Physical Fitness Assessment System for College Students Based on Apriori Algorithm

In recent times, the utilization of machine learning algorithms to analyze and predict human fitness has received widespread attention. As the cornerstone of the future of the country, it holds great importance to evaluate the physical fitness of college students and provide scientific guidance according to the evaluation results. To address the issue of low accuracy of current physical fitness assessment methods for college students, a physical fitness assessment system is constructed by combining decision tree $\mathbf{C 4. 5}$ and association rule algorithm. The system was compared and analyzed, and the outcomes indicated that the assessment F1 values of the system were 0.987 and 0.976 in terms of accuracy, respectively, which were both better than the comparison system. Subsequently, the system was analyzed with other systems for application effects, and the results showed that the system measured students’ cardiorespiratory fitness, muscular endurance, muscular strength, flexibility, and obesity with an accuracy rate of 97.8%, $\mathrm{9 8. 2 \%, 9 5. 3 \%, 9 8. 3 \%}$,and 96. 4 %, which were better than the comparison system. The above results indicate that the proposed physical fitness assessment system can validly raise the accuracy of physical fitness assessment of college students.