Clustering Analysis of Cocoa-Producing Areas Using the Gaussian Mixture Model Algorithm (A Case Study in Southeast Aceh Regency)
DOI:
https://doi.org/10.24235/93m0r329Keywords:
Gaussian Mixture Model, Clustering, agriculture, Southeast Aceh, information systemAbstract
This study aims to identify and cluster agricultural areas in Southeast Aceh Regency using the Gaussian Mixture Model (GMM) algorithm. The dataset consists of village-level agricultural data, including land area, production volume, productivity, and the number of farmers. To ensure comparability across variables, Z-Score normalization was applied. The optimal number of clusters was determined using the Bayesian Information Criterion (BIC), resulting in three distinct groups: high, medium, and low production areas. Clustering performance was evaluated using the Silhouette Score (0.3893) and the Davies-Bouldin Index (0.8548), indicating moderate clustering quality with reasonable separation between clusters. To improve accessibility and practical use, a web-based information system was developed to visualize agricultural data, clustering outcomes, and evaluation metrics interactively. These findings highlight the value of GMM-based machine learning in supporting data-driven decision-making and prioritizing agricultural development efforts by local governments.
Downloads
References
[1] J. Porsiana, J. Riry, and M. K. Lesilolo, “Pengujian Kadar Air Biji Kakao dengan Suhu Tinggi dan Rendah terhadap Kualitas Biji Kakao (Testing the moisture content of cocoa beans at high and low temperatures on the quality of cocoa beans),” J. Pertan. Kepul., vol. 8, no. 1, pp. 7–12, 2024.
[2] Muhammad Fajar Zikri, Cut Mulyani, and Yenni Marnita, “Tingkat Serangan Penyakit Busuk Buah Kakao (Phytophthora Palmivora L.) Dan Kehilangan Hasil Tanaman Kakao Di Kecamatan Darul Ihsan Kabupaten Aceh Timur,” J. Penelit. Agrosamudra, vol. 9, no. 2, pp. 11–20, 2022, https://doi.org/10.33059/jupas.v9i2.6565.
[3] R. Ariani, “Jurnal Sains Pertanian Analisis produktivitas kakao di Kabupaten Aceh Tenggara Analysis of cocoa productivity in Southeast Aceh District,” vol. 6, pp. 96–98, 2022.
[4] J. Riyono, S. D. Puspa, and C. E. Pujiastuti, “Simulasi Clustering Provinsi di Indonesia dalam Penyebaran Covid-19 Berdasarkan Indikator Kesehatan Masyarakat Menggunakan Algoritma Gaussian Mixture Model,” Majamath J. Mat. dan Pendidik. Mat., vol. 5, no. 1, pp. 43–60, 2022.
[5] N. N. Alyarahma, G. Kholijah, and C. Sormin, “Pengelompokan Provinsi di Indonesia Menggunakan Gaussian Mixture Model Berdasarkan Indikator Kemiskinan,” vol. 6, no. 2, pp. 158–167, 2024, https://doi.org/10.31605/jomta.v6i2.4032.
[6] D. Siregar, W. Rahayu, B. M. Wardana, Ketrin Natasya Stefany, and Bayu Wibisono, “Characteristics of Provinces in Indonesia Based on JKN Indicator Outcomes by Gaussian Mixture Model with Expectation-Maximization Algorithm and Biplot,” J. Stat. dan Apl., vol. 8, no. 1, pp. 17–30, 2024, https://doi.org/10.21009/jsa.08102.
[7] M. Harahap, A. W. D. R. Zamili, M. A. Arvansyah, E. F. Saragih, S. Rajen, and A. M. Husein, “K-Means Clustering Algorithm Approach in Clustering Data on Cocoa Production Results in the Sumatra Region,” J. Resti, vol. 6, no. 6, pp. 905–910, 2022, https://doi.org/10.29207/resti.v6i6.4199.
[8] A. Kartakoullis, N. Caporaso, M. B. Whitworth, and I. D. Fisk, “Gaussian mixture model clustering allows accurate semantic image segmentation of wheat kernels from near-infrared hyperspectral images,” Chemom. Intell. Lab. Syst., vol. 259, no. February, p. 105341, 2025, https://doi.org/10.1016/j.chemolab.2025.105341.
