ABDULLAH AZZAM, ABDULLAH AZZAM (2025) CLUSTERING POTENSI KOPI MENGGUNAKAN METODE KMEANS BERBASIS GEOGRAPHIC INFORMATION SYSTEM (GIS) CLUSTERING COFFEE POTENTIAL USING THE K-MEANS METHOD BASED ON GEOGRAPHIC INFORMATION SYSTEM (GIS). Diploma thesis, UNIVERSITAS SULAWESI BARAT.
ABDULLAH AZZAH (pdf.io).pdf
Download (1MB)
ABDULLAH AZZAH.pdf
Restricted to Repository staff only
Download (6MB)
Abstract
Kabupaten Mamasa di Sulawesi Barat memiliki potensi besar dalam pengembangan komoditas kopi, namun masih minim sistem pendukung berbasis data spasial untuk analisis potensi lahan. Penelitian ini bertujuan membangun sistem yang mengintegrasikan algoritma K-Means manual dengan visualisasi peta interaktif berbasis Geographic Information System (GIS) untuk mengelompokkan potensi kopi secara spasial. Data dianalisis berdasarkan atribut numerik seperti luas lahan, jumlah petani, produksi, dan produktivitas, dengan proses normalisasi menggunakan MinMaxScaler. Evaluasi klaster menggunakan Davies-Bouldin Index (DBI) menunjukkan bahwa hasil clustering memiliki tingkat kompaksi dan separasi yang baik. Sistem berhasil membentuk tiga klaster deskriptif (“Rendah”, “Sedang”, “Tinggi”) yang divisualisasikan dalam peta interaktif berbasis Streamlit. Uji coba menunjukkan semua fitur, mulai dari unggah data, clustering, hingga visualisasi GIS, berjalan sesuai ekspektasi. Hasil penelitian ini memberikan kontribusi nyata dalam pengambilan keputusan strategis di sektor perkebunan kopi.
Mamasa Regency in West Sulawesi holds significant potential for coffee commodity development, yet lacks spatial data-based support systems for land potential analysis. This study aims to develop a system that integrates a manual K-Means algorithm with interactive map visualization based on Geographic Information System (GIS) to spatially cluster coffee potential. The data were analyzed using numerical attributes such as land area, number of farmers, production, and productivity, with normalization performed using MinMaxScaler. Cluster evaluation using the Davies-Bouldin Index (DBI) indicates that the clustering results demonstrate good compactness and separation. The system successfully formed three descriptive clusters (“Low”, “Medium”, “High”), which are visualized through an interactive map built with Streamlit. Testing showed that all features from data upload, clustering, to GIS visualization functioned as expected. The findings of this research provide tangible contributions to strategic decision-making in the coffee plantation sector.
| Item Type: | Thesis (Diploma) |
|---|---|
| Uncontrolled Keywords: | K-Means, Kopi Mamasa, GIS, Clustering. K-Means, Mamasa Coffee, GIS, Clustering. |
| Subjects: | FAKULTAS TEKNIK > Informatika |
| Divisions: | Fakultas Teknik |
| Depositing User: | Unnamed user with email aryatiunsulbar@gmail.com |
| Date Deposited: | 13 Oct 2025 03:13 |
| Last Modified: | 13 Oct 2025 03:13 |
| URI: | https://repository.unsulbar.ac.id/id/eprint/2371 |
