Klasifikasi jenis kaca menggunakan algoritma neural network pada dataset glass identification
Article Sidebar
Main Article Content
Abstract
Penelitian ini menerapkan teknik data mining untuk mengklasifikasikan jenis kaca pada Glass Identification Dataset menggunakan algoritma Neural Network berbasis Backpropagation. Dataset mencakup sembilan atribut komposisi kimia dan fisik, serta satu atribut target berupa tipe kaca. Proses penelitian meliputi data understanding, preprocessing, pembangunan model jaringan syaraf tiruan, dan evaluasi performa. Model dilatih menggunakan pembagian data training dan testing, dengan optimasi bobot secara iteratif melalui mekanisme error backpropagation. Hasil pengujian menunjukkan akurasi 72%, dengan performa yang lebih baik pada kelas data yang memiliki distribusi seimbang. Temuan ini menunjukkan bahwa Neural Network mampu mempelajari pola komposisi kimia kaca secara efektif dan relevan digunakan dalam analisis forensik berbasis data mining.
Article Details
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
References
G. Cai, H. Li, and J. Huang, “Glass Classification and Identification based on K-means++ Clustering Analysis and BP Neural Network Method,” Highlights Sci. Eng. Technol., vol. 39, pp. 482–489, 2023, doi: 10.54097/hset.v39i.6573.
Z. Chen, Y. Xu, C. Zhang, and M. Tang, “Prediction of Glass Chemical Composition and Type Identification Based on Machine Learning Algorithms,” Appl. Sci., vol. 14, no. 10, May 2024, doi: 10.3390/app14104017.
Nanwin and W. D. Ofor, “Glass recognition as a cutting-edge machine learning approach for identification and classification,” FNAS J. Sci. Innov., vol. 5, no. 2, pp. 1–16, 2023, [Online]. Available: www.fnasjournals.com
S. Hu and Y. Xiong, “Composition Analysis and Identification of Ancient Glass Products Based on OLS,” Highlights Sci. Eng. Technol., vol. 22, pp. 356–360, 2022, doi: 10.54097/hset.v22i.3403.
C. Zheng et al., “GlassNet: Label Decoupling-based Three-stream Neural Network for Robust Image Glass Detection,” Comput. Graph. Forum, vol. 41, no. 1, pp. 377–388, 2022, doi: 10.1111/cgf.14441.
K. Yoshikawa, K. Yano, S. Goto, K. Kim, and N. Matubayasi, “Graph neural network-based structural classification of glass-forming liquids and its interpretation via self-attention mechanism,” J. Chem. Phys., vol. 163, no. 2, 2025, doi: 10.1063/5.0277279.
G. Jung et al., “Roadmap on machine learning glassy dynamics,” Nat. Rev. Phys., vol. 7, no. 2, pp. 91–104, 2025, doi: 10.1038/s42254-024-00791-4.
D. R. Cassar, “GlassNet: A multitask deep neural network for predicting many glass properties,” Ceram. Int., vol. 49, no. 22, pp. 36013–36024, 2023, doi: 10.1016/j.ceramint.2023.08.281.
R. Suppa, “Comparative Performance Evaluation Results of Classification Algorithm in Data Mining to Identify Types of Glass Based on Refractive Index and Itâ€TMs Elements,” PENA Tek. J. Ilm. Ilmu-Ilmu Tek., vol. 8, no. 1, pp. 20–31, 2023, doi: 10.51557/pt_jiit.v8i1.1705.
Z. Hajiakhondi-Meybodi, A. Mohammadi, J. Abouei, and K. N. Plataniotis, “CLSA: Contrastive-Learning-Based Survival Analysis for Popularity Prediction in MEC Networks,” IEEE Internet Things J., vol. 11, no. 4, pp. 6352–6367, 2024, doi: 10.1109/JIOT.2023.3314667.
S. Bishnoi, S. Badge, Jayadeva, and N. M. A. Krishnan, “Predicting oxide glass properties with low complexity neural network and physical and chemical descriptors,” J. Non. Cryst. Solids, vol. 616, pp. 1–15, 2023, doi: 10.1016/j.jnoncrysol.2023.122488.
C. B. D. Schulz, Informed Machine Learning. 2025. [Online]. Available: https://link.springer.com/10.1007/978-3-031-83097-6
R. M. Forrest and A. L. Greer, “Machine-learning improves understanding of glass formation in metallic systems,” Digit. Discov., vol. 1, no. 4, pp. 476–489, 2022, doi: 10.1039/d2dd00026a.
X. Peng, X. Tong, and X. Hu, “Research on glass classification prediction model based on machine learning,” Highlights Sci. Eng. Technol., vol. 22, pp. 246–253, 2022, doi: 10.54097/hset.v22i.3369.
G. Maier, J. Hamaekers, D. S. Martilotti, and B. Ziebarth, “Predicting Properties of Oxide Glasses Using Informed Neural Networks,” Cogn. Technol., vol. Part F287, pp. 161–185, 2025, doi: 10.1007/978-3-031-83097-6_8.