Composition Analysis and Identification of Ancient Glass Products

Weisen Cheng; Shuyu Wei; Genrui Zhang

doi:10.54691/sjt.v4i11.2943

Authors

Weisen Cheng
Shuyu Wei
Genrui Zhang

DOI:

https://doi.org/10.54691/sjt.v4i11.2943

Keywords:

Principal Component Analysis; Random Forest Classification; Chi-Square; Cluster Analysis.

Abstract

This paper mainly studies the statistical analysis of chemical composition of ancient glass products, classification and prediction of types, and other issues. It is necessary to complete the analysis of the surface weathering of glass relics, the physical characteristics and chemical composition of glass, as well as the analysis of the classification rules of high-potassium glass and lead-barium glass. Through the analysis of chemical composition, the types of cultural relics are predicted and the correlation between different types of glass chemical composition is analyzed, which is decomposed into seven small problems to be solved. In order to solve these problems, this paper adopts several models such as stochastic decision forest and principal component analysis.

Downloads

Download data is not yet available.

References

The SPSSAU project (2022). SPSSAU. (Version22.0) [Online Application Software]. Retrieved from https://www.spssau.com.

Hosmane B S. Improved likelihood ratio tests and pearson chi-square tests for independence in two dimensional contingency tables[J]. Communications in Statistics, 1986, 15(6):1875-1888.

MatthewGoldstein, EdwardWolf, WilliamDillon. On a test of independence for contingency tables[J]. Communications in Statistics, 1976, 5(2):159-169.

Saroj, Kavita. Review: study on simple K means and modified K means clustering technique[J]. International Journal of Computer Science Engineering and Technology,2016,6(7): 279-281.

Zhihua Zhou. Machine learning[M]. Tsinghua University Press, 2016.

Xu Weichao. Review of correlation coefficient research[J]. Journal of Guangdong University of Technology, 2012,29(3):12-17.