Measurement of Student Physical Fitness Based on Association Rule Algorithm

In this paper, the body mass index data are firstly selected and transformed into Boolean data suitable for Apriori algorithm after data cleaning, data reduction and data transformation according to the characteristics of limited and consistent length of college students’ body measurement data. Then, the operation efficiency of the Apriori association rule mining model is improved jointly from the perspective of transaction compression hash technology. Finally, strong association rules between indicators are screened based on the support and confidence framework. The experiment result shows that: The Apriori algorithm based on transaction compression and hash proposed in this paper is more efficient. Compared with the classical Apriori algorithm, the implementation efficiency of the body measurement data algorithm for girls is improved by 86.12%, and that for boys is improved by 92.65%;Compared with Apriori algorithm based on transaction compression, the performance efficiency of the female body measurement data algorithm is improved by 80.57%, female body by 89.32%;Compared with the Apriori algorithm based on hash, the implementation efficiency of the body measurement data algorithm is improved by 48.1% for girls and 55.69% for boys. Result finding that the model can obtain effective correlation information between body mass indexes and improve the operation efficiency significantly, it can be applied to physical fitness test practice.