Pendekatan Hybrid DBSCAN dan K-Means untuk Optimasi Zona Penerimaan Peserta Didik Baru

Sa'adah Sa'adah; Finki Dona Marleny; Windarsyah Windarsyah

Authors

Sa'adah Sa'adah Universitas Muhammadiyah Banjarmasin
Finki Dona Marleny Universitas Muhammadiyah Banjarmasin
Windarsyah Windarsyah Universitas Muhammadiyah Banjarmasin

Keywords:

DBSCAN, Hybrid Clustering, K-Means, Klasterisasi Spasial, Sosial-Ekonomi, Zonasi Sekolah

Abstract

Penentuan batas wilayah dalam sistem Penerimaan Peserta Didik Baru (PPDB) berbasis zonasi menuntut mekanisme yang mampu mengakomodasi dua dimensi sekaligus: kedekatan geografis antara tempat tinggal siswa dengan sekolah, serta kondisi sosial-ekonomi keluarga yang melatarbelakangi kebutuhan mereka. Penelitian ini merancang pendekatan gabungan antara algoritma DBSCAN (Density-Based Spatial Clustering of Applications with Noise) guna membentuk zona geografis secara adaptif, dan K-Means untuk memetakan profil sosial-ekonomi siswa. Data yang digunakan mencakup 1.091 siswa SMAN 1 Alalak dengan 10 atribut sosial-ekonomi beserta koordinat GPS. Hasil optimasi menunjukkan bahwa DBSCAN dengan parameter ε=3,0 km dan min_samples=3 menghasilkan tiga zona bermakna dengan 54 titik terpencil (4,9%), Silhouette Score 0,7685, dan Davies-Bouldin Index 0,1447. K-Means dengan K=5 klaster dan reduksi dimensi PCA 3 komponen menghasilkan lima profil sosial-ekonomi mulai dari Sangat Rendah (62 siswa) hingga Tinggi (459 siswa) dengan Silhouette Score 0,8824 dan Davies-Bouldin Index 0,1866. Perpaduan hybrid dari kedua algoritma menghasilkan 15 segmen unik yang memungkinkan pemetaan kebutuhan siswa secara menyeluruh. Segmen yang paling memerlukan intervensi adalah 58 siswa di Zona-1 dengan profil Sangat Rendah. Kebaruan penelitian ini terletak pada penyatuan klasterisasi densitas spasial berbasis metrik Haversine dengan segmentasi sosial-ekonomi berbasis PCA dalam satu kerangka hybrid, sebuah pendekatan yang sebelumnya belum diterapkan di wilayah sungai dan rawa seperti Kalimantan Selatan.

References

Kementerian Pendidikan dan Kebudayaan, "Peraturan Menteri Pendidikan dan Kebudayaan Nomor 1 Tahun 2021 tentang Penerimaan Peserta Didik Baru," 2021, Kemendikbud, Jakarta.

E. N. Saputra and R. Wardoyo, "Penerapan DBSCAN dengan metrik Haversine untuk pengelompokan data spasial wilayah di Indonesia," Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 10, no. 4, pp. 823–830, 2023, doi: 10.25126/jtiik.2023104894.

S. Gust, E. A. Hanushek, and L. Woessmann, "Global universal basic skills: Current deficits and implications for world development," J. Dev. Econ., vol. 166, p. 103205, 2024, doi: 10.1016/j.jdeveco.2023.103205.

Direktorat Jenderal Pendidikan Dasar dan Menengah, "Panduan Pelaksanaan PPDB Tahun Pelajaran 2025/2026," Jakarta, 2025.

R. A. Poernomo, B. Setiyono, and H. Supriyanto, "School location analysis by integrating the accessibility, natural and biological hazards to support equal access to education," ISPRS Int. J. Geoinf., vol. 11, no. 1, p. 12, 2022, doi: 10.3390/ijgi11010012.

X. Tu, C. Fu, A. Huang, H. Chen, and X. Ding, "DBSCAN spatial clustering analysis of urban production-living-ecological space based on POI data," Int. J. Environ. Res. Public Health, vol. 19, no. 9, p. 5153, 2022, doi: 10.3390/ijerph19095153.

Badan Pusat Statistik Provinsi Kalimantan Selatan, Kalimantan Selatan Dalam Angka 2024. Banjarbaru: BPS Provinsi Kalimantan Selatan, 2024. [Online]. Available: https://kalsel.bps.go.id

A. Bushra, D. Kim, Y. Kan, and G. Yi, "AutoSCAN: Automatic detection of DBSCAN parameters and efficient clustering of data in overlapping density regions," PeerJ Comput. Sci., vol. 10, p. e1921, 2024, doi: 10.7717/peerj-cs.1921.

R. Venkatesan and B. Mappillairaju, "Detection of hotspots of school dropouts in India: A spatial clustering approach," PLoS One, vol. 18, no. 1, p. e0280034, 2023, doi: 10.1371/journal.pone.0280034.

M. A. Valles-Coral, A. L. Pisco-Sanchez, L. Y. Castro-Medina, J. Mesias-Ramirez, and J. M. Pinedo-Garcia, "Density-based unsupervised learning algorithm to categorize college students into dropout risk levels," Data (Basel)., vol. 7, no. 11, p. 165, 2022, doi: 10.3390/data7110165.

