EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

An Extreme Learning Machine-Based Method for Forecasting Stunted Growth in Pediatric Health Data

Dasril Aldo, Riski Novera Yenita, Adanti Wido Paramadini, Ihsan Maulana, Gilang Sulaeman

JOIV : International Journal on Informatics Visualization · 31.05.2026 · 10 (3) · 1032

DOI: 10.62527/joiv.10.3.3210 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JOIV : International Journal on Informatics Visualization, online erschienen am 31.05.2026. Verfasst von Dasril Aldo und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Stunting remains a significant global public health problem, particularly in developing countries, due to its long-term impact on children’s physical and cognitive development. Early detection is essential to mitigate its effects and enable timely interventions. This study aims to support early detection and intervention by evaluating the performance of the Extreme Learning Machine (ELM) in diagnosing stunting. A stratified dataset was created from 196,071 samples, supplemented with 300 additional entries containing relevant descriptors (age, gender, height, and nutritional status). Data preprocessing included interpolation, missing value imputation, and normalization. Performance metrics such as accuracy, precision, recall, and F1-score were used to compare ELM with Decision Tree, Random Forest, and SVM classifiers. Results indicated that ELM outperformed other models, achieving 89.00% accuracy initially, and 96.67% accuracy, 98.99% recall, 92.08% specificity, and 96.10% precision after adding the new data. The main contribution of this study is using and testing ELM for detecting stunting in children on a large scale, showing it works better than traditional machine learning models and can be used effectively in public health efforts.

Zitieren

APA

Aldo, D., Yenita, R. N., Paramadini, A. W., Maulana, I., & Sulaeman, G. (2026). An Extreme Learning Machine-Based Method for Forecasting Stunted Growth in Pediatric Health Data. JOIV : International Journal on Informatics Visualization, 10(3), 1032. https://doi.org/10.62527/joiv.10.3.3210

Vancouver

Aldo D, Yenita RN, Paramadini AW, Maulana I, Sulaeman G. An Extreme Learning Machine-Based Method for Forecasting Stunted Growth in Pediatric Health Data. JOIV : International Journal on Informatics Visualization. 2026;10(3):1032. doi:10.62527/joiv.10.3.3210

BibTeX
@article{Aldo2026,
  author = {Aldo, Dasril and Yenita, Riski Novera and Paramadini, Adanti Wido and Maulana, Ihsan and Sulaeman, Gilang},
  title = {An Extreme Learning Machine-Based Method for Forecasting Stunted Growth in Pediatric Health Data},
  journal = {JOIV : International Journal on Informatics Visualization},
  year = {2026},
  volume = {10},
  number = {3},
  pages = {1032},
  doi = {10.62527/joiv.10.3.3210}
}
Kostenlos starten →