K-Means++ Clustering Algorithm in Categorization of Glass Cultural Relics
Source abstract
Abstract
We used statistical methods to study the classification of high-potassium glass and lead–barium glass and analyzed the correlation between the chemical composition of different types of glass samples. We investigated the categorization methodology of glass cultural relics, conducted a principal component analysis on the chemical composition data of the glass, and developed a case-specific clustering algorithm (K-Means++) to further categorize the glass cultural relics. K-Means++ was developed to reduce the sensitivity of a traditional K-Means clustering algorithm, by choosing the next clustering center with probability inversely proportional to the distance from the current clustering center. Then we verified the validity of the six subcategories we defined by inertia and silhouette score and evaluated the sensitivity of the clustering algorithm. We obtained a robustness ratio that maintained over 0.9 in the random noise test and a silhouette score of 0.525 in the clustering, which illustrated significant divergence among different clusters and showed the result is reasonable. With our proposed algorithm and classification result, a more comprehensive understanding of glass relics can be gained.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Clustering Algorithms Research · Sensory Analysis and Statistical Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Science and Technology, Tsinghua University, Beijing 100083, China
Weiyang College, Tsinghua University, Beijing 100083, China
College of Information Engineering, Inner Mongolia University of Technology, Hohhot 010080, China
Funding
central government guides’ local science and technology development fund projects
References (25)
Show source-provided references
1. Component analysis of ancient glass products by association prediction
2. Using fuzzy mathematics knowledge to classify the disease types of stone, ceramic and glass relics in the collection
3. Weathering of sodium-calcium-aluminum-magnesium silicate glass and alkali-lead silicate glass
4. The PXRF analysis and related issues of some glassware unearthed in Xi′an
5. Feng, B. (2021). Construction and application of ancient glass beads database unearthed in China. [Master’s Thesis, Northwest University].
6. Simulation method of glass composition and properties
7. Li, J. (2021). Glass defect detection based on deep learning. [Master’s Thesis, Fujian University of Engineering].
8. Original composition prediction and sub-classification method of weathered silicate glass based on machine learning
9. Yigit, H. (2013, January 7–9). A weighting approach for KNN classifier. Proceedings of the 2013 International Conference on Electronics, Computer and Computation (ICECCO), Ankara, Turkey.10.1109/ICECCO.2013.6718270 ↗
10. Taneja, S., Gupta, C., Aggarwal, S., and Jindal, V. (2015, January 3–4). MFZ-KNN—A modified fuzzy based K nearest neighbor algorithm. Proceedings of the 2015 International Conference on Cognitive Computing and Information Processing(CCIP), Noida, India.10.1109/CCIP.2015.7100689 ↗
11. Kuang, Z. (2019). Optimization of KNN classification algorithm in high-dimensional data. [Master’s Thesis, Guangdong University of Technology].
12. Angün, E., and Altınoy, A. (2019, January 23–26). A New Mixed-Integer Linear Programming Formulation for Multiple Responses Regression Clustering. Proceedings of the 2019 6th International Conference on Control, Decision and Information Technologies (CoDIT), Paris, France.10.1109/CoDIT.2019.8820674 ↗
13. Rani, A.J.M., and Parthipan, L. (2012, January 27–29). Clustering analysis by Improved Particle Swarm Optimization and K-means algorithm. Proceedings of the IET Chennai 3rd International on Sustainable Energy and Intelligent Systems (SEISCON 2012), Tiruchengode, India.10.1049/cp.2012.2195 ↗
14. Dehariya, V.K., Shrivastava, S.K., and Jain, R.C. (2010, January 26–28). Clustering of Image Data Set Using K-Means and Fuzzy K-Means Algorithms. Proceedings of the 2010 International Conference on Computational Intelligence and Communication Networks, Bhopal, India.10.1109/CICN.2010.80 ↗
15. Density-based K-means initial clustering center selection algorithm
16. Dimensionality reduction of principal component analysis data based on mutual information credibility
17. Discussion on the application of machine learning classification based on data dimensionality reduction
18. Comparative study of principal component analysis and linear discriminant analysis
19. K-means algorithm combining Pearson similarity and minimum spanning tree
20. Fast sorting method for retired power batteries using improved K-means algorithm
21. Algorithms for hierarchical clustering: An overview
22. Silhouettes: A graphical aid to the interpretation and validation of cluster analysis10.1016/0377-0427(87)90125-7 ↗
23. Evaluation method of clustering results based on mutual information and contour coefficient
24. Improved KNN data classification model based on linear regression method
25. K-means clustering algorithm based on optimizing initial clustering center and contour coefficient