Prediction and management of physical injuries caused by gym equipment and facilities using a Support Vector Machine (SVM) algorithm

Document Type : Original Article


Associate Professor, Department of Sports Management, Faculty of Physical Education and Sports Sciences, Allameh Tabatabai University, Tehran, Iran



Purpose: This study aimed to predict and manage physical injuries caused by gym equipment and facilities using the SVM algorithm.

Method: This study was of a developmental-applied type. The snowball method was used to select the subjects. Subjects were asked to answer the questionnaire online and send it to friends and acquaintances of athletes. The validity of the instrument was confirmed through the opinions of university professors and convergent validity. Cronbach's alpha was used to check reliability. The sample questionnaire included 612 athletes in the age group of 18 to 60 years. 158 people were healthy, 54 people had head injuries, 211 people had leg injuries, and 189 people had hand injuries. The SVM algorithm was used to classify people. In addition, MATLAB software version 2022 was used for data analysis. The evaluation was conducted based on the clutter matrix and accuracy criteria.

Results: The results showed that the SVM algorithm can predict head, arm and leg injuries with 74.6% accuracy and 73.2% accuracy, respectively.

Conclusion: This study showed that by discovering hidden patterns and relationships in the data, this algorithm can probably be used correctly to improve the quality of sports facilities management to prevent physical injuries of athletes.