Ancient glass is extremely susceptible to weathering due to the environment in which it was buried. In the process of weathering, there is a massive exchange of interior elements with those of the environment, resulting in the compositional proportions of the glass being affected, thereby interfering with the accurate judgment of its category. In this paper, aiming at the problem of ancient glass products, using contingency table chi-square test, linear binary classification support vector machine, K-means++ clustering algorithm and other methods, the composition analysis and identification model of glass is established, and the problem of classifying unknown samples is solved, and did a model test and sensitivity analysis.

Xinyao Zhang, Weijun He. Compositional analysis and identification of ancient glass products using clustering algorithm. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 3: 69-74. https://doi.org/10.25236/AJCIS.2023.060309.

[1] Lu Qingyun, Liu Hongxia. Analysis on the use of chi square test of contingency table in mathematical education research [J]. Statistics and Decision Making, 2008 (02): 156-158

[2] Sheng Sud, Xie Shiqian, Pan Chengyi. Probability Theory and Mathematical Statistics Beijing Higher Education Press 2019.12.

[3] Siqin Biliger, Li Qinghui, Gan Fuxi. Analysis of components of ancient Chinese potassium glasses by laser ablation inductively coupled plasma atomic emission spectrometry/mass spectrometry. Shanghai Institute of Optics and Precision Machinery, Chinese Academy of Sciences, Fudan University. Analytical Chemistry. 2013, 41 (09), 1328-1333

[4] Wang Jie, Li Mo, Ma Qinglin, Zhang Zhiguo, Zhang Meifang, Wang Julin. Study on the weathering of an octagonal lead barium glassware in the Warring States Period [J]. Glass and Enamel, 2014,42 (02): 6-13. DOI: 10.13588/j.cnki.g.e.1000-2871.2014.02.002

[5] Mathematical Cihai Committee. Mathematical Cihai (1-6). Volume 3 [M] Nanjing, 2002