Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Jurnal Teknoif Teknik Informatika Institut Teknologi Padang

SISTEM INFORMASI GEOGRAFIS PEMETAAN JENIS KEKERASAN TERHADAP PEREMPUAN DI JAWA TENGAH MENGGUNAKAN METODE K-MEANS CLUSTERING Maulana, Novan; Harjanta, Aris Tri Jaka; Novita, Mega
Jurnal Teknoif Teknik Informatika Institut Teknologi Padang Vol 13 No 2 (2025): TEKNOIF OKTOBER 2025
Publisher : ITP Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21063/jtif.2025.V13.2.77-86

Abstract

Violence against women is a social issue with widespread impacts and remains highly prevalent in Indonesia, including in Central Java Province. The forms of violence include physical, psychological, and sexual abuse, exploitation, neglect, and others. Presenting data in a general form without spatial mapping often makes it difficult to identify regions with high levels of vulnerability. This study aims to cluster regencies/municipalities in Central Java based on types of violence against women by integrating the K-Means Clustering method with Geographic Information Systems (GIS). The data used are records of violence against women in 2024 from 35 regencies/municipalities. The K-Means method was applied iteratively until reaching a convergent condition, resulting in three main clusters. The clustering results were visualized using QGIS software in the form of thematic maps, facilitating the interpretation of spatial patterns. The evaluation shows that spatial classification was successfully applied with a spatial match rate of 100%, and a Silhouette Score of 0.577, indicating a moderately good cluster quality. The majority of regions are included in the low cluster, while only one region is in the high cluster. This study concludes that the combination of K-Means and GIS is effective in detecting and visualizing regional vulnerability to violence against women and has the potential to serve as a basis for developing more targeted and evidence-based protection policies. It is recommended that future research expand the dataset, include additional risk variables, and explore alternative clustering methods or advanced spatial analyses to improve the accuracy and understanding of violence patterns.