Farklı Ağırlıklar ile Yapılan Squat Sıçramanın Makine Öğrenme Yöntemleri ile Değerlendirilmesi

Öz

Kuvvet-Hız profili sporcunun performansının ve uygun olan antrenman programının belirlenmesi için hem antrenörler hem de araştırmacılar tarafından sıklıkla kullanılan bir test yöntemidir. Ancak test protokolünde sporcunun yüksek ağırlıklar ve çok sayıda tekrar yapması hem sporcu yaralanmasına hem de yorgunluk kaynaklı performansın doğru ölçülememesine sebep olmaktadır. Bu sebeple çalışma kapsamında farklı ağırlıklardaki sıçrama yüksekliğinin tek tekrarlı ölçüm verisi kullanılarak makine öğrenme modeller ile tahmin edilmesi amaçlanmıştır. Çalışmaya Akdeniz Üniversitesi’nde öğrenim gören 52 sporcu katılmıştır. Tüm katılımcıların öncelikle demografik özellikleri, ardından dikey sıçrama protokolüne göre dört farklı ağırlıkta sıçrama yükseklikleri belirlenmiştir. Ölçülen veriler normalize edilerek makine öğrenme modellerine girdi olarak verilmiş ve dikey sıçrama yükseklikleri tahmin edilmiştir. Beş farklı makine öğrenme modeli arasından dikey sıçrama yüksekliğini en yüksek başarı ile tahmin eden makine öğrenme modeli Gaussian Süreç Regresyonu olduğu gözlenmiştir. Sporcularda yaralanmaya sebep olabilecek yüksek ağırlıklardaki farklı sayıda sıçrama yerine tek tekrarlı sıçrama yaparak diğer ağırlıklardaki sıçrama yüksekliğinin belirlenmesi ile çalışmanın literatüre hem sporcu sağlığı hem de testin daha rahat uygulanabilirliği açısından literatüre katkı sağlaması beklenmektedir.

Anahtar Kelimeler

• Kuvvet-Hız Profili
• Dikey Sıçrama
• Makine Öğrenme

Evaluation of Squat Jumping with Different Weights by Machine Learning

Abstract

The Force-Velocity profile is a test method that is frequently used by both trainers and researchers to determine the athlete's performance and the appropriate training program. However, performing a large number of repetitions under high weights in the test protocol causes both athlete injury and failure to measure performance due to fatigue. For this reason, within the scope of the study, it is aimed to predict the jump height at different weights with machine learning models using single repetitive measurement data. 52 athletes studying at Akdeniz University participated in the study. First of all, demographic characteristics of all participants were measured, and then jump heights were determined at four different weights according to the vertical jump protocol. The measured data were normalized and given as input to the machine learning models and the vertical jump heights were estimated. It has been observed that the machine learning model that predicts the vertical jump distance with the highest success among the five different machine learning models is the Gaussian Process Regression. It is expected that the study will contribute to the literature in terms of both athlete health and the easier applicability of the test by determining the jump distance by making a single repetitive jump instead of different numbers of jumps at high weights that may cause injury to the athletes.

Keywords

• Force-Velocity profile
• Vertical Jump
• Machine Learning

Kaynakça

1. Alcazar, J., Csapo, R., Ara, I., & Alegre, L. M. (2019). On the shape of the force-velocity relationship in skeletal muscles: The linear, the hyperbolic, and the double-hyperbolic. Frontiers in physiology, 769.
2. Alcazar, J., Pareja-Blanco, F., Rodriguez-Lopez, C., Navarro-Cruz, R., Cornejo-Daza, P. J., Ara, I., & Alegre, L. M. (2021). Comparison of linear, hyperbolic and double-hyperbolic models to assess the force–velocity relationship in multi-joint exercises. European Journal of Sport Science, 21(3), 359-369.
3. Byrne, C., & Eston, R. (2002). The effect of exercise-induced muscle damage on isometric and dynamic knee extensor strength and vertical jump performance. Journal of sports sciences, 20(5), 417-425.
4. Colyer, S. L., Stokes, K. A., Bilzon, J. L., Holdcroft, D., & Salo, A. I. (2018). Training-related changes in force–power profiles: implications for the skeleton start. International journal of sports physiology and performance, 13(4), 412-419.
5. Eston, R., Byrne, C., & Twist, C. (2003). Muscle function after exercise-induced muscle damage: Considerations for athletic performance in children and adults. Journal of Exercise Science and Fitness, 1(2), 85-96.
6. Falvo, M. J., & Bloomer, R. J. (2006). Review of exercise-induced muscle injury: relevance for athletic populations. Research in Sports Medicine, 14(1), 65-82.
7. Giroux, C., Rabita, G., Chollet, D., & Guilhem, G. (2015). What is the best method for assessing lower limb force-velocity relationship? International journal of sports medicine, 36(02), 143-149.
8. Gutierrez Becker, B., Klein, T., Wachinger, C., Alzheimer's Disease Neuroimaging, I., the Australian Imaging, B., & Lifestyle flagship study of, a. (2018). Gaussian process uncertainty in age estimation as a measure of brain abnormality. Neuroimage, 175, 246-258. https://doi.org/10.1016/j.neuroimage.2018.03.075

