Penerapan K-NN untuk mengklasifikasi status gizi balita di Pos Kesehatan Desa Rongga Koe

Toddler nutritional status is an important indicator in assessing the level of public welfare and health. At Rongga Koe Village Health Post, determining nutritional status is still done manually, so it takes a long time and is prone to errors. This study aims to develop a classification system for toddler nutritional status using the K-Nearest Neighbors (k-NN). The data used was 100 samples with five parameters: gender, age, weight, height, and upper arm circumference. The classification process was carried out with variations in the ratio of training and testing data (90:10, 80:20, 70:30, 60:40), as well as the k value and distance calculation method (Euclidean, Manhattan, Chebyshev, Mahalanobis). The results showed that the best combination was obtained at a ratio of 90:10 and a k value = 9 with the Mahalanobis Distance method, which achieved the highest accuracy of 85.7%. This study proves that the K-NN method is effective in helping to classify nutritional status digitally and more efficiently.