SavedAdd your journal

Journals / Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi / 2026 / Cilt: 32 Sayı: 6

Performance prediction of hearing impaired athletes with tree-based algorithms

Ağaç tabanlı algoritmalarla işitme engelli sporcuların performans tahmini

Mustafa Mikail Özçiloğlu(KILIS 7 ARALIK UNIVERSITY)
Cemanur Aydınalp(ISTANBUL TECHNICAL UNIVERSITY)
Önder Karakoç(KILIS 7 ARALIK UNIVERSITY)
Pages
1285–1292
Publication Date
2026-10-08
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Model 11, including physical-based parameters (gender, weight, age, leg strength, subcutaneous fat percentages from thigh, triceps, biceps, chest, abdomen, suprailiac, subscapula) and performance-based parameters (push-up, and 12 min-running), demonstrated superior predictive capability.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Analyzing sports activities using machine learning algorithms is an emerging approach for identifying key parameters that influence the athlete’s performance.
📊
Key Findings & Data:Implementing such algorithms enables sports engineers to develop improved sports equipment and facilities, analyze athlete performance and design personalized training programs.
💡
Conclusion & Impact:Model 11, including physical-based parameters (gender, weight, age, leg strength, subcutaneous fat percentages from thigh, triceps, biceps, chest, abdomen, suprailiac, subscapula) and performance-based parameters (push-up, and 12 min-running), demonstrated superior predictive capability.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Makine öğrenmesi · Performans tahmini · Spor performansı

Abstract

Analyzing sports activities using machine learning algorithms is an emerging approach for identifying key parameters that influence the athlete’s performance. Implementing such algorithms enables sports engineers to develop improved sports equipment and facilities, analyze athlete performance and design personalized training programs. In this study, 18 physical and performance-related parameters were collected from 30 hearing-impaired athletes, and 20 models were constructed based on different parameter combinations. Tree-based machine learning algorithms (tree boost, decision tree forest, and single decision tree) were applied to predict athletes’ standing long jumping distance. Model performance was evaluated using root mean square error (RMSE), mean absolute percentage error (MAPE), and the coefficient of determination (R2). The best results were obtained from the tree boost algorithm for Model 11 with an RMSE of 15.08, an R2 value of 0.95, and a MAPE of 6.31%. Model 11, including physical-based parameters (gender, weight, age, leg strength, subcutaneous fat percentages from thigh, triceps, biceps, chest, abdomen, suprailiac, subscapula) and performance-based parameters (push-up, and 12 min-running), demonstrated superior predictive capability.

Özet

Spor aktivitelerini makine öğrenimi algoritmaları aracılığıyla analiz etmek, sporcuların performansını etkileyen önemli parametreleri belirlemede yeni bir yaklaşımdır. Bu algoritmaların uygulaması, spor mühendislerinin spor ekipmanları ve spor tesisleri geliştirmelerine, sporcuların performansını analiz etmelerini ve kişiye özel antrenman programları tasarlamalarına olanak sağlayabilir. Bu çalışmada, 30 işitme engelli sporcuya ait 18 fiziksel ve performans tabanlı parametre toplandı ve farklı parametre kombinasyonlarına dayalı olarak 20 model oluşturuldu. Sporcuların uzun atlama mesafesini tahmin etmek için ağaç tabanlı makine öğrenmesi algoritmaları (ağaç güçlendirme, karar ağacı ormanı ve tek karar ağacı) kullanıldı. Modellerin performansı, kök ortalama kare hata (RMSE), ortalama mutlak yüzde hata (MAPE) ve belirleme katsayısı (R2) ile değerlendirildi. En iyi sonuç, Model 11 için tree boost algoritmasından elde edilmiş ve RMSE değeri 15.08, R² değeri 0.95 ve MAPE değeri %6.31’dir. Model 11, cinsiyet, kilo, yaş, bacak, uyluk, triseps, biseps, göğüs, karın, suprailiak, subscapula, şınav ve 12 dk. koşuyu içermekte olup, üstün tahmin yeteneği göstermiştir.

🔖

Cite This Article

Özçiloğlu, M. M., Aydınalp, C., Karakoç, Ö. (2026). Performance prediction of hearing impaired athletes with tree-based algorithms. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, Cilt: 32 Sayı: 6, 1285–1292. https://doi.org/10.65206/pajes.34662

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (27)

