Pengelompokan Desa Berdasarkan Ketahanan Pangan di Kabupaten Tuban Menggunakan Metode K-Means dan Density-Based Spatial Clustering of Application With Noise

Heksa, Bagus Adi Cahyono (2025) Pengelompokan Desa Berdasarkan Ketahanan Pangan di Kabupaten Tuban Menggunakan Metode K-Means dan Density-Based Spatial Clustering of Application With Noise. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5003211068-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (2MB) | Request a copy

Abstract

Ketahanan pangan merupakan aspek penting dalam pembangunan berkelanjutan. Penelitian ini bertujuan untuk mengelompokkan 328 desa di Kabupaten Tuban berdasarkan tiga pilar ketahanan pangan: ketersediaan, keterjangkauan, dan pemanfaatan. Dua metode klasterisasi diterapkan, yaitu K-Means dan DBSCAN, untuk membandingkan efektivitas pengelompokan. K-Means membentuk empat cluster, sedangkan DBSCAN menghasilkan tiga cluster utama serta satu kelompok noise yang merupakan outlier. Evaluasi performa menggunakan Davies-Bouldin Index menunjukkan DBSCAN lebih optimal (DBI = 0,7835) dibandingkan K-Means (DBI = 1,2979). Hasil ini menunjukkan bahwa DBSCAN lebih cocok untuk memetakan kondisi ketahanan pangan yang kompleks dan tidak merata. Penelitian ini diharapkan dapat menjadi dasar bagi perumusan kebijakan pangan berbasis wilayah yang lebih tepat sasaran.
=====================================================================================================================================
Food security is a critical aspect of sustainable regional development. This study aims to cluster 328 villages in Tuban Regency based on the three main pillars of food security: availability, accessibility, and utilization. Two clustering methods—K-Means and Density-Based Spatial Clustering of Applications with Noise (DBSCAN)—were applied to analyze and compare the effectiveness of each approach. The K-Means algorithm formed four clusters, while DBSCAN produced three main clusters along with one noise group, which represents villages with extreme conditions. Performance evaluation using the Davies-Bouldin Index indicated that DBSCAN yielded better clustering quality (DBI = 0,7835) compared to K-Means (DBI = 1,2979). These results suggest that DBSCAN is more suitable for capturing complex and uneven patterns of food security conditions. The clustering outcomes are expected to support the development of spatially-targeted food security policies that are more equitable and data-driven.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	DBSCAN, Kabupaten Tuban, Ketahanan Pangan, K-Means, Food Security, Tuban District
Subjects:	Q Science > QA Mathematics > QA278.55 Cluster analysis Q Science > QA Mathematics > QA278 Cluster Analysis. Multivariate analysis. Correspondence analysis (Statistics)
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Bagus Adi Cahyono Heksa
Date Deposited:	04 Aug 2025 08:26
Last Modified:	04 Aug 2025 08:26
URI:	http://repository.its.ac.id/id/eprint/127108

Actions (login required)

View Item