<![CDATA[This study aims to analyze and classify various food items based on their nutritional content using an unsupervised learning approach, specifically the K-Means Clustering algorithm. The increasing complexity of nutritional data requires effective data-driven methods to support accurate and efficient analysis. This research utilizes K-Means to group food items into distinct clusters according to their energy, fat, carbohydrate, protein, and fiber levels. The clustering process successfully identified three main groups that represent different nutritional characteristics. Cluster 1 consists of high-energy and high-fat foods suitable for individuals with high physical activity. Cluster 0 includes balanced-nutrition foods recommended for daily consumption, while Cluster 2 contains low-calorie and high-fiber foods ideal for weight control or diet programs. The results demonstrate that K-Means is effective in simplifying complex nutritional data and providing clear classifications for practical use. This study highlights the potential of machine learning as a valuable tool in nutritional analysis and digital health innovation. The application of this method can support the development of intelligent nutrition-based applications that help individuals manage healthy diets more effectively and contribute to promoting public awareness of balanced nutrition.]]>
Copyrights © 2025
