Abstract

This study presents an intelligent model for assessing students’ physical activity based on physiological and anthropometric indicators. The limitations of traditional assessment methods are analyzed, and the effectiveness of machine learning algorithms and artificial intelligence techniques is demonstrated.
An experimental study involving 420 students aged 7–15 from general education schools in Urgench compared the performance of Random Forest, Support Vector Machine (SVM), and Deep Neural Network (DNN) algorithms. The proposed multidimensional model achieved an accuracy of 94.3%, which is 18.7% higher than that of traditional index-based assessment methods.
The findings demonstrate that the combined analysis of heart rate, VO₂max, and body mass index (BMI) enables a more accurate assessment of students’ physical activity levels. The results of the study also provided the basis for the development of a software prototype with practical applications for school medical services and physical education teachers.