<![CDATA[Current physical activity is no longer viewed merely as a bodily exercise but has become an essential part of the lifestyle. However, the diversity of available workout types often makes it difficult for individuals to determine the most suitable form of exercise based on their personal needs and lifestyle habits. This issue serves as the foundation of this research, which aims to develop a workout recommendation system based on lifestyle data using the K-Nearest Neighbor (KNN) algorithm. The results indicate that the KNN algorithm, with an optimal K value of 107, achieves an accuracy rate of 90% in recommending workout types. The High Intensity Interval Training (HIIT) and Yoga categories were identified as the most accurately recognized exercises by the model, with an F1-score of 95%. These findings demonstrate that the KNN method is effective in identifying lifestyle patterns and providing personalized workout recommendations. Therefore, the KNN-based recommendation system is expected to serve as an adaptive and intelligent solution to assist individuals in selecting workout types that best fit their lifestyles.]]>
Copyrights © 2025
