<![CDATA[This study aims to compare the performance of K-Means, Fuzzy C-Means, and Hierarchical Clustering algorithms for non-communicable disease (NCD) surveillance data from the Lhokseumawe City Health Office, and to implement the best-performing algorithm into a web-based application. The dataset consisted of 3,421 records with 15 attributes collected in 2025. Data preprocessing included missing value checking and Min-Max normalization, while the optimal number of clusters was determined using the Elbow method, resulting in four clusters. Clustering performance was evaluated using the Silhouette Score, Davies-Bouldin Index, and Calinski-Harabasz Index. The results show that K-Means achieved the best performance, with a Silhouette Score of 0.8456, a Davies-Bouldin Index of 0.8005, and a Calinski-Harabasz Index of 2489.5630, outperforming Fuzzy C-Means and Hierarchical Clustering. The four resulting clusters showed distinct characteristics based on case frequency, dominant disease type, age group, and reporting period. K-Means was then implemented into a web-based application supporting dataset upload, filtering, clustering, and interactive visualization, which was validated through black box testing with all functions running successfully. This application is expected to help the Health Office analyze non-communicable disease patterns and support data-driven decision-making.]]>
Copyrights © 2026
