IMPLEMENTASI K-MEANS CLUSTERING BERBASIS GIS DALAM MENGIDENTIFIKASI DAERAH RAWAN KECELAKAAN LALU LINTAS DI KOTA MATARAM
Implementation of GIS-Based K-Means Clustering for Identifying Traffic Accident-Prone Areas in Mataram City
DOI:
https://doi.org/10.59896/gara.v20i2.642Keywords:
Cluster Analysis, Geographic Information System, K-Means Clustering, Traffic Accidents, Silhouette CoefficientAbstract
The growth in the number of vehicles in Mataram City has led to increased traffic congestion and a higher risk of accidents each year. Data from the Mataram Police Department recorded 439 traffic accident cases in 2023. This study aims to identify and map accident-prone areas using the K-Means Clustering method integrated with a Geographic Information System (GIS). The analysis was conducted using a clustering approach to group areas based on their level of accident risk, taking into account the weighted number of incidents and casualties. The quality of the clustering results was evaluated using the Silhouette Coefficient to measure cluster accuracy. The data used in this study are secondary traffic accident data from the 2021–2024 period obtained from the Mataram Police Department, focusing on arterial and collector roads. The results show that several road segments are consistently categorized as accident-prone, namely Jalan Lingkar Selatan, Jalan Ahmad Yani, Jalan Jenderal Sudirman, Jalan Sandubaya, Jalan Saleh Sungkar, and Jalan Sriwijaya. The K-Means Clustering method produced three categories of areas: “Safe,” “Moderately Prone,” and “Prone,” with Silhouette Coefficient values ranging from 0.7 to 1.0, indicating a strong cluster structure. GIS-based visualization provides a clear depiction of the distribution of accident-prone areas and can serve as a basis for the government in formulating traffic safety policies in Mataram City
References
Al Qubro, K., Fauzi, M., & Christine, A. (2022). Penentuan Titik Rawan Kecelakaan (Black Spot) Pada Ruas Jalan Nasional Palembang – Indralaya. Jurnal Penelitian Dan Kajian Teknik Sipil, 7(3), 151–158.
Aprianti, W., & Permadi, J. (2018). K-means Clustering Untuk Data Kecelakaan Lalu Lintas Jalan Raya Di Kecamatan Pelaihari. Jurnal Teknologi Informasi Dan Ilmu Komputer, 5(5), 613–620.
Aronoff, S. (1989). Geographic information systems: a management perspective. Taylor & Francis.
Badan Pusat Statistik Indonesia. (2024). Jumlah Kecelakaan, Korban Mati, Luka Berat, Luka Ringan, dan Kerugian Materi - Tabel Statistik.
Badan Pusat Statistik Kota Mataram (2025) Jumlah Kendaraan Bermotor Menurut Kabupaten/Kota dan Jenis Kendaraan di Provinsi Nusa Tenggara Barat.
Departemen Permukiman dan Prasarana Wilayah. (2004). Pedoman Angka Ekivalen Kecelakaan.
Harahap, B. (2019). Penerapan Algoritma K-Means Untuk Menentukan Kelas. 23, 394–403.
Pradipta, A. D. R., Awaluddin, M., & Nugraha, A. L., (2018). Pemetaan Daerah Rawan Kecelakaan di Kota Semarang dengan Menggunakan Metode Cluster Analysis (Studi Kasus: Kecamatan Banyumanik dan Tembalang). Jurnal Geodesi Undip, 7(7), 185–194.
Rousseeuw, P. J. (1987). Silhouettes: A Graphical Aid To The Interpretation And Validation Of Cluster Analysis. Journal of Computational and Applied Mathematics, 20(C), 53–65.
Surbakti, C., Sudarsono, B., & Wahyuddin, Y. (2021). Implementasi Metode Cluster Analysis Dalam Analisis Daerah Rawan kecelakaan di Kecamatan Semarang Utara. Jurnal Geodesi Undip, 10(3), 1–10.
Tan, P.-N., Steinbach, M., & Kumar, V. (2006). Introduction To Data Mining: Instructur’s. Library of Congress, 769.
Undang-Undang (UU) Nomor 22 Tahun 2009 Tentang Lalu Lintas Dan Angkutan Jalan (22). (2009). https://peraturan.bpk.go.id/Details/38654/uu-no-22-tahun-2009
WHO. (2018). Global Status Report On Road Safety 2018.
WHO. (2023). Global Status Report On Road Safety 2023.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Rohani Rohani, Hasyim Hasyim, Siti Maulida Handayani
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
