Implementation of ANN for Toddler Nutrition Classification Using Feature Selection
Journal of Applied Informatics and Computing · 16.04.2026 · 10 (2) · 1229-1238
DOI: 10.30871/jaic.v10i2.12266 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Applied Informatics and Computing, online erschienen am 16.04.2026. Verfasst von Ferdita Inayah Hestu Saputri und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
The nutritional status of toddlers is an important indicator in assessing the health and growth quality of children. In Indonesia, nutritional problems such as malnutrition and obesity are still serious issues that require rapid and accurate identification strategies. Using the Artificial Neural Network (ANN) algorithm, this study classified the nutritional status of toddlers based on anthropometric data collected from the Tanjungharjo Community Health Center, Kapas District, Bojonegoro Regency. This study combines ANN with several feature selection and reduction methods, including Chi-Square, Pearson Corelation (PC), and Pearson Component Analysis (PCA). In addition, it compares the performance of the model under data conditions with data without Min–Max Scaler normalization. The dataset was processed through preprocessing, encoding, normalization, and division stages using 80% training data and 20% test data. The results showed that ANN+PC with pearson corelations without normalization provided the best performance, with an accuracy value of 0.9809, precision of 0.9827, recall of 0.9809, and F1 score of 0.9815. These results indicate that data normalization does not always improve ANN performance; on the contrary, the PC method showed a significant improvement in performance after applying Min–Max without normalization. These results show that the feature selection method used is highly dependent on the method used. This study found that ANN+PC is an effective way to classify the nutritional status of toddlers, provided that the preprocessing and feature selection techniques are chosen correctly. The results of this study are expected to assist in decision-making regarding how to monitor and prevent nutritional problems in toddlers.
Zitieren
APA
Saputri, F. I. H., Prastya, I. D. W., & Ardianti, A. D. (2026). Implementation of ANN for Toddler Nutrition Classification Using Feature Selection. Journal of Applied Informatics and Computing, 10(2), 1229-1238. https://doi.org/10.30871/jaic.v10i2.12266
Vancouver
Saputri FIH, Prastya IDW, Ardianti AD. Implementation of ANN for Toddler Nutrition Classification Using Feature Selection. Journal of Applied Informatics and Computing. 2026;10(2):1229-1238. doi:10.30871/jaic.v10i2.12266
BibTeX
@article{Saputri2026,
author = {Saputri, Ferdita Inayah Hestu and Prastya, Ifnu Dwi Wisma and Ardianti, Aprillia Dwi},
title = {Implementation of ANN for Toddler Nutrition Classification Using Feature Selection},
journal = {Journal of Applied Informatics and Computing},
year = {2026},
volume = {10},
number = {2},
pages = {1229--1238},
doi = {10.30871/jaic.v10i2.12266}
}
EUVIMED