Abstract
Stunting is a serious problem for the health of children under five. The lack of quality of life for toddlers is one of the causes of the current high prevalence of stunting. East Nusa Tenggara ranks second with the highest prevalence of stunting in Indonesia in 2023. This high rate is triggered by several factors, such as health, socio-economics and environment. In terms of the environment, remote sensing technology can be utilised as a supporting tool in monitoring the incidence of stunting in the region. This study aims to map districts/cities in East Nusa Tenggara based on the incidence of stunting in children under five years old through the integration of multi-source satellite imagery and official statistics using machine learning algorithms. Researchers used non-hierarchical clustering methods such as K-Means, K-Medoids, and Fuzzy C-Means which will then be compared to find the best method. The best method was obtained based on internal validity, such as connectivity, Dunn index, and Silhouette coefficient. The results of this study show that K-Means is the best clustering method based on internal validity criteria. The optimal number of clusters formed is two with connectivity, Dunn index, and Silhouette coefficient values of 2.9290, 0.6931, and 0.4509, respectively. Areas included in cluster two are still very vulnerable to stunting problems. The cluster results obtained are expected to be the basis for the government in overcoming stunting problems in East Nusa Tenggara.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call