Hybrid Genetic Algorithm and Particle Swarm Optimization as Centroid Initialization in K-Means Clustering for National Nutrition Dataset
DOI:
https://doi.org/10.5614/itbj.ict.res.appl.2026.20.2.5Keywords:
genetic algorithm, hybrid clustering, K-means, national nutrition, particle swarm optimizationAbstract
The efficacy of large-scale public health interventions, such as Indonesia?s Makan Bergizi Gratis (MBG) program, relies heavily on the precise identification of vulnerable regions. Conventional clustering techniques like K-means are essential for such mapping but frequently suffer from performance degradation due to sensitivity to random centroid initialization, leading to suboptimal and unstable solutions. This study proposes a sequential hybrid metaheuristic framework (K-means+GAPSO) that synergizes the broad global exploration of genetic algorithms (GA) with the rapid local exploitation of particle swarm optimization (PSO). The proposed model was rigorously validated using the Indonesian National Nutrition Dataset (2021?2023) through 10 independent runs to ensure stochastic robustness. Computational results at the optimal cluster count (K = 3) demonstrated that the K-means+GAPSO (prob = 0.3) configuration significantly outperformed the standard baselines, achieving a highly stable silhouette mean of 0.7130 (0.0036) and a Davies-Bouldin index mean of 0.4708 (0.0178). This metric achievement represents a substantial performance improvement in separation and compactness compared to standard K-means. The implementation of this structurally robust method for nutritional clustering provides a reliable analytical foundation for policymakers to accurately target food security initiatives and minimize resource misallocation.
Downloads
References
Tsipi, L., Michailidis, E.T., Karavolos, M., Vouyioukas, D. & Kanatas, A.G., AI-driven Aerial Relay Placement and Power Allocation for Enhanced Secrecy in Untrusted UAV-enabled Networks, IEEE Access., 13, pp. 99970-99984, 2025. doi:10.1109/ACCESS.2025.3577053.
Yin, X., Rong, Y., Li, L., He, W., Lv, M. & Sun, S., Health State Prediction Method Based on Multi-featured Parameter Information Fusion, Appl. Sci., 14(15), p. 6809, Aug. 2024. doi:10.3390/app14156809.
Latief, M.A., Pandiya, R. & Putri, A.L.R., Least Square-based Differential Evolution Algorithm for N-dimensional Data Clustering Problem, Eurasian J. Math. Comput. Appl., 2025. doi:10.32523/2306-6172-2025-13-3-36-49.
Abdo, A., Abdelkader, O. & Abdel-Hamid, L., SA-PSO-GK++: A New Hybrid Clustering Approach for Analyzing Medical Data, IEEE Access., 12, pp. 12501-12516, 2024. doi:10.1109/ACCESS.2024.3350442.
Latief, M.A., Candraningtyas, R.G., Khomsah, S. & Pandiya, R., Grey Wolf Algorithm for Optimizing K-modes in Determining Initial Centroid, in 2024 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT), Mataram, Indonesia: IEEE, pp. 429-436, Nov. 2024. doi:10.1109/COMNETSAT63286.2024.10862708.
Suwirmayanti, N.L.G.P., Gede Darma Putra, I.K., Sudarma, M., Sukarsa, I.M. & Setyaningsih, E., IWOKM-GA Hybrid Method to Improve Clustering Accuracy in Banking Data, Int. J. Comput. Digit. Syst., 18(1), pp. 1-11, Apr. 2025. doi:10.12785/ijcds/1571110934.
Karishma & Kumar, H., A Novel Hybrid Model for Task Scheduling based on Particle Swarm Optimization and Genetic Algorithms, Math. Eng., 6(4), pp. 559-606, 2024. doi:10.3934/mine.2024023.
Politi, R.R. & Tanyel, S., Minimizing Delay at Closely Spaced Signalized Intersections Through Green Time Ratio Optimization: A Hybrid Approach with K-means Clustering and Genetic Algorithms, IEEE Access., 13, pp. 43981-43999, 2025. doi:10.1109/ACCESS.2025.3549970.
Zhou, Y. & Yan, The Application of Big Data Technology Combined with Improved Genetic Simulated Annealing Algorithm in the Construction of Intelligent Delivery Models, Int. J. Mechatron. Appl. Mech., 1(20), Jun. 2025. doi:10.17683/ijomam/issue20.7.
Hassan, E. et al., A Hybrid K-Means++ and Particle Swarm Optimization Approach for Enhanced Document Clustering, IEEE Access., 13, pp. 48818-48840, 2025. doi:10.1109/ACCESS.2025.3535226.
Pramudya, R.I., Kurniawan, T.A., Candra, M.H., Onn, C.W. & Dissanayake, K.K., Advancing Unsupervised Clustering: A Systematic Review of Hybrid K-means and Metaheuristic Optimization Algorithms in Data Mining, Comput. Sci. Rev., 61, 100972, Aug. 2026. doi: 10.1016/j.cosrev.2026.100972.
Bafadal, I.Z., Ardi, R. & Yuraisyah Salsabila, N., A Proposed Reverse Logistics Network for End-of-life Electric Vehicle Battery Management in the Jakarta Greater Area: A MILP Approach, World Electr. Veh. J., 16(8), 2025. doi:10.3390/wevj16080476.
Li, K., Wang, Z., Zhou, Y. & Li, S., Lung Adenocarcinoma Identification Based on Hybrid Feature Selections and Attentional Convolutional Neural Networks, Math. Biosci. Eng., 21(2), pp. 2991-3015, 2024. doi:10.3934/mbe.2024133.
Zaghdoud, R., Rhaiem, O.B., Amara, M., Mesghouni, K. & Galet, S., A Hybrid Genetic Algorithm Approach based on Patient Classification to Optimize Home Health Care Scheduling and Routing, Eng. Technol. Appl. Sci. Res., 14(4), pp. 15099-15105, Aug. 2024. doi:10.48084/etasr.7649.
Seo, Y., Lim, D., Lee, J., So, J. & Kim, H., A Framework for Evaluating Driving Patterns of Automated Vehicle Based on On-Road Driving Records, IEEE Access., 13, pp. 67894-67907, 2025. doi:10.1109/ACCESS.2025.3556299.
Wang, X.L., Guo, H., Wen, F. & Wang, K., Optimized low carbon scheduling strategy of integrated energy sources considering load aggregators, AIP Adv., 14(4), 045228, Apr. 2024. doi:10.1063/5.0190409.
Li, J., Ma, Y., Li, H., Liu, Y. & Li, Y., A Load Classification Method Based on Hybrid Clustering of Continuous?Discrete Electricity Consumption Characteristics, Processes, 13(4), 1208, Apr. 2025. doi:10.3390/pr13041208.
National Food Agency, Food Open Data: Data for 2021?2023, 2024. Available: https://data.badanpangan.go.id/. (15 June 2026)
