<![CDATA[This manuscript proposes an approach that uses the Particle Swarm Optimization (PSO) algorithm to optimize the parameters of the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) method in mapping the spatial pattern of malnutrition in Java. Results showed that with a Silhouette Coefficient value close to 1 (0.134) and the lowest Davies-Bouldin Index (1.80), PSO successfully determined the optimal epsilon (eps) value of 1.76 and the optimal minimum number of points of 3. Index validation showed that DBSCAN could map the study area into three clusters that reflected the level of malnutrition, where 82 districts/cities were included in Cluster 0, 5 districts/cities in Cluster 1, and 3 districts/cities in Cluster 2. In contrast, 29 districts/cities were identified as noise. This finding confirms that the PSO approach in optimizing DBSCAN parameters can improve the method's effectiveness in handling complex cases such as malnutrition in a geospatial context.]]>
Copyrights © 2025
