Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 8, Issue 2, 2024

A study of ancient glass subclassification based on K-means algorithm

Download as PDF

DOI: 10.23977/acss.2024.080214 | Downloads: 11 | Views: 95

Author(s)

Xuan Yang 1, Pengao Tian 2, Jiahe Weng 1

Affiliation(s)

1 School of Surveying, Mapping and Urban Spatial Information, Beijing University of Civil Engineering and Architecture, Beijing, China
2 School of Science, Beijing University of Civil Engineering and Architecture, Beijing, China

Corresponding Author

Xuan Yang

ABSTRACT

The chemical composition of glass artifacts has an important impact on ancient glass artifacts, this paper explores the various chemical compositions of the artifacts' surfaces by studying the changing law of the chemical composition ratio of the two glass artifacts' surfaces after being affected by weathering and classifying the ancient glass into subclasses. This paper firstly adopts the random forest classification method to explore how to distinguish the chemical composition of high-potassium glass and lead-barium glass to a greater extent under different weathering situations, and finds that SrO2 is the largest determinant for distinguishing the two kinds of glass after weathering, and BaO is the main indicator for determining the category before weathering. In addition, box plots were drawn in the overall dimension to preliminarily screen out reasonable chemical compositions for subclassification. Finally, the k-means clustering method was applied to establish the subclass division model, in which the k values of the model were all taken as 2. BaO was taken for subclass division in lead-barium glass, and Al2O3 was taken for subclass division in high-potassium glass, respectively.

KEYWORDS

K-means, high-potassium glass, lead-barium glass, random forests

CITE THIS PAPER

Xuan Yang, Pengao Tian, Jiahe Weng, A study of ancient glass subclassification based on K-means algorithm. Advances in Computer, Signals and Systems (2024) Vol. 8: 88-95. DOI: http://dx.doi.org/10.23977/acss.2024.080214.

REFERENCES

[1] Jinyun Cao, Tianyu Xu, Yong Liu, et al. Composition prediction and classification of ancient glassware based on RBF and SVM [J]. Science and Technology Innovation and Application, 2023, 13(18):41-43, 48.
[2] Wang Jie, Li Mo, Ma Qinglin, et al. Weathering study of an octagonal columnar lead-barium glass vessel from the Warring States period [J]. Glass and Enamel, 2014, 42(2):6-13.
[3] Xiao Jinjuan, Pang Jinxiang, Chen Wenzhuo. Principal component identification and classification of ancient glass based on random forest model [J]. Science and Technology Innovation, 2023(14):37-40.
[4] Lin Xiaoqing. K-means clustering algorithm applied to online learning behavior research in big data era[J]. Electronic Design Engineering, 2021, 29(18):181-184, 193.
[5] T.J. Xu, P.S. Wang, X. B. Yang. Three-branch k-means clustering algorithm based on artificial bee colony[J]. Computer Science, 2023, 50(6):116-121.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 13647
Visits: 260304

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.