Research on glass relics based on neural network and K-means clustering algorithm

Dechen Xing; Tingting Yan; Zhuoling Han; Jiawei Liu; Long Ma

doi:10.1117/12.2678966

14 June 2023 Research on glass relics based on neural network and K-means clustering algorithm

Dechen Xing, Tingting Yan, Zhuoling Han, Jiawei Liu, Long Ma

Proceedings Volume 12725, International Conference on Pure, Applied, and Computational Mathematics (PACM 2023); 1272514 (2023) https://doi.org/10.1117/12.2678966
Event: International Conference on Pure, Applied, and Computational Mathematics (PACM 2023), 2023, Suzhou, China

Abstract

In this paper, we construct a prediction and classification model based on neural network and K-means clustering algorithm to complete the prediction of glass composition before weathering and the classification of unknown glass. In the process of studying glass relics, we discussed the important chemical components and analyzed their influence on the properties of glass. At the same time, through the collected data, the neural network algorithm is used to train and test the data to analyze the composition content of glass before and after weathering. Then, the classification simulation of the data is carried out according to the K-means clustering algorithm. Finally, the classification results of glass relics with different chemical composition in the classification model are analyzed. We conclude that there are six classification systems for high-potassium glass and lead-barium glass. Effective classification can not only reduce the difficulty of scholars' archaeological classification, but also effectively improve the research value of glass relics.

Citation Download Citation

Dechen Xing, Tingting Yan, Zhuoling Han, Jiawei Liu, and Long Ma "Research on glass relics based on neural network and K-means clustering algorithm", Proc. SPIE 12725, International Conference on Pure, Applied, and Computational Mathematics (PACM 2023), 1272514 (14 June 2023); https://doi.org/10.1117/12.2678966

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