Classification of Stunting using a Website-Based Support Vector Machine (SVM) Algorithm (Case Study: Pagar Merbau Community Health Center)

Muhammad Davin Diza Ghifary; Chairunisah; Said Iskandar Al Idrus; Faridawaty Marpaung; Kana Saputra

doi:10.59934/jaiea.v5i1.1774

Authors

Muhammad Davin Diza Ghifary Universitas Negeri Medan
Chairunisah Universitas Negeri Medan
Said Iskandar Al Idrus Universitas Negeri Medan
Faridawaty Marpaung Universitas Negeri Medan
Kana Saputra Universitas Negeri Medan

DOI:

https://doi.org/10.59934/jaiea.v5i1.1774

Keywords:

stunting, Support Vector Machine, classification, website, Data Mining

Abstract

Stunting is a chronic nutritional problem that affects the physical growth and cognitive development of toddlers, and remains a serious challenge in Indonesia, including in the working area of the Pagar Merbau Community Health Center. Determining stunting status in the field often faces the risk of error when done manually, so a fast and accurate classification system is needed. This study aims to develop a classification model for the nutritional status of infants (normal, stunted, and severely stunted) using the Support Vector Machine (SVM) algorithm with a Radial Basis Function (RBF) kernel, and to integrate it into a web-based system to facilitate healthcare workers in conducting automatic data analysis. The data used were collected from infants aged 0–60 months at the Pagar Merbau Community Health Center (2023–2025), with four main attributes: gender, age, weight, and height. Model testing yielded an accuracy of 90%, with precision values of 0.95 (normal), 0.78 (stunting), and 1.00 (severe stunting), and recall values of 0.73, 0.96, and 1.00 for the same class. The implementation of the model on the website allows for the input of infant data, automatic analysis, and real-time visualization of classification results. This system is expected to improve the accuracy, efficiency, and precision of nutritional interventions at the Pagar Merbau Community Health Center

Downloads

Download data is not yet available.

References

Apriastini, N., et al., “Determinants of Stunting in Early Childhood,” Public Health Journal, 2024.

Haskay, R., “Chronic Malnutrition and Cognitive Delay in Indonesian Children,” Journal of Nutrition Studies, 2024.

Kurniati, D., Djuwita, A., & Istiqfani, N., “Nutritional Deficiency and Growth,” Child Health Research, 2023.

Gurning, R., Mulyani, A., & Setiawan, T., “Stunting Statistics in Indonesia,” Indonesian Health Review, 2022.

Prasetiya, T., et al., “Manual Anthropometric Assessment Errors,” BMC Pediatrics, 2020.

Wahyuni, S.D., & Kusumodestoni, R.H., “Implementation of Support Vector Machine in Medical Classification,” IJCA, 2024.

Cortes, C., & Vapnik, V., “Support Vector Networks,” Machine Learning, vol. 20, pp. 273–297, 1995

Prastyo, D., et al., “Kernel Functions in SVM,” Data Science Review, 2020.

Fajri, R., & Primajaya, D., “Parameter Optimization in SVM,” Computational Intelligence Journal, 2023.

Dwi Normawati, “Evaluation Metrics in Classification,” Information Systems Research, 2021.

Widhari, W., Triyadi, A., & Sari, R.T.K., “Naïve Bayes and KNN in Diagnosing Stunting,” Int. J. Health Informatics, 2022.

Prasetya, T., Ali, I., & Rohmat, C.L., “Classification of Stunting in Slangit Village Using KNN,” Applied Computing Journal, 2020.

Kurniawan, B., Gunawan, R., & Elanda, A. (2022, May). Redesain Sistem Aplikasi Web Sumber Reload. In Prosiding Seminar Nasional Inovasi dan Adopsi Teknologi (INOTEK) (Vol. 2, No. 1, pp. 240-249).

Gustiandi, B. (2023). Langkah Awal Menguasai Bahasa Pemrograman Python.

Santoso, H.R., Yulina, S., & Muslim, I. (2024). Pelatihan Pemrograman Dasar Python pada SMKN 7 Pekanbaru. JITER-PM (Jurnal Inovasi Terapan - Pengabdian Masyarakat) [14] Gustiandi, B. (2023). Langkah Awal Menguasai Bahasa Pemrograman Python.

Tommy Rustandi, S.R., Suhaedi, D., & Pemanasari, Y. (2023). Pemetaan Hyperlane Pada Support Vector Machine. Bandung Conference Series: Mathematics.