[9] F. Riza, S. Safwandi, and S. Fadlan, “Klasifikasi Varietas Kopi Berdasarkan Kondisi Tanah dan Suhu Menggunakan Algoritma Gaussian Naïve Bayes,” J. Algoritm., pp. 312–323, 2025, https://doi.org/10.33364/algoritma/v.22-1.2311.
[10] N. Hendrastuty, “Penerapan Data Mining Menggunakan Algoritma K-Means Clustering Dalam Evaluasi Hasil Pembelajaran Siswa,” J. Ilm. Inform. dan Ilmu Komput., vol. 3, no. 1, pp. 46–56, 2024, https://doi.org/10.58602/jima-ilkom.v3i1.26.
[11] N. Nur Afidah, “Penerapan Metode Clustering dengan Algoritma K-means untuk Pengelompokkan Data Migrasi Penduduk Tiap Kecamatan di Kabupaten Rembang,” Prism. Pros. Semin. Nas. Mat., vol. 6, pp. 729–738, 2023.
[12] Taufik Hidayat, Mohamad Jajuli, and Susilawati, “Clustering daerah rawan stunting di Jawa Barat menggunakan algoritma K-Means,” Infotech J. Inform. Teknol., vol. 4, no. 2, pp. 137–146, 2023, https://doi.org/10.37373/infotech.v4i2.642.
[13] R. K. Dinata, N. Hasdyna, S. Retno, and M. Nurfahmi, “K-means algorithm for clustering system of plant seeds specialization areas in east Aceh,” Ilk. J. Ilm., vol. 13, no. 3, pp. 235–243, 2021, https://doi.org/10.33096/ilkom.v13i3.863.235-243.
[14] S. R. Kasa and V. Rajan, “Avoiding inferior clusterings with misspecified Gaussian mixture models,” Sci. Rep., vol. 13, no. 1, pp. 1–13, 2023, doi: 10.1038/s41598-023-44608-3.
[15] Y. L. Nainel, E. Buulolo, and I. Lubis, “Penerapan Data Mining Untuk Estimasi Penjualan Obat Berdasarkan Pengaruh Brand Image Dengan Algoritma Expectation Maximization (Studi Kasus: PT. Pyridam Farma Tbk),” Jurikom (Jurnal Ris. Komputer), vol. 7, no. 2, p. 214, 2020, https://doi.org/10.30865/jurikom.v7i2.2097.
[16] Suhada, G. L. Ginting, and R. K. Hondro, “Penerapan Data Mining Untuk Memprediksi Besarnya Pembayaran Pajak Kendaraan Pada: (Badan Pengelolaan Pajak Dan Retribusi Daerah Upt Samsat Medan Selatan) Menggunakan Algoritma Expectation Maximization,” Bull. Inf. Technol., vol. 2, no. 2, pp. 69–75, 2021.
[17] J. You, Z. Li, and J. Du, “A new iterative initialization of EM algorithm for Gaussian mixture models,” PLoS One, vol. 18, no. 4 April, pp. 1–17, 2023, https://doi.org/ 10.1371/journal.pone.0284114.
[18] N. W. Yanto, H. Sukoco, and S. N. Neyman, “Pemodelan Proxy Anonim Menggunakan Algoritme Expectation Maximization Dengan Data Balancing,” J. Ilmu Komput. dan Bisnis, vol. 12, no. 1, pp. 60–69, 2021, https://doi.org/10.47927/jikb.v12i1.91.
[19] P. P. Allorerung, A. Erna, and M. Bagussahrir, “Analisis Performa Normalisasi Data untuk Klasifikasi K-Nearest Neighbor pada Dataset Penyakit,” vol. 9, no. 3, pp. 178–191, 2024.
[20] I. Permana and F. N. S. Salisah, “Pengaruh Normalisasi Data Terhadap Performa Hasil Klasifikasi Algoritma Backpropagation,” Indones. J. Inform. Res. Softw. Eng., vol. 2, no. 1, pp. 67–72, 2022, https://doi.org/10.57152/ijirse.v2i1.311.
