| Using CNN Artificial intelligence algorithm to predict stress levels of football players |
| Paper ID : 1571-SPORTCONGRESS |
| Authors |
|
صابر رضانژاد *1, ابراهیم قاسمیان2, مهدی نمازی زاده3, مجید خدادادی3 1دکتری بیوشیمی و متابولیسم ورزشی، گروه فیزیولوژی ورزشی، دانشکده علوم ورزشی، دانشگاه اصفهان، اصفهان، ایران 2کارشناس ارشد روانشناسی ورزشی موسسه آموزش عالی المهدی مهر اصفهان 3عضو هیات علمی موسسه آموزش عالی المهدی اصفهان |
| Abstract |
| In the present study, we aimed to be able to predict the stress level of football players through the CNN artificial intelligence algorithm. The statistical population of this study was all football players in Isfahan city at all levels, and the statistical sample of this study was 405 questionnaires distributed as a convenience sample among the statistical population using the Cochran formula. In the inferential statistics section, after measuring the reliability of the information obtained from the questionnaire, the CNN algorithm was used to predict the stress level of football players in MATLAB software. In the training data, 198 players had symptoms of high stress, of which the CNN neural network correctly identified 188 players with high stress levels. The correlation coefficient between the predicted value and the actual values in the training data, validation, and testing of the neural network model is 0.83, 0.52, and 0.52, respectively. Also, in the total data under study, the correlation coefficient between the predicted value and the actual values is 0.75. The correlation coefficient between the factors explaining stress and players' stress was calculated to be 0.60 based on the Pearson correlation coefficient, which is actually a linear relationship between variables; while the correlation coefficient was improved to 0.15 based on the neural network method, which indicates that the neural network method used in this study has improved the efficiency of predicting stress in football players. |
| Keywords |
| CNN algorithm, artificial intelligence, stress level prediction, football players. |
| Status: Abstract Accepted (Poster Presentation) |
