<![CDATA[Sufficient and regular physical activity plays an important role in supporting students' physical, mental, and social health. However, variations in exercise habits necessitate a more objective evaluation of students' physical activity levels. This study aims to categorize students' sports activities based on duration and distance using the K-Means algorithm, in order to evaluate exercise patterns and provide relevant information for the development of physical fitness coaching programs. Data were collected from 30 students and analyzed using an unsupervised learning approach. The clustering results formed three main clusters: (1) students with low activity, short duration, and high BMI values; (2) students with moderate activity, ideal duration, and normal BMI values; and (3) students with very high activity, long duration, and consistently healthy BMI values. These findings indicate that clustering methods are effective in identifying groups of students based on their exercise habits and can serve as a foundation for fitness improvement strategies. Keywords: Physical Activity, K-Means Clustering, Exercise Habits]]>
Copyrights © 2025
