Performance assessment and fitness analysis of athletes using decision tree and data mining techniques

Recently, the rise in student numbers has led to the establishment of many new colleges and universities in China. As a result, there has been a significant increase in data collection on students' athletic skills. To manage these data, educational institutions are implementing information management systems. However, tracking sports results remain challenging since sports information may not always be collected during sports teaching. This work presents a systematic strategy to address this problem by evaluating student athletes' abilities using an Apriori algorithm, decision tree (DT), and association rule. It covers the processes for collecting data, preprocessing, selecting features, and evaluating models. The efficiency of the DT algorithm in solving classification problems, including student achievement analysis, is emphasized. The association rule algorithm is applied to figure out the correlation between students' physical fitness and their involvement in physical education. The Apriori algorithm is introduced to reduce the amount of data needed in merging item sets. Lastly, the overall architecture of the college students' physical fitness analysis system is presented. It covers the insertion of sports test scores, the calculation of total scores, and the application of DT analysis for evaluating student achievements. The process involves standardizing database information, selecting a training instance set, and determining attributes based on information gain. The efficiency of the system is evaluated in terms of accuracy, precision, recall, and F1 score. In comparison with previous works, our recommended system can track and analyze students' athletic capability, fitness, and physical ability to create personalized workout routines and monitor their health in real-time.