The Classification and Identification of Ancient Glass Artifacts Based on Decision Tree and Cluster Analysis

Jia Wang; Yiwei Wei; Yuqian Liu

doi:10.54097/vvtkty73

Authors

Jia Wang
Yiwei Wei
Yuqian Liu

DOI:

https://doi.org/10.54097/vvtkty73

Keywords:

Decision Tree, K-means++ Cluster Analysis, Ancient Glass, Archaeological Artifact Identification.

Abstract

The analysis of ancient glass compositions is crucial for accurately identifying artifact categories. This study establishes a classification standard for high-potassium glass and lead-barium glass by constructing a decision tree model, with PbO content less than 5.46% being classified as high-potassium glass, and the opposite as lead-barium glass. Furthermore, cluster analysis is used to further subdivide high-potassium glass into high-silicon and low-silicon categories, and lead-barium glass into high-copper and low-copper categories. This method not only helps to accurately identify unknown types of glass, improving the precision of manual classification, but also provides a reliable scientific basis for historical research.

Downloads

Download data is not yet available.

References

[1] Wang Z, Zhang Z, Wang F, et al. A pXRF-based approach to identifying the material source of stone cultural relics: a case study [J]. Minerals, 2022, 12 (2): 199.

[2] Wu Q, Zhang B, Hu Y. Comparison and Research Progress of Protein Detection Technology for Cultural Relic Materials [J]. Coatings, 2023, 13 (8): 1319.

[3] Mastelaro V R, Zanotto E D. X-ray absorption fine structure (XAFS) studies of oxide glasses—a 45-year overview [J]. Materials, 2018, 11 (2): 204.

[4] Guo K, Qiao Y, Gao Z. Based on BP neural network glass cultural relics chemical category and composition prediction model construction [J]. Highlights in Science, Engineering and Technology, 2023, 42: 111 - 117.

[5] Zou Y. Molecular-composition analysis of glass chemical composition based on time-series and clustering methods [J]. Molecules, 2023, 28 (2): 853.

[6] Wen Y. Prediction of chemical composition of cultural relics glass based on moving average algorithm of least square method [J]. Highlights in Science, Engineering and Technology, 2023, 58: 179 - 187.

[7] Ai X. Study on Composition Analysis and Species Identification of Glass Relics Based on the Multiple Linear Regression Model [J]. Advances in Computer, Signals and Systems, 2023, 7 (4): 55 - 63.

[8] Chang S, Yang Y, Xu Y H, et al. Composition analysis and identification of ancient glass products based on gray correlation [J]. Highlights in Science, Engineering and Technology, 2023, 42: 188 - 196.

[9] Shao K, Du R, Xiong H. Composition Analysis of Glass Based on Weighted Mean and Correlation Analysis [J]. Highlights in Science, Engineering and Technology, 2023, 42: 55 - 62.

[10] Li X, Yi S, Cundy A B, et al. Sustainable decision-making for contaminated site risk management: A decision tree model using machine learning algorithms [J]. Journal of Cleaner Production, 2022, 371: 133612.