<![CDATA[Assessing the nutritional status of toddlers is crucial for monitoring their nutritional development. This study attempts to compare two methods of classifying the nutritional status of toddlers: using the K-Nearest Neighbors (K-NN) method and the Support Vector Machine (SVM) method based on anthropometric indices. The research aims to determine which technique is most effective for categorizing toddlers in the nutritional dataset. The data used for this process includes information such as gender, age, weight, height, and body mass index. We also calculate the nutritional status of toddlers based on anthropometric indices, including Weight for Age (WFA), Height for Age (HFA), Weight for Height (WFH), and Body Mass Index for Age (BMIFA). To gauge the effectiveness of these techniques, we use 827 toddler data as training data and 207 toddler data as test data. The results indicate that the K-Nearest Neighbors (K-NN) model achieves an accuracy of approximately 93.01%, while the SVM model has an accuracy of about 91.8%. This means that the K-NN model is slightly better than the SVM model in classifying the nutritional status of toddlers based on anthropometric indices.]]>
Copyrights © 2024
