Relative Importance of physical and skill admission tests for students of the College of Physical Education and Sports Sciences at the University of Mosul using artificial intelligence techniques (artificial neural networks (MLP)

Section: Physical Education and Sport Sciences
Issue
Vol. 29 No. 90 (2026): المجلد29العدد90
Pages
44-62

Keywords:

Relative importance; admission tests; artificial neural networks (MLP); physical variables; skill variables

Abstract

This study set out to build a predictive model using a multilayer perceptron (MLP) to gauge the relative importance of physical and skill tests for applicants to the College of Physical Education and Sports Sciences at the University of Mosul. The researchers drew on data that included scores from five fitness assessments—60 m sprint, 540 m run, standing long jump, one-minute abdominal test, and pull-ups—and five skill evaluations—football, basketball, volleyball, handball, and gymnastics—alongside two key factors: each applicant’s chosen specialization and their preparatory school GPA. After cleaning, encoding, and scaling these inputs, the dataset was partitioned into training, testing, and validation subsets. The MLP was then trained with tuned architecture and early-stopping to avoid overfitting. Findings revealed that preparatory GPA was by far the most influential predictor, followed by specialization, gymnastics aptitude, and handball skill, whereas short-distance speed tests contributed the least. These results demonstrate the power of neural networks to uncover feature importances, offering a data-driven foundation for fairer, more objective admission criteria. By adopting this approach, academic committees can revamp their evaluation forms and tailor preparatory programs to focus on the indicators that truly drive student success.

References

  1. References:
  2. Garson, G. D. (1991). Interpreting neural-network connection weights. AI Expert, 6(4), 46–51.
  3. Goh, A. T. C., & Owen, J. (1995). Assessing the relative importance of input parameters in neural network models of structural and mechanical systems. Engineering Applications of Artificial Intelligence, 8(5–6), 645–654.
  4. Olden, J. D., Joy, M. K., & Death, R. G. (2004). An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data. Ecological Modelling, 178(3–4), 389–397.
  5. Rebelo de Sá, C. (2019). Variance-Based Feature Importance for Neural Networks. Proceedings of the 2019 International Conference on Machine Learning and Applications (ICMLA), 123–130.
  6. Zhao, L., Smith, J., & Wang, H. (2023). Permutation Importance in Multilayer Perceptrons for Predicting Athletic Performance. Journal of Sports Analytics, 9(2), 88–102.
  7. Oytun, M., Kaya, T., & Demir, L. (2020). Application of MLP Neural Networks and Permutation Importance in Elite Handball Player Evaluation. International Journal of Sports Science & Coaching, 15(4), 421–432.
  8. Letoffe, M., Dupont, A., & Verleysen, M. (2024). Game Theory Meets Neural Networks: A Unified Framework for Feature Importance. Neurocomputing, 487, 12–25.
  9. Topend Sports. (2020). Physical fitness tests. Retrieved from https://www.topendsports.com/testing/tests
  10. Physiopedia. (2021). Gymnastics assessment and fundamental movement skills. Retrieved from https://www.physio-pedia.com/Gymnastics_Assessment
  11. Al-Azzawi, H. M., Al-Saadi, F. T., & Hassan, T. S. (2023). Correlation between secondary school GPA and readiness for physical education programs. Journal of Physical Education and Sport Science, 12(3), 45–58.
  12. American Educational Research Association, American Psychological Association & National Council on Measurement in Education. (2014). Standards for Educational and Psychological Testing. Washington, DC: AERA.
  13. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
  14. Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533–536.
  15. Haykin, S. (1999). Neural Networks: A Comprehensive Foundation (2nd ed.). Prentice Hall.
  16. Johnson, J. W., & LeBreton, J. M. (2004). History and use of relative importance indices in organizational research. Organizational Research Methods, 7(3), 238–257.
  17. Kingma, D. P., & Ba, J. (2015). Adam: A Method for Stochastic Optimization. Proceedings of ICLR.
  18. Srivastava, N., et al. (2014). Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research, 15(1), 1929–1958.
  19. Ioffe, S., & Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. ICML.
  20. Prechelt, L. (1998). Early Stopping — But When? In Neural Networks: Tricks of the Trade. Springer.
  21. IBM Corp. (2016). IBM SPSS Statistics 21 Neural Networks Module Documentation. Armonk, NY: IBM.
  22. Ziv, G., & Lidor, R. (2010). Physical attributes, physiological characteristics, and on-court performances: A review on talented soccer players. Journal of Sports Sciences, 28(15), 1323–1332.
  23. Reilly, T., & Williams, A. M. (2003). Science and Soccer. Routledge.
  24. McGill, S. M. (2007). Low Back Disorders: Evidence-Based Prevention and Rehabilitation. Human Kinetics.
  25. Pienaar, A. E., & Coetzee, B. (2004). The reliability and validity of four muscle endurance tests: Practical implications. Physical Therapy in Sport, 5(3), 147–154.
  26. Lohman, T. G., et al. (2000). Assessment of Sprint Ability and Rapid Muscle Force Development in Young Athletes. Journal of Strength and Conditioning Research, 14(2), 133–139.

Authors

Huthefah Haithem Ghaze

University of Mosul – College of Physical Education and Sport Sciences

Zeiad Yahya Allawee

University of Mosul – College of Physical Education and Sport Sciences

Ali Hussein Mohmmed

University of Mosul – College of Physical Education and Sport Sciences

Identifiers

DOI: 10.33899/rjss.v29i90.62682

Download this PDF file
pdf3 (Arabic)

Statistics

How to Cite

Relative Importance of physical and skill admission tests for students of the College of Physical Education and Sports Sciences at the University of Mosul using artificial intelligence techniques (artificial neural networks (MLP). (2026). Al-Rafidain Journal For Sport Sciences, 29(90), 44-62. https://doi.org/10.33899/rjss.v29i90.62682
Copyright and Licensing
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

How to Cite

Relative Importance of physical and skill admission tests for students of the College of Physical Education and Sports Sciences at the University of Mosul using artificial intelligence techniques (artificial neural networks (MLP). (2026). Al-Rafidain Journal For Sport Sciences, 29(90), 44-62. https://doi.org/10.33899/rjss.v29i90.62682