Hybrid Machine Learning for Stunting Prevalence: A Novel Comprehensive Approach to Its Classification, Prediction, and Clustering Optimization in Aceh, Indonesia DOI Creative Commons
Novia Hasdyna, Rozzi Kesuma Dinata, Rahmi Rahmi

et al.

Informatics, Journal Year: 2024, Volume and Issue: 11(4), P. 89 - 89

Published: Nov. 21, 2024

Stunting remains a significant public health issue in Aceh, Indonesia, and is influenced by various socio-economic environmental factors. This study aims to address key challenges accurately classifying stunting prevalence, predicting future trends, optimizing clustering methods support more effective interventions. To this end, we propose novel hybrid machine learning framework that integrates classification, predictive modeling, optimization. Support Vector Machines (SVM) with Radial Basis Function (RBF) Sigmoid kernels were employed improve the classification accuracy, RBF kernel outperforming kernel, achieving an accuracy rate of 91.3% compared 85.6%. provides reliable tool for identifying high-risk populations. Furthermore, linear regression was used yielding low Mean Squared Error (MSE) 0.137, demonstrating robust prevalence. Finally, process optimized using weighted-product approach enhance efficiency K-Medoids. optimization reduced number iterations from seven three improved Calinski–Harabasz Index 85.2 93.7. comprehensive not only enhances prediction, results but also delivers actionable insights targeted interventions policymaking aimed at reducing Aceh.

Language: Английский

Hybrid Machine Learning for Stunting Prevalence: A Novel Comprehensive Approach to Its Classification, Prediction, and Clustering Optimization in Aceh, Indonesia DOI Creative Commons
Novia Hasdyna, Rozzi Kesuma Dinata, Rahmi Rahmi

et al.

Informatics, Journal Year: 2024, Volume and Issue: 11(4), P. 89 - 89

Published: Nov. 21, 2024

Stunting remains a significant public health issue in Aceh, Indonesia, and is influenced by various socio-economic environmental factors. This study aims to address key challenges accurately classifying stunting prevalence, predicting future trends, optimizing clustering methods support more effective interventions. To this end, we propose novel hybrid machine learning framework that integrates classification, predictive modeling, optimization. Support Vector Machines (SVM) with Radial Basis Function (RBF) Sigmoid kernels were employed improve the classification accuracy, RBF kernel outperforming kernel, achieving an accuracy rate of 91.3% compared 85.6%. provides reliable tool for identifying high-risk populations. Furthermore, linear regression was used yielding low Mean Squared Error (MSE) 0.137, demonstrating robust prevalence. Finally, process optimized using weighted-product approach enhance efficiency K-Medoids. optimization reduced number iterations from seven three improved Calinski–Harabasz Index 85.2 93.7. comprehensive not only enhances prediction, results but also delivers actionable insights targeted interventions policymaking aimed at reducing Aceh.

Language: Английский

Citations

0