Chemical composition classification of glass relics study based on statistical testing and clustering algorithms

Haoyang Chen; Xuan He; Nanyang Huang

doi:10.1117/12.3000039

23 August 2023 Chemical composition classification of glass relics study based on statistical testing and clustering algorithms

Haoyang Chen, Xuan He, Nanyang Huang

Author Affiliations +

Proceedings Volume 12784, Second International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2023); 127841S (2023) https://doi.org/10.1117/12.3000039
Event: 2023 2nd International Conference on Applied Statistics, Computational Mathematics and Software Engineering (ASCMSE 2023), 2023, Kaifeng, China

Abstract

Glass cultural relics are susceptible to weathering due to the burial environment, resulting in changes in their chemical composition. This paper uses the chemical composition content data of glass relics, through the construction of statistical test, feature engineering and clustering algorithms, to analyze the statistical laws of these cultural relics and to divide reasonable subclasses of glass cultural relics. The results show that: (1) The SiO₂ content of the high-potassium glass is significantly improved after weathering, and the content of SrO, P₂O₅, etc. is reduced; the SrO and P₂O₅ content of the ead-barium silicate glass is improved after weathering, and the content of Al₂O₃, K₂O, etc. is reduced. (2) The decision tree algorithm uses the lead oxide content of 9.3% as the threshold to divide relics into two major categories, and the hierarchical clustering method divides the cultural relics into several sub-categories, including K₂O-PbO-SiO₂ glass system, Al₂O₃-MgO-SiO₂ glass system, etc.

Citation Download Citation

Haoyang Chen, Xuan He, and Nanyang Huang "Chemical composition classification of glass relics study based on statistical testing and clustering algorithms", Proc. SPIE 12784, Second International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2023), 127841S (23 August 2023); https://doi.org/10.1117/12.3000039

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available