In the paper, the chemical ingredient of potash glasswork and baryta glasswork is known from the archaic Chinese glassworks. The class, ornamentation and pigment of glasswork are known both without and with rotting. The chemical ingredient percentage before rotting is predicted. Thus, the chemical ingredient is subclassified. The relativity of the chemical ingredient between the different classes of glasswork is found.
HanLWangY. Component analysis and type identification of ancient glass cultural relics. J Yuxi Norm Uni2024; 40(03): 78–86.
2.
FuZ. Research on the composition of the ancient glass products based on the statistical analysis method. J Shandong Commer Voca Tech Coll2024; 24(02): 110–114.
3.
ShaoGXiaXYinH. Prediction model study of ancient glass classification based on CART and cluster analysis. J Tonghua Norm Uni2024; 45(02): 31–35.
4.
WuHXiaoZWangL. Component analysis and identification of glass products based on machine learning and regression algorithms. Shandong Chem Indus2024; 53(02): 150–153.
5.
XieHZhangJGuoL. Research on the mathematical modeling of the attributes and chemical composition of ancient glass products. J Texas Coll2023; 39(06): 6–14.
6.
LiGLinXPengM. Component analysis and identification of ancient glass products based on random forest and support vector machine. Scientific and technological innovation and application.
7.
LiuNCuiJJiangX. Discovery and scientific and technological research of ancient glass in Xinjiang. Stud Western Reg2023; 04: 113–121+169.
8.
YangLTongWZongY. Mathematical model of composition analysis and identification problems of ancient glass products. J Beijing Ins Print Tech2023; 31(09): 61–66.
9.
XuSXieJLinH. Component analysis and identification of weathered glass products based on the decision tree model. Comp Know Tech2023; 19(25): 125–129.
10.
WangZ. Mathematical model used for the composition analysis and identification of ancient glass products. Mod Inform Tech2023; 7(14): 88–93+98.
11.
QiY. Component analysis and identification of ancient glass products based on machine learning. Dig Tech App2023; 41(07): 111–114.
12.
DuSLeJZhouH. Study on the composition analysis and identification of unearthed glass products. J Northwest Univ Nation2023; 44(02): 8–16.
13.
HuangHLiCLiuS. Component analysis and identification of ancient glass products based on compositional data. Math Mod App2023; 12(02): 52–62+124.
14.
WanHDengW. Statistical modeling of the composition analysis and identification of ancient glass products. Math Mod App2023; 12(02): 27–40.
15.
MaPHanYLiD. Analysis and classification of ancient glass products based on compositional data. Math Mod App2023; 12(02): 63–73.
16.
ZhangQLuKZhaoX. Component analysis of ancient glass products based on a random forest classification model. Henan Sci Tech2023; 42(09): 19–22.
17.
ZhaiS. Component analysis and identification of glass products based on the decision tree. Heilongjiang Sci2023; 14(08): 47–49.
18.
ChenZJiJ. Component analysis and identification of ancient glass products based on the hierarchical clustering model. Mod Inform Tech2023; 7(08): 122–125.
19.
ZhangSSunRRenH. Chemical composition analysis and correlation study of ancient glass products. Chem Ind Manage2023; 08: 138–141+164.
20.
LuJ. An ancient glass classification model based on ensemble feature selection and random forest. J Silic2023; 51(04): 1060–1065.
21.
LuFFuHLiuC. Component analysis and identification of ancient glass products based on machine learning. Inform Comp2023; 35(04): 98–102.
22.
liL. Analysis and identification of the components of ancient glass products based on the statistical analysis method. Chinese New Tech New Pro2023; 02: 99–101.
23.
YinY. Analysis of the composition of ancient glass products through association prediction. Contem Chem Ind Res2023; 01: 122–126.
