JAFT • pISSN 2355-9152 • eISSN 2614-7076 • Member of CrossRef®

DOI: https://doi.org/10.17728/jaft.29754

Multivariate Exploration of Food Security in the Sulampua Region Identification of Clusters and Dominant Dimensions of Food Security

*Wawan Saputra  -  Department of Statistics and Data Science, School of Science, Mathematics, and Informatics, IPB University, Bogor, Indonesia, Indonesia
Naufalia Alfiryal  -  Department of Statistics and Data Science, School of Science, Mathematics, and Informatics, IPB University, Bogor, Indonesia, Indonesia
I Putu Gde Inov Bagus Prasetya  -  Department of Statistics and Data Science, School of Science, Mathematics, and Informatics, IPB University, Bogor, Indonesia, Indonesia
Anwar Fitrianto  -  Department of Statistics and Data Science, School of Science, Mathematics, and Informatics, IPB University, Bogor, Indonesia, Indonesia
Kevin Alifviansyah  -  Department of Statistics and Data Science, School of Science, Mathematics, and Informatics, IPB University, Bogor, Indonesia, Indonesia
Open Access Copyright 2025 Journal of Applied Food Technology

Citation Format:
Abstract

Food security is a strategic issue closely related to economic development, community welfare, and the achievement of sustainable development goals. The Food Security Index (FSI) is an important instrument for measuring food security conditions at the provincial and district/city levels. However, FSI performance in Indonesia still shows regional disparities, particularly in Sulawesi, Maluku, and Papua (Sulampua), which tend to have low scores. This study aims to explore patterns of food security and vulnerability in Sulampua through multivariate analysis and regional clustering using K-Means and K-Medoids (PAM) methods. The analysis begins with Principal Component Analysis (PCA) to reduce the dimensionality of FSI indicators and identify dominant factors contributing to data variation. The PCA results show that the first three components explain more than 77% of the variance, with dominant factors including poverty, food expenditure, basic infrastructure access, as well as health and nutrition indicators. The clustering analysis produces two main groups: cluster 1, which includes the majority of districts/cities in Sulawesi and Maluku with relatively better food security, and cluster 2, consisting of 16 districts/cities in Papua with significant food insecurity. Cluster validity evaluation indicates that the K-Medoids method performs better than K-Means, being more robust to outliers and producing more consistent cluster separation. This study contributes to the literature by providing multivariate visual exploration and regional classification based on FSI indicators, which can serve as a basis for formulating more targeted food security policies in the Sulampua region.

Fulltext View|Download
Keywords: Food security; PCA; K-Means; K-Medoids; Sulampua

Article Metrics:

Article Info
Section: Research Articles
Language : EN
Recent articles
Sustainable Marine Macroalgal Polysaccharide Films and Coatings: Toward Active and Intelligent Food Packaging System Mechanisms and Applications of Essential Oils as Natural Preservatives in Meat Products: A Review Improved Extrusion Cooking Technology (IECT): Utilization of Milder Conditions for Better Starch Modification Evaluation of Effects of Specific Bioactive Compounds in Plant, Propolis and Bee-Pollen on Crohn’s Disease: A Food Nutrition Approach Physicochemical Quality and Antioxidant Enhancement of Jack Bean Sauce with Pineapple Extract Addition and Different Fermentation Time Development and Characterization of Calcium Lactate-Activated Sodium Alginate-Gum Arabic Edible Films More recent articles
  1. Arora, P., Deepali, Varshney, S. 2016. Analysis of K-means and K-medoids algorithm for big data. Procedia Computer Science 78, 507–512
  2. Aselnino, P., Wijayanto, A.W. 2023. Comparative analysis of hierarchical and non-hierarchical methods in clustering Indonesian provinces based on women empowerment indicators. Indonesian Journal of Applied Statistics, 6(1), 57–68
  3. Azhar, A.L., Sulianto. 2023. Modeling of food security index in Indonesia based on ordinal logistic regression with random effects panel data approach. Jurnal Ketahanan Nasional 29(2), 166–177. doi: 10.22146/jkn.86511
  4. Badan Pangan Nasional. 2022. Food Security Index. Jakarta: Badan Pangan Nasional
  5. Dewi, D.A.I.C., Pramita, D.A.K. 2019. Comparative analysis of Elbow and Silhouette methods in K-Medoids clustering algorithm for grouping Balinese handicraft production. Jurnal Matrix, 9(3), 102–108
  6. Dunn, J.C. 1974. Well separated clusters and optimal fuzzy partitions. Journal of Cybernetics 4(1), 95–104
  7. Firliana, R., Wulaningrum, R., Sasongko, W. 2015. Implementation of Principal Component Analysis (PCA) for human face recognition. Nusantara of Engineering, 2(1), 65–70
  8. Food and Agriculture Organization of the United Nations. 2013. The state of food insecurity in the world 2013: The multiple dimensions of food security. Rome: FAO
  9. Herman, T., Heryanto, R. 2022. Cluster analysis with K-Means versus K-Medoids in financial performance evaluation. Applied Sciences 12(15), 7985
  10. Khairiyakh, R., Irham, Mulyo, J.H. 2015. Contribution of agricultural sector and sub-sectors to the Indonesian economy. Ilmu Pertanian 18(3), 150–159
  11. Kossakov, M., Mukasheva, A., Balbayev, G., Seidazimov, S., Mukammejanova, D., Sydybayeva, M. 2024. Quantitative comparison of machine learning clustering methods for tuberculosis data analysis. Engineering Proceedings 60(1), 20. doi: 10.3390/engproc2024060020
  12. Nahdliyah, M.A., Widiharih, T., Prahutama, A. 2019. K-medoids clustering method with silhouette index and C-index validation (Case study: number of crimes in Central Java regencies/cities in 2018). Jurnal Gaussian 8(2), 161–170. Available from: http://ejournal3.undip.ac.id/index.php/gaussian
  13. Prihandoko, Bertalya, Ramadhan, M.I. 2017. An analysis of natural disaster data using K-means and K-medoids algorithms of data mining techniques. Proceedings of the 15th International Conference on Quality in Research (QiR): International Symposium on Electrical and Computer Engineering, 221. IEEE. doi: 10.1109/QIR.2017.8168485
  14. Savira, A.R. 2023. Optimizing clustering models using Principal Component Analysis for car customers. Indonesian Journal of Computing and Cybernetics Systems (IJCCS), 17(2), 145–152. https://doi.org/10.22146/ijccs.94744
  15. Shang, Q., Yu, Y., Xie, T. 2022. A hybrid method for traffic state classification using K-medoids clustering and self-tuning spectral clustering. Sustainability 14(17), 11068. doi: 10.3390/su141711068
  16. Ula, M., Ula, M., Yulisda, D., Susanti, S. 2023. Fuzzy C-means with Borda algorithm in cluster determination system for food-prone areas in North Aceh. ILKOM Jurnal Ilmiah 15(1), 21–31
  17. Wicaksono, A.P., Widjaja, S., Nugroho, M.F., Christina, Putri, P. 2024. Analysis of K-value toward ticket sales clustering on K-Means using Elbow and Silhouette methods. SISTEMASI: Jurnal Sistem Informasi 13(1), 28–38
  18. Zhang, L., Yang, Z., Xiu, J., Liu, C. 2020. An optimized interpolation model based on K-means clustering for rainfall calculation. Proceedings of the 5th International Conference on Mechanical, Control and Computer Engineering (ICMCCE), 1198–1202. IEEE

Last update:

No citation recorded.

Last update:

No citation recorded.