Research Article
Analysis and identification of the composition of ancient glass objects based on an improved DBSCAN model
@INPROCEEDINGS{10.4108/eai.24-2-2023.2330619, author={Ruijin Li and Kaihao Zhang and Baoyi An}, title={Analysis and identification of the composition of ancient glass objects based on an improved DBSCAN model}, proceedings={Proceedings of the 2nd International Conference on Engineering Management and Information Science, EMIS 2023, February 24-26, 2023, Chengdu, China}, publisher={EAI}, proceedings_a={EMIS}, year={2023}, month={6}, keywords={heritage identification; support vector machine; dbscan model; binary logistic regression model}, doi={10.4108/eai.24-2-2023.2330619} }- Ruijin Li
Kaihao Zhang
Baoyi An
Year: 2023
Analysis and identification of the composition of ancient glass objects based on an improved DBSCAN model
EMIS
EAI
DOI: 10.4108/eai.24-2-2023.2330619
Abstract
A scientific approach to classifying cultural objects is conducive to more efficient management of historical artefacts. According to existing research, the chemical composition content of artefacts can determine the type of composition, degree of weathering, and production age. This paper provides a method for classifying and identifying ancient glass artefacts based on their chemical composition content, which has not yet been investigated. An improved DBSCAN model is used to classify marked glass artefact samples. A support vector machine and a combined binary logistic regression model are used to classify and identify unknown glass artefact samples, achieving an accuracy of 90%. The method is used to classify two common types of ancient glass artefacts and their degree of weathering in China, thus providing a new approach to dating artefact production.
