Identification model of surface composition of glass relics based on K-means clustering and boosting learning strategy

Abstract

As one of the main commodities circulated on the Silk Road, glass is valuable material evidence of early trade, but glass is vulnerable to external factors leading to weathering, so this paper establishes a comprehensive identification model to study the chemical composition of the surface of glass cultural relics. In this paper, the Chi-square independence test and fuzzy function are used to analyze the relationship between the type of glass, weathering degree and chemical composition. Then the principal component analysis is used to extract the principal components, and the clustering and algorithm analysis is carried out to identify the unknown glass cultural relics. Finally, the variance test method was used to test the difference between the correlation coefficients of glass types and chemical elements, and the correlation and difference between the chemical components of different types of glass cultural relics were analyzed.