Physical fitness testing,as the fundamental way to provide feedback on the physical health level of college students,provides data support for universities to carry out student health intervention work.However,it has become particularly important to scientifically analyze and reasonably use physical fitness data.This paper uses data mining techniques to study the physical measurement data of college students,and uses decision trees,naive Bayes,and Bayesian neural networks to predict the physical measurement data.The results show that Bayesian neural networks have the highest prediction accuracy.By using the CART decision tree to classify physical testing data,the optimal decision tree can be obtained.It analyzes the important factors that affect the physical fitness level of college students through the optimal decision tree,further explore the impact and role of physical testing scores on the physical fitness of college students,and thereby enhance their enthusiasm and interest in participating in campus sports.
data miningDecision Treenaive BayesBayesian Neural Networkscampus sports
国家科技期刊平台
NSTL
万方数据
