<![CDATA[This study aims to analyze the spatial patterns of ambulance transport demand in Semarang City based on patients’ origin subdistricts, origin villages, and destination healthcare facilities. The analysis employed the K-Means Clustering algorithm as a data mining method to group areas according to similarities in the volume of ambulance requests. The dataset consisted of ambulance transport service records from January 2024 to September 2025, obtained from the Semarang City Health Office. The analytical procedures included data cleaning, normalization, determination of the optimal number of clusters using the Elbow Method, and cluster formation using K-Means. The results show two main clusters for subdistricts and destination healthcare facilities. High-demand subdistricts were generally densely populated areas such as Banyumanik and Pedurungan, with an average of 1,256 requests, while RSUP Dr. Kariadi emerged as the dominant referral facility with 3,893 requests. Meanwhile, village-level origins formed three clusters, with average demands of 549 (high), 190 (medium), and 36 (low). These findings are expected to support strategic planning for equitable ambulance fleet distribution and improved efficiency of patient transportation services in Semarang City.]]>
Copyrights © 2025