  1. World Bank Group. “Disability Inclusion Overview”. https://www.worldbank.org/en/topic/disability (03.01.2025).
  2. Wilson PE, Clayton GH. “Sports and disability”. PM&R. 2(3),46-54, 2010.
  3. Howe PD, Silva CF. Technology, Disability and High-Performance Sport: A Socio-Cultural Reading. Editors: Veronika T, Michael F. Interactive Sports Technologies, 168-181, London, Routledge, 2022.
  4. George JD, Tolley JR, Vehrs PR, Reece JD, Akay MF, Cambridge, ED. “New approach in assessing core muscle endurance using ratings of perceived exertion”. The Journal of Strength & Conditioning Research, 32(4), 1081-1088, 2018.
  5. Niemelä M, Kulmala JP, Kauppi JP, Kosonen J, Äyrämö J. “Prediction of active peak force using a multilayer perceptron”. Sports Engineering, 20(3), 213-219, 2017.
  6. Akay MF, Abut F, Cetin E, Yarim I, Sow B. “Support vector machines for predicting the hamstring and quadriceps muscle strength of college-aged athletes”. Turkish Journal of Electrical Engineering and Computer Sciences, 25(4), 2567-2582, 2017.
  7. Akay MF, Abut F, Özçiloğlu MM, Heil D. “Identifying the discriminative predictors of upper body power of cross-country skiers using support vector machines combined with feature selection”. Neural Computing and Applications, 27(6), 1785-96, 2016.
  8. Trewin S, Basson S, Muller M, Branham S, Treviranus J, Gruen J, Manser D, Baeza-Yates RM. “Considerations for AI fairness for people with disabilities”, AI Matters, 5(3), 40-63, 2019.
  9. da Silva BG, Miziara IM, Furtado DA, dos Santos SS, Fidale TM, Pereira AA. “Electromyographical activity of the pectoralis, triceps, and deltoideus during the sub-phases of bench press in Paralympic powerlifters”. Sports Engineering, 25(1), 1-10, 2022.
  10. Favretto E, Fin W, dos Santos Albarello JC, Halmenschlager GH, Bona CG, Pimentel CG, da Silva JAF, Olivira RA. “Cardiorespiratory fitness and muscular strength of deaf futsal players”. Journal of exercise rehabilitation, 15(3), 424-429, 2019.
  11. Karakoc O. “The investigation of physical performance status of visually and hearing impaired applying judo training program”. Journal of Education and Training Studies, 4(6), 10-17, 2016.
  12. Imas Y, Irene K, Dmytro K, Georgiy K, Maryna S, Viktoriya K. “Neural network modeling of diagonal stride technique of highly qualified skiers with hearing impairments”. Journal of Physical Education and Sport, 18(2), 1217-1222, 2018.
  13. Alves DL, Castro PHC, Freitas JV, De-Oliveira FR, Lima JRP, Cruz R. “What variables determine sprint performance in young athletes?”. Science & Sports, 36(3), 87-94, 2021.
  14. Yıldız ER, Bitirim Y. “Performance evaluation of the machine learning algorithms for emotion classification on the CASE dataset”. Pamukkale University Journal of Engineering Sciences, 31(1), 79-85, 2025.
  15. Nacaroglu E, Karakoc O. “Effects of eight-week plyometric study on the balance performance of hearing impaired athletes”. International Education Studies, 11(6), 1-7, 2018.
  16. Foster JI, Williams KL, Timmer BHB, Brauer SG. “The association between hearing impairment and postural stability in older adults: A systematic review and meta-analysis”. Trends in Hearing, 26, 23312165221144155, 2022.
  17. Iglesias E, Clavel I, Dopico J, Tuimil J. “Acute effect of the specific effort of judo on different strength manifestations and their relation with the reached cardiac frequency during the confrontation”. Revista Rendimiento Deportivo, 6, 2003. http://www.rendimientodeportivo.com/N006/Artic027.htm.
  18. Vabalas A, Gowen E, Poliakoff E, Casson A. “Machine learning algorithm validation with a limited sample size”. PLoS ONE, 14(11), 1-20, 2019.
  19. Liu S, Xiao J, Liu J, Wang X, Wu J, Zhu J. “Visual diagnosis of tree boosting methods”. IEEE Transactions on Visualization and computer graphics, 24(1), 163-173, 2017.
  20. Quinlan JR. “Induction of decision trees”. Machine Learning, 1(1), 81-106, 1986.
  21. Mrva J, Neupauer Š, Hudec L, Ševcech J, Kapec P. “Decision support in medical data using 3D decision tree visualization”. In: E-Health and Bioengineering Conference, Iasi, Romania, 1-4, November 2019.
  22. Panhalkar AR, Doye DD. “A novel approach to build accurate and diverse decision tree forest”. Evolutionary Intelligence, 15(1), 439-453, 2022.
  23. Agrawal L, Adane D. “Improved decision tree model for prediction in equity market using heterogeneous data”. IETE Journal of Research, 69(9), 6065-6074, 2023.
  24. Polikar R. “Ensemble based systems in decision making”. IEEE Circuits and Systems Magazine, 6(3), 21-45, 2006.
  25. Christie D, Neill S. “Measuring and observing the ocean renewable energy resource”. Reference Module in Earth Systems and Environmental Sciences, 8(1), 149-175, 2021.
  26. Saunders LJ, Russell RA, Crabb DP. “The coefficient of determination: what determines a useful r2 statistic?”. Investigative Ophthalmology & Visual Science, 53(11), 6830-6832, 2012.
  27. Prayudani S, Hizriadi A, Lase Y, Fatmi Y, Rahim R, Siahaan APU. “Analysis accuracy of forecasting measurement technique on random k-nearest neighbor (rknn) using mape and mse”. Journal of Physics: Conference Series, 1361(1), 1-8, 2019.