The analysis on college students' physical fitness testing data — two cases study

Abstract

College students physical fitness test is an important means for physical fitness evaluation. The test includes body mass index(BMI), lung's capacity, 50 and 1000(male)/800(female) meters run, standing long jump, sit and reach, pull-up(male)/sit-up(female). Final result is weighted sum of the seven items. According to national standard of physical fitness for students, the weights are 15%, 15%, 20%, 10%, 20%, 10%, 10%, respectively. We can regard it as a dimensionality reduction process, which reduces the original data to one dimension. Using fixed weights, the results will neglect differences among students in different areas. Therefore, it is important to learn the weights from the data. The learned weights can not only give students a reasonable evaluation of physical ability, but also reflect the characteristics of the samples. In this paper, we present a learning model for the weights of students' physical fitness tests. The solution algorithm is also presented. We then employ proposed method to analyze two data sets, The results demonstrate that the model presented in this paper has advantages for college students physical fitness test data analysis.