# Classification of Toddler Nutrition Status with Anthropometry using the K-Nearest Neighbor Method

2019 International Conference on Electrical, Electronics and Information Engineering (ICEEIE)（2019）

摘要

One indicator of children's health is nutrition status, So it is necessary to monitor their nutrition status. Monitoring is one way to find out the growth of children under five years old, monitoring the nutrition status can using anthropometric calculations. Anthropometric calculations use three assessment indexes, namely Weight for Age (WFA), Height for Age (HFA), and Weight for Height (WFH). The purpose of this study is to classify the nutritional status of children under five years old based on three anthropometric indexes using the K-Nearest Neighbor method or algorithm. The results are evaluated based on the number of true and false k-fold cross-validation. The K values used are k = 3, k = 9 and k = 15 of all K values, the highest accuracy results of the testing data in WFA index at Table. 9 is 85.24% by using value k=3, k=5, k=7, k=9 and the lowest accuracy is 84.76% by using k=15. The highest accuracy in HFA index at Table. 10 is always 73.81%. The highest accuracy in WFA index at Table. 11 is 73.33% by using value k=3, and the lowest accuracy is 72.38% by using k=5, k=7, k=9 and k=15. While the lowest accuracy on the WFH index is 72.38% by using value k=5, k=7, k=9 and k=15, the results show that the k-nearest neighbor method can be used to categorize children under the Anthropometric index standard.

更多查看译文

关键词

nutrition status,anthropometry,k-nearest neighbors

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络