Author:
Ma Ji,Chen Qian,Li Haoxuan,Chen Yongqi,Lu Yuteng,Yang Hong
Abstract
With the deepening of human awareness of heritage conservation today, the category identification of excavated glass artifacts is particularly important. This paper draws on data related to the chemical composition of some glass artifacts. The data were analyzed by Mann-Whitney U analysis, SOM cluster analysis, and random forest algorithm, and a model was developed to accurately identify the categories of glass artifacts based on their chemical composition. The results show that the three chemical components of potassium oxide, barium oxide, and lead oxide have the greatest influence on the weathering and corrosion of glass artifacts through Mann-Whitney U analysis; the SOM cluster analysis model shows that the glass artifacts with high potassium can be divided into two subclasses, and the glass artifacts with lead and barium can be divided into three subclasses. Finally, we combined the results of the existing analysis and used the random forest algorithm to establish a model for accurate identification of glass artifacts based on their chemical composition. The sensitivity test shows that the model has high robustness and accuracy. This method will play an important role in the accurate identification of glass artifacts of unknown categories in the future.
Publisher
Darcy & Roy Press Co. Ltd.
Reference15 articles.
1. Cheng Qian, Zhang Jianlin. Scientific analysis and research on glass beads excavated from the Xiaoling Tomb of Emperor Wu of the Northern Zhou Dynasty[J]. Archaeology and Cultural Properties, 2011(1):107-112
2. Conradt, Reinhard (2019). Prospects and physical limits of processes and technologies in glass melting. Journal of Asian Ceramic Societies, (), 1–20.
3. Liu, S., & Zhang, Y. (2022). Based on the analysis and identification of ancient glass products. Highlights in Science, Engineering and Technology, 21, 212–221.
4. Ishii, Keizo (2019). PIXE and Its Applications to Elemental Analysis. Quantum Beam Science, 3(2), 12–.
5. Sharma, V., Acharya, R., Bagla, H. K., & Pujari, P. K. (2021). Standardization of an external (in air) PIGE methodology using tantalum as a current normalizer in conjunction with INAA for rapid and non-destructive chemical characterization of “as-received” glass fragments towards forensic applications. Journal of Analytical Atomic Spectrometry, 36(3), 630–643.