Pemanfaatan Algoritma K-Means dalam Menentukan Cluster pada Glass Dataset Secara Efektif
Article Sidebar
Main Article Content
Abstract
Kaca merupakan material dengan komposisi kimia yang kompleks sehingga pengelompokan jenis kaca memerlukan pendekatan komputasional untuk mengekstraksi pola laten dari data berdimensi tinggi. Penelitian ini bertujuan memanfaatkan algoritma K-Means untuk menentukan cluster pada Glass Dataset berdasarkan atribut kimia seperti refractive index, Na, Mg, Al, Si, K, Ca, Ba, dan Fe. Metode penelitian meliputi pengumpulan dataset, preprocessing melalui normalisasi, pengolahan data menggunakan RapidMiner, penentuan jumlah cluster optimal, pembentukan model K-Means, serta evaluasi dan interpretasi hasil. Kualitas clustering dievaluasi menggunakan Davies–Bouldin Index dan performance vector. Hasil penelitian menunjukkan bahwa K-Means membentuk tiga cluster utama dengan karakteristik kimia berbeda, ditunjukkan oleh nilai Davies–Bouldin Index sebesar 0,530 yang menandakan pemisahan dan kekompakan cluster yang baik. Cluster yang terbentuk merepresentasikan kaca dengan komposisi umum, variasi tertentu, serta karakteristik ekstrem yang berpotensi sebagai outlier. Dengan demikian, algoritma K-Means efektif digunakan untuk analisis pengelompokan Glass Dataset dan mendukung identifikasi material serta analisis berbasis komposisi kimia.
Article Details
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
References
Chen, Y., & Ji, K. (2023). Glass Classification Method Based on K-Means ++ Algorithm. 41, 331–339.
Dong, K. (2023). Composition analysis and identification of ancient glass based on K-Means clustering. 42, 346–355. https://doi.org/10.54097/hset.v42i.7114
Gao, M., Tang, Y., Liu, H., & Ma, R. (2023). Statistics of fingerprint minutiae frequency and distribution based on automatic minutiae detection method. Forensic Science International, 344, 111572. https://doi.org/https://doi.org/10.1016/j.forsciint.2023.111572
Ji, Z. (2023). regression model and K-means clustering analysis. 40. https://doi.org/10.54097/hset.v40i.6526
Kong, Y., Liu, Z., Tan, W., & Wu, W. (2023). A study of glass classification and identification based on K- means clustering and Euclidean distance. 58. https://doi.org/10.54097/hset.v58i.10031
Loh, C., Chen, Y., Su, C., & Lin, S. (2024). applied sciences Multi-Objective Decision Support for Irrigation Systems Based on Skyline Query.
Lv, Y., Tan, H., Meng, F., Shao, G., & Yang, S. (2023). Glass Classification and Identification Based on K-Means Clustering Model. 42, 28–37. https://doi.org/10.54097/hset.v42i.7057
Meng, J., Yu, Z., & Cai, Y. (2023). applied sciences K-Means ++ Clustering Algorithm in Categorization of Glass Cultural Relics. https://doi.org/10.3390/app13084736
The many faces of ceramics: New developments in the study of archaeological ceramics from the 15th European meeting on ancient ceramics (Barcelona, 16th–18th september 2019). (2022). Journal of Archaeological Science: Reports, 44, 103550. https://doi.org/https://doi.org/10.1016/j.jasrep.2022.103550
Wang, Z., & Shen, W. (2023). Analysis and identification of the compositional correlations of glasses and the variability of different classes of compositions. 4(5), 25–30. https://doi.org/10.25236/AJMC.2023.040504
Yan, S., Zhang, K., & Sun, J. (2023). Classification of Glass Products Based on Clustering Algorithm. 43. https://doi.org/10.54097/hset.v43i.7445
Yang, J., Wang, Y., Yao, X., & Lin, C. (2021). Adaptive Initialization Method for K-Means Algorithm. 4(November), 1–13. https://doi.org/10.3389/frai.2021.740817
Yin, H. (2022). Identification model of surface composition of glass relics based on K-means clustering and boosting learning strategy. 22, 340–346. https://doi.org/10.54097/hset.v22i.3401
Zhang, J. (2022). Identification and Analysis of Glass Components by Fusing K-Means Clustering and Ridge Regression. 5(13), 30–37. https://doi.org/10.25236/AJCIS.2022.051305
Zhang, Y., Guo, J., & Deng, Q. (2023). Identification of ancient glass products based on K- means composition analysis. 4(3), 39–46. https://doi.org/10.25236/AJMC.2023.040306