W. Lu, Y. Li, R. Zhao, B. He, and Z. Qian, "Spatial pattern and fairness measurement of educational resources in primary and middle schools," Int. J. Environ. Res. Public Health, vol. 19, no. 17, p. 10840, 2022, doi: 10.3390/ijerph191710840.

A. M. Ikotun, A. E. Ezugwu, L. Abualigah, B. Abuhaija, and J. Heming, "K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data," Inf. Sci. (N. Y)., vol. 622, pp. 178–210, 2023, doi: 10.1016/j.ins.2022.11.139.

A. A. Wani, "Comprehensive analysis of clustering algorithms: Exploring limitations and innovative solutions," PeerJ Comput. Sci., vol. 10, p. e2286, 2024, doi: 10.7717/peerj-cs.2286.

B. J. J. Kremers, A. Ho, J. Citrin, and K. L. van der Plassche, "Two step clustering for data reduction combining DBSCAN and K-means clustering," arXiv preprint arXiv:2111.12559, 2021.

I. Rosydiana, A. Hermawan, and R. Prasasti, "Application of data mining using the K-Means clustering algorithm for opening industrial classes in vocational high schools," Indonesian Journal of Artificial Intelligence and Data Mining, vol. 5, no. 2, pp. 137–146, 2022, doi: 10.24014/ijaidm.v5i2.19172.

K. P. Sinaga, I. Hussain, and M.-S. Yang, "Entropy K-means clustering with feature reduction under unknown number of clusters," IEEE Access, vol. 9, pp. 67736–67751, 2021, doi: 10.1109/ACCESS.2021.3077622.

A. E. Ezugwu and others, "A comprehensive survey of clustering algorithms," Eng. Appl. Artif. Intell., vol. 110, p. 104743, 2022, doi: 10.1016/j.engappai.2022.104743.

B. M. S. Hasan and A. M. Abdulazeez, "A review of principal component analysis algorithm for dimensionality reduction," Journal of Soft Computing and Data Mining, vol. 2, no. 1, pp. 20–30, 2021, doi: 10.30880/jscdm.2021.02.01.003.

A. Jauhari, I. O. Suzanti, D. R. Anamisa, and F. T. Admojo, "PCA-counseled K-means and K-medoids with dimension reduction for improved in determining optimal aid clustering," Jurnal Ilmiah Kursor, vol. 13, no. 1, pp. 46–55, 2025, doi: 10.21107/kursor.v13i1.460.

A. M. Bagirov, R. M. Aliguliyev, and N. Sultanova, "Finding compact and well-separated clusters: Clustering using silhouette coefficients," Pattern Recognit., vol. 135, p. 109144, 2023, doi: 10.1016/j.patcog.2022.109144.

D. Chicco and others, "The Silhouette coefficient and the Davies-Bouldin index are more informative than Dunn index, Calinski-Harabasz index, Shannon entropy, and Gap statistic," PeerJ Comput. Sci., vol. 11, p. e3309, 2025, doi: 10.7717/peerj-cs.3309.

F. Perafan-Lopez, V. L. Ferrer-Gregory, C. Nieto-Londono, and J. Sierra-Perez, "Performance analysis and architecture of a clustering hybrid algorithm called FA+GA-DBSCAN using artificial datasets," Entropy, vol. 24, no. 7, p. 875, 2022, doi: 10.3390/e24070875.

M. Gagolewski, M. Bartoszuk, and A. Cena, "Are cluster validity measures (in)valid?," Inf. Sci. (N. Y)., vol. 581, pp. 620–636, 2021, doi: 10.1016/j.ins.2021.10.004.

F. Putra, "Penerapan Teknologi Machine Learning dalam Deteksi Dini Penyakit Pada Tanaman Pangan," Jurnal Kolaborasi Sains dan Ilmu Terapan, vol. 3, no. 1, pp. 1–5, 2024, [Online]. Available: https://utilityprojectsolution.org/ejournal/index.php/JuKSIT/article/view/50

Scikit-learn Developers, "Scikit-learn documentation version 1.3," 2023. [Online]. Available: https://scikit-learn.org

W. Konyk, A. Smith, B. Wong, and A. Tollefson, "Thirty years of maintaining WGS 84 with GPS," Navigation: Journal of the Institute of Navigation, vol. 72, no. 2, p. e693, 2025, doi: 10.33012/navi.693.

World Bank, Realizing Education's Promise: A World Bank Retrospective. Washington, DC: World Bank Group, 2023.

F. D. Marleny, I. Maulida, and Mambang, "Simple Linear Iterative Clustering (SLIC) untuk segmentasi motif dasar citra kain sasirangan," Jurnal Simantec, vol. 11, no. 1, pp. 19–26, 2022, doi: 10.21107/simantec.v11i1.14274.

P. Macharia, N. Ray, C. W. Gitonga, R. W. Snow, and E. Giorgi, "Combining school-catchment area models with geostatistical models," Spat. Stat., vol. 49, p. 100679, 2022, doi: 10.1016/j.spasta.2022.100679.

M. Noval, Windarsyah, and F. D. Marleny, "Implementasi algoritma K-Means untuk analisis pola penjualan pada Toko Monisa," Jurnal Media Informatika, vol. 6, no. 3, pp. 1996–2002, 2025, doi: 10.55338/jumin.v6i3.6237.