Sıçramadan Sonra Yere İniş Hata Puanlama Sistemi’nin Yapay Zeka İle Belirlenmesi

Öz

Amaç: Çalışmada, Adaptive Boosting (AdaBoost) algoritması ile Sıçramadan Sonra Yere İniş Hata Puanlama Sistemi (SSYİ-HPS) sonuçlarının öngörülebilirliğinin incelenmesi amaçlanmıştır. Materyal ve Metot: Puanlama sistemini daha da kısaltmak için yapay zeka yardımıyla bir model geliştirilmiştir. Veri ön işleme aşamasında, orijinal veri setinde yer alan 17 farklı madde 13'e düşürülmüştür. Çalışmada kullanılan veri setinde toplam 3790 veri yer almış ve veri seti 4 farklı alt veri setine ayrılmıştır. Regresyon için kullanılan beş farklı makine öğrenim modelinden en yüksek doğruluğu veren AdaBoost seçilmiştir. Modelin başarısı, önerilen AdaBoost modelinin performans metrikleri ile test edilmesiyle değerlendirilmiştir. Bulgular: SSYİ-HPS'de klinisyen tarafından verilen hata puanı %0-86,6 aralığındaydı. Önerilen AdaBoost modelinde sırasıyla Sub1, Sub2, Sub3 ve Sub4 için %98, %87, %88, %89 doğruluk sağlanmıştır. Sonuç: Araştırmada önerilen model ile SSYİ-HPS’nin 8., 10., 16. ve 17. maddelerine verilen puan yüksek doğrulukla tahmin edilebilmekte ve toplam puana ulaşılabilmektedir.

Anahtar Kelimeler

• AdaBoost modeli
• sıçrama
• sıçramadan sonra yere iniş hata puanlama sistemi
• veri seti
• yapay zeka

Determining the Landing Error Scoring System after a Jump by Artificial Intelligence

Abstract

Objective: The study aims to examine the predictability of the Landing Error Scoring System (LESS) results after the jump with the Adaptive Boosting (AdaBoost) algorithm. Materials and Methods: A model has been developed by artificial intelligence to shorten the scoring system significantly. In the data preprocessing stage, 17 different items contained in the original dataset were reduced to 13. A total of 3790 data items were included in the dataset used in the study, and the dataset was divided into 4 different sub-datasets. AdaBoost was chosen to give the highest accuracy tested in five different machine learning used for regression. The model's reliability was evaluated by testing the proposed AdaBoost model with performance metrics. Results: The error score given by the clinician in the LESS was in the range of 0-86.6%. Recommended AdaBoost model for Sub1, Sub2, Sub3, and Sub4 respectively 98%, 87%, 88%, 89% accuracy has been achieved. Conclusions: The score given to the LESS's 8th, 10th, 16th, and 17th items can be predicted with high accuracy, and the total score can be reached through the model proposed in the research.

Keywords

• AdaBoost model
• artificial intelligence
• dataset
• jump
• landing error scoring system

References

1. 1. Alahmari A, Herrington L, Jones R. Concurrent validity of two-dimensional video analysis of lower-extremity frontal plane of movement during multidirectional single-leg landing. Phys Ther Sport. 2020;42:40-45. doi:10.1016/j.ptsp.2019.12.009
2. 2. Padua DA, DiStefano LJ, Beutler AI, De La Motte SJ, DiStefano MJ, Marshall SW. The landing error scoring system as a screening tool for an anterior cruciate ligament injury–prevention program in elite-youth soccer athletes. J Athl Train. 2015;50(6):589-595. doi:10.4085/1062-6050-50.1.10
3. 3. James J, Ambegaonkar JP, Caswell SV, Onate J, Cortes N. Analyses of landing mechanics in division I athletes using the landing error scoring system. Sports Health. 2016;8(2):182-186. doi:10.1177/1941738115624891
4. 4. Peebles AT, Arena SL, Queen RM. A new method for assessing landing kinematics in non-laboratory settings. Phys Ther Sport. 2021;49:21-30. doi:10.1016/j.ptsp.2021.01.012
5. 5. Rabin A, Einstein O, Kozol Z. Agreement between visual assessment and 2-dimensional analysis during jump landing among healthy female athletes. J Athl Train. 2018;53(4):386-394. doi:10.4085/1062-6050-237-16
6. 6. Padua DA, Marshall SW, Boling MC, Thigpen CA, Garrett JrWE, Beutler AI. The landing error scoring system (LESS) is a valid and reliable clinical assessment tool of jump-landing biomechanics: the JUMP-ACL study. Am J Sports Med. 2009;37(10):1996-2002. doi:10.1177/0363546509343200
7. 7. Hanzlíková I, Athens J, Hébert-Losier K. Factors influencing the landing error scoring system: Systematic review with meta-analysis. J Sci Med Sport. 2021;24(3):269-280. doi:10.1016/j.jsams.2020.08.013
8. 8. Hanzlíková I, Hébert-Losier K. Is the landing error scoring system reliable and valid? A systematic review. Sports Health. 2020;12(2):181-188. doi:10.1177/1941738119886593

