Modul Instructions in Physical Education Online Learning. Retos: nuevas tendencias en edu-cación física, deporte y recreación, (56), 319-327.

Nurhidayah, D., Prasetyo, Y., Sutapa, P., Mitsalina, D., Yuliana, E., & Pambudi, T. (2024). Relationship exercise moti-vation levels on quality of life during retirement from elite sport. Retos: nuevas tendencias en educación física, de-porte y recreación, (56), 433-438.

Babaskin, D., Masharipov, F., Savinkova, O., Shustikova, N., Volkova, N., & Chakalova, A. (2024). Functional state of team sports athletes in the annual training cycle. Retos: Nuevas Perspectivas de Educación Física, Deporte y Rec-reación, 54.

Descargas

Publicado

2024-10-02

Cómo citar

Kaldarova, B., Toktarova, A., & Abdrakhmanov, R. (2024). Mejorando el entrenamiento de peso muerto a través de un sistema de coaching personal impulsado por inteligencia artificial utilizando análisis esquelético (Enhancing deadlift training through an artificial intelligence-driven personal coaching system using skeletal analysis). Retos, 60, 439–448. https://doi.org/10.47197/retos.v60.109183

Número

Sección

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