Composition analysis of glass relics based on a clustering model
DOI:
https://doi.org/10.54097/hset.v21i.3165Keywords:
Chi-square test, cluster analysis, entropy weight prediction model, sensitivity analysis of subclass division.Abstract
The analysis and identification of the chemical composition of ancient glass are of great significance for the evolution of history through time and space. The chemical content of ancient glass will change due to weathering, so a comprehensive evaluation model for the chemical content of the ancient glass is proposed in this paper. In this paper, the chi-square test is used to analyze the four classification variables, and it is found that there are significant differences between the ornamentation and colour, and the chemical composition content before weathering is predicted. Then the system clustering is used, and a subclass division model is proposed for the clustering results. Finally, the sensitivity analysis of the classification results is carried out, and different degrees of disturbance items are added respectively to obtain different model accuracy rates. The results show that the sensitivity of the model is better. The results show that the model can be used to analyze the composition of ancient glass relics and achieve good results.
Downloads
References
Fu Weizhong, Chu Liuping. Research on the Evaluation of Manufacturing High Quality Development from the Perspective of Yangtze River Delta Integration -- TOPSIS Evaluation Model based on the improved CRITIC- entropy weight method combined weight [J]. Industrial technology and economics,2020,39(09):145-152.
L Syafaah,D Arisnanda,M Irfan,R H Hendaryati. Correlation of risk factors for coronary heart disease in type-2 diabetes mellitus using the chi-square method[J]. IOP Conference Series Materials Science and Engineering,2020,821(1).
li xingqi, gao xiaohong. Dimensionless method of effectiveness evaluation [J]. Journal of statistics and decision, 2021 ((15) : 24 to 28, DOI: 10.13546 / j.carol carroll nki tjyjc. 2021.15.005.
Shen Ying. T test and F Application of inspection in Trend Analysis of chemical test quality control data [J]. Chinese journal of inspection and quarantine,2019,29(02):105-107.
he xiuli. Multivariate Linear model and Ridge regression analysis [D]. Huazhong University of Science and Technology,2005.
Yan Chun, Li Yaqi, Sun Haitang. Research on Auto Insurance Fraud Identification based on Ant Colony Optimization Random Forest Model [J]. Insurance research, 2017 (6) : 114-127. The DOI: 10.13497 / j.carol carroll nki is. 2017.06.011.
Deng Yurui, xu-dong cheng, Tang Fang, zhou yong. Risk control of Rice mildew in storage based on multiple linear regression analysis and random forest algorithm [J]. Journal of University of Science and Technology of China,202,52(01):47-54+72+55.
Tian Bing, Huang Shan, Sun Ye, Yan Yujie, Jin Kangkang. Rockburst Prediction based on SOM neural network clustering and gray TOPSIS evaluation method [J]. China mining,2021,30(01):188-192.
guo wenjuan. K-means clustering algorithm based on Optimized initial clustering Center [J]. Wind technology, 2022 (4) : 63-65. The DOI: 10.19392 / j.carol carroll nki. 1671-7341.202204021.
Wu Huijie. Study on Application and Optimization Method of random machine forest Algorithm [D]. Jiangnan great learning, 2021. DOI: 10.27169 /, dc nki. Gwqgu. 2021.001718.
Zhang Weifeng. Statistical analysis of Spearman's simple correlation coefficient and Gini Gamma correlation coefficient [D]. wide East university of technology, 2020. DOI: 10.27029 /, dc nki. Ggdgu. 2020.001333.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
