Academic Journal of Computing & Information Science, 2022, 5(13); doi: 10.25236/AJCIS.2022.051305.
School of Electronic and Information Engineering, Guangdong Ocean University, Zhanjiang, Guangdong, China, 524088
The craft production of glass has a long history, and glass has been a valuable physical evidence of trade exchanges during the Silk Road. As traditional value crafts, the study and identification of the chemical composition of glass is of great significance. This paper mainly completes the classification problem by K-means clustering analysis and clustering tree, etc.; the statistical law study and prediction analysis of data are completed by integrating radial basis ridge regression and ARIMA differential autoregression, etc., which solves the problem of identification, classification and prediction of glass components. Firstly, the correlation analysis of the given data is carried out, and the Pearson correlation coefficient is calculated and visualized as the heat map representation, and performed statistical law fitting analysis of the data by ridge regression with fused radial bases, and finally predicted the chemical composition content before and after weathering by Autoregressive Integrated Moving Average (ARIMA) differential autoregression.
Glass chemical composition; Ridge regression; Pearson correlation coefficient; K-means cluster analysis; ARIMA differential autoregression; regression prediction
Jingyu Zhang. Identification and Analysis of Glass Components by Fusing K-Means Clustering and Ridge Regression. Academic Journal of Computing & Information Science (2022), Vol. 5, Issue 13: 30-37. https://doi.org/10.25236/AJCIS.2022.051305.
 Prabhu Nimitha S, Sharmila K, Karunakara N, Almousa Nouf, Sayyed M I, Kamath Sudha D. Thermoluminescence Dosimetric Attributes of Yb3+ Doped BaO-ZnO-LiF-B2 O3 Glass Material After Er3+ Co-doping.[J]. Luminescence: the journal of biological and chemical luminescence, 2022, 37 (5).
 Ma Han, Liang Shunlin. Development of the GLASS 250-m leaf area index product (version 6) from MODIS data using the bidirectional LSTM deep learning model [J]. Remote Sensing of Environment, 2022, 273.
 Gilmar Veriato Fluzer Santos, Lucas Gamalel Cordeiro, Claudio Antonio Rojo, Edison Luiz Leismann. A Review of the Anthropogenic Global Warming Consensus: An Econometric Forecast Based on the ARIMA Model of Paleoclimate Series [J]. Applied Economics and Finance, 2022, 9(3).
 Wenbo Zhang, Zhenyang Li. Research on Prediction Method of Photovoltaic Building Integration Plate Index Based on ARIMA Model [J]. Environment, Resource and Ecology Journal, 2022, 6(3).
 Spyrou Evangelos D., Tsoulos Ioannis, Stylios Chrysostomos. Applying and Comparing LSTM and ARIMA to Predict CO Levels for a Time-Series Measurements in a Port Area [J]. Signals, 2022, 3(2).