9. 9. Beese ME, Joy E, Switzler CL, Hicks-Little CA. Landing error scoring system differences between single-sport and multi-sport female high school–aged athletes. J Athl Train. 2015;50(8):806-811. doi:10.4085/1062-6050-50.7.01
10. 10. Smith HC, Johnson RJ, Shultz SJ, et al. A prospective evaluation of the landing error scoring system (LESS) as a screening tool for anterior cruciate ligament injury risk. Am J Sports Med. 2012;40(3):521-6. doi:10.1177/0363546511429776
11. 11. Dar G, Yehiel A, Cale’Benzoor M. Concurrent criterion validity of a novel portable motion analysis system for assessing the landing error scoring system (LESS) test. Sports Biomech. 2019;18(4):426-436. doi:10.1080/14763141.2017.1412495
12. 12. Fister I, Fister D, Deb S, Mlakar U, Brest J. Post hoc analysis of sport performance with differential evolution. Neural Comput & Applic. 2020;32:10799-10808
13. 13. Rajšp A, Fister I. A systematic literature review of intelligent data analysis methods for smart sport training. Appl Sci. 2020;10(9):3013. doi:10.3390/app10093013
14. 14. Rigamonti L, Albrecht UV, Lutter C, Tempel M, Wolfarth B, Back DA. Potentials of digitalization in sports medicine: a narrative review. Curr Sports Med Rep. 2020;19(4):157-163. doi:10.1249/JSR.0000000000000704
15. 15. Schmidt SL. 21st Century Sports: How Technologies Will Change Sports in the Digital Age. 1st ed. Cham, Switzerland: Springer Nature; 2020.
16. 16. Emmert-Streib F, Dehmer M. Evaluation of regression models: Model assessment, model selection and generalization error. Mach Learn Knowl Extr. 2019; 1(1): 521-551. doi:10.3390/make1010032
17. 17. Haste T, Tibshirani R, Friedman J. The elements of statistical learning: Data mining, inference and prediction. New York, USA: Springer; 2009.
18. 18. Wang R. AdaBoost for feature selection, classification, and its relation with SVM, a review. Physics Procedia. 2012;25:800-807. doi:10.1016/j.phpro.2012.03.160
19. 19. Chicco D, Jurman G. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC genomics. 2020; 21(6): 1-13. doi: 10.1186/s12864-019-6413-7
20. 20. Phasinam K, Mondal T, Novaliendry D, Yang CH, Dutta C, Shabaz M. Analyzing the performance of machine learning techniques in disease prediction. J Food Qual. 2022; 2022: 1-9. doi.org/10.1155/2022/7529472
21. 21. Akosa JS. Predictive accuracy: a misleading performance measure for highly imbalanced data. In: Proceedings of the SAS Global Forum 2017 Conference. Cary, North Carolina: SAS Institute Inc.; 2017: 942–2017.
22. 22. Baldi P, Brunak S, Chauvin Y, Andersen C, Nielsen H. Assessing the accuracy of prediction algorithms for classification: an overview. Bioinformatics. 2000; 16(5): 412–424.
23. 23. Gensler A, Sick B. Novel criteria to measure performance of time series segmentation techniques. In LWA. 2014: 193-204.
24. 24. Mauntel TC, Padua DA, Stanley LE, et al. Automated quantification of the landing error scoring system with a markerless motion-capture system. J Athl Train. 2017;52(11):1002-1009. doi:10.4085/1062-6050-52.10.12
25. 25. Ratten V. Sport technology: A commentary. J High Technol Manag Res. 2020;31(1):100383. doi:10.1016/j.hitech.2020.100383
26. 26. Farrokhi A, Farahbakhsh R, Rezazadeh J, Minerva R. Application of internet of things and artificial intelligence for smart fitness: A survey. Computer Networks. 2021;107859. doi:10.1016/j.comnet.2021.107859
27. 27. Taborri J, Molinaro L, Santospagnuolo A, Vetrano M, Vulpiani MC, Rossi S. A machine-learning approach to measure the anterior cruciate ligament injury risk in female basketball players. Sensors. 2021; 21(9):3141. doi:10.3390/s21093141