9. Jalil, N. A., Hwang, H. J., & Dawi, N. M. (2019). Machines learning trends, perspectives and prospects in education sector. Proceedings of the 2019 3rd International Conference on Education and Multimedia Technology.
10. Jaric, S. (2015). Force-velocity relationship of muscles performing multi-joint maximum performance tasks. International journal of sports medicine, 36(09), 699-704.
11. Jiménez-Reyes, P., Samozino, P., Brughelli, M., & Morin, J.-B. (2017). Effectiveness of an individualized training based on force-velocity profiling during jumping. Frontiers in physiology, 677.
12. Jordan, M. I., & Mitchell, T. M. (2015). Machine learning: Trends, perspectives, and prospects. Science, 349(6245), 255-260. https://doi.org/10.1126/science.aaa8415
13. Kotani, Y., Lake, J., Guppy, S. N., Poon, W., Nosaka, K., Hori, N., & Haff, G. G. (2021). Reliability of the Squat Jump Force-Velocity and Load-Velocity Profiles. Journal of Strength and Conditioning Research.
14. Markus, I., Constantini, K., Hoffman, J., Bartolomei, S., & Gepner, Y. (2021). Exercise-induced muscle damage: Mechanism, assessment and nutritional factors to accelerate recovery. European journal of applied physiology, 121(4), 969-992.
15. Morin, J.-B., Jiménez-Reyes, P., Brughelli, M., & Samozino, P. (2018). Jump height is a poor indicator of lower limb maximal power output: theoretical demonstration, experimental evidence and practical solutions.
16. Musa, R. M., Majeed, A. A., Taha, Z., Abdullah, M., Maliki, A. H. M., & Kosni, N. A. (2019). The application of Artificial Neural Network and k-Nearest Neighbour classification models in the scouting of high-performance archers from a selected fitness and motor skill performance parameters. Science & Sports, 34(4), e241-e249.
17. Page, P. (1995). Pathophysiology of acute exercise-induced muscular injury: clinical implications. Journal of athletic training, 30(1), 29.
18. Powers, S. K., & Jackson, M. J. (2008). Exercise-induced oxidative stress: cellular mechanisms and impact on muscle force production. Physiological reviews, 88(4), 1243-1276.
19. Raj, J. S., & Ananthi, J. V. (2019). Recurrent neural networks and nonlinear prediction in support vector machines. Journal of Soft Computing Paradigm (JSCP), 1(01), 33-40.
20. Samozino, P. (2018). A simple method for measuring lower limb force, velocity and power capabilities during jumping. In Biomechanics of training and testing (pp. 65-96). Springer.
21. Samozino, P., Edouard, P., Sangnier, S., Brughelli, M., Gimenez, P., & Morin, J.-B. (2014). Force-velocity profile: imbalance determination and effect on lower limb ballistic performance. International journal of sports medicine, 35(06), 505-510.
22. Samozino, P., Morin, J.-B., Hintzy, F., & Belli, A. (2008). A simple method for measuring force, velocity and power output during squat jump. Journal of biomechanics, 41(14), 2940-2945.
23. Uslu, S., Nüzket, T., & Uysal, H. (2018). Modified motor unit number index (MUNIX) algorithm for assessing excitability of alpha motor neuron in spasticity. Clinical neurophysiology practice, 3, 127-133.
24. Vapnik, V. (1999). The nature of statistical learning theory. Springer science & business media.
25. Vapnik, V., & Chapelle, O. (2000). Bounds on error expectation for support vector machines. Neural Computation, 12(9), 2013-2036. https://doi.org/Doi 10.1162/089976600300015042
26. Williams, C. K., & Rasmussen, C. E. (2006). Gaussian processes for machine learning (Vol. 2). MIT press Cambridge, MA.
27. Xu, M., Watanachaturaporn, P., Varshney, P. K., & Arora, M. K. (2005). Decision tree regression for soft classification of remote sensing data. Remote Sensing of Environment, 97(3), 322-336.
28. Zivkovic, M. Z., Djuric, S., Cuk, I., Suzovic, D., & Jaric, S. (2017). A simple method for assessment of muscle force, velocity, and power producing capacities from functional movement tasks. Journal of sports sciences, 35(13), 1287-1293.