Research on College Physical Fitness and Health Testing Combining Clustering Algorithm and Association Rule Mining

Artificial intelligence technology’s quick development has given colleges new tools and techniques for managing health and sports. To overcome the issues of low accuracy and low efficiency in the analysis of standard sports physical fitness and health test data, a technique combining association rule mining and clustering algorithms is suggested. This method divides students into groups with similar physical characteristics through cluster analysis, and uses association rule mining to reveal significant correlations between physical fitness test indicators. The outcomes revealed that the proposed method has an average accuracy improvement of $9.79 \%$ and a running efficiency improvement of $79.37 \%$, which is significantly better than traditional statistical methods. This study provides reliable technical support for the intelligent decision-making of sports health management in colleges and universities, and expands the application scenario of artificial intelligence technology in the field of sports health.