EUVIMEDEUVIMED entdecken
Crossref

SUPERVISED LOGIC MINING FOR ATHLETE INJURY DATA WITH RANDOM 3-SATISFIABILITY

Nurin Hazwani Hamidi, Nur Ezlin Zamri, Nurin Kamalin Mohd Fadil, Farisya Husna Mansor, Nurul Huda Ahmad Rusli, Ameer Azamuddin Abdul Ghafar

International Journal of Supply Chain Operation Management and Logistics · 31.03.2026 · 6 (11) · 1

DOI: 10.35631/ijscol.611001 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Supply Chain Operation Management and Logistics, online erschienen am 31.03.2026. Verfasst von Nurin Hazwani Hamidi und 5 weiteren Autor:innen. Die Arbeit nennt 17 Literaturangaben. Gefördert von: IPM Putra Grant.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Nowadays, athletes are exposed to high performance demands and intense training loads, increasing their risk of injury. The absence of early detection systems often leads to late interventions, longer recovery periods and performance decline. This project addresses the need for an interpretable early detection model for athlete injury prevention. The proposed solution is built using Random 3-Satisfiability Reverse Analysis (RAN3SATRA) model enhanced through correlation-based attribute selection. By implementing logic mining, the systems able to extract human-readable rules that explain relationships between injury and performance factors, allowing domain experts to make transparent, data-driven decisions. The model was tested using the Athlete Injury and Performance Dataset and demonstrated strong and consistent performance across multiple metrics including accuracy, sensitivity, specificity, Matthews Correlation Coefficient and Negative Predictive Value. These results indicate that the proposed logic-based framework is affective in identifying injury risk patterns while maintaining interpretability. The logic mining process successfully identified key injury-related factors such as training load balance, ACL injury risk level, fatigue level, weekly recovery days and weekly training duration. These findings offer direct insight into injury prevention and enable the development of actionable monitoring systems for coaches, physiotherapists and sports scientists. This project reflects the potential of explainable AI in sports analytics, combining data science and logic reasoning to protect athlete health and optimise performance.

Förderung

  • IPM Putra Grant

Zitieren

APA

Hamidi, N. H., Zamri, N. E., Fadil, N. K. M., Mansor, F. H., Rusli, N. H. A., & Ghafar, A. A. A. (2026). SUPERVISED LOGIC MINING FOR ATHLETE INJURY DATA WITH RANDOM 3-SATISFIABILITY. International Journal of Supply Chain Operation Management and Logistics, 6(11), 1. https://doi.org/10.35631/ijscol.611001

Vancouver

Hamidi NH, Zamri NE, Fadil NKM, Mansor FH, Rusli NHA, Ghafar AAA. SUPERVISED LOGIC MINING FOR ATHLETE INJURY DATA WITH RANDOM 3-SATISFIABILITY. International Journal of Supply Chain Operation Management and Logistics. 2026;6(11):1. doi:10.35631/ijscol.611001

BibTeX
@article{Hamidi2026,
  author = {Hamidi, Nurin Hazwani and Zamri, Nur Ezlin and Fadil, Nurin Kamalin Mohd and Mansor, Farisya Husna and Rusli, Nurul Huda Ahmad and Ghafar, Ameer Azamuddin Abdul},
  title = {SUPERVISED LOGIC MINING FOR ATHLETE INJURY DATA WITH RANDOM 3-SATISFIABILITY},
  journal = {International Journal of Supply Chain Operation Management and Logistics},
  year = {2026},
  volume = {6},
  number = {11},
  pages = {1},
  doi = {10.35631/ijscol.611001}
}
Kostenlos starten →