Component Analysis and Identification of Ancient Glass Products Based on Statistical Methods
Kerui Wu *
School of Mathematics, Liaoning Normal University, Dalian-116029, China.
Minghan Li
School of Mathematics, Liaoning Normal University, Dalian-116029, China.
Hongyi Ren
School of Mathematics, Liaoning Normal University, Dalian-116029, China.
*Author to whom correspondence should be addressed.
Abstract
This paper analyzes its role in the composition analysis and identification of ancient glass products by flexible use of statistical methods, and emphasizes four statistical methods: systematic clustering algorithm, K-means algorithm, logistic regression model and grey correlation analysis. Taking the C project of CUMCM in 2022 as an example, this paper systematically introduces these four common data classification and statistical methods to classify and analyze the given data. In this paper, suitable chemical components of high potassium and lead barium glass were selected for subdivision, and the specific division methods and results w ere given. The chemical composition of glass relics of unknown category was analyzed to identify their type. The grey correlation matrix of surface weathering of high-potassium cultural relics was obtained, and the correlation degree of chemical components was analyzed. This greatly promotes the composition analysis and identification of chemical components in ancient relics.
Keywords: System cluster analysis algorithm, K-means clustering analysis, Logistic regression model, Grey correlation method