Identification of ancient glass categories based on distance discriminant analysis
Abstract It is crucial for archaeological investigations to identify the category of cultural relics by analyzing their chemical composition. This study analyzed the chemical composition distribution of glass cultural relics and applied distance discriminant analysis methods to classify them into tw...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-08-01
|
| Series: | Heritage Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40494-023-00999-0 |
| _version_ | 1797752633737347072 |
|---|---|
| author | Shuyu Wu Jingyang Zhong Hui Ye Xusheng Kang |
| author_facet | Shuyu Wu Jingyang Zhong Hui Ye Xusheng Kang |
| author_sort | Shuyu Wu |
| collection | DOAJ |
| description | Abstract It is crucial for archaeological investigations to identify the category of cultural relics by analyzing their chemical composition. This study analyzed the chemical composition distribution of glass cultural relics and applied distance discriminant analysis methods to classify them into two categories. Through stepwise regression, four key feature factors ( $${SiO}_{2}, {K}_{2}O, PbO$$ SiO 2 , K 2 O , P b O , and the presence of weathering on the artifact's surface) were selected from a total of 15 features, including surface weathering. Aside from using columnar table analysis to determine weathering on the surface of the artifact and correlations between categories, and using Spearman correlation coefficients to select key feature factors such as $${SiO}_{2}, {K}_{2}O, PbO, BaO, and \,SrO$$ SiO 2 , K 2 O , P b O , B a O , a n d S r O from 14 total feature factors (excluding weathering on the surface), we established a Mahalanobis distance discriminant model to differentiate unknown glass artifacts. Results indicate that Spearman-Mahalanobis distance discrimination outperformed stepwise regression-Mahalanobis distance discrimination, with an overall accuracy of 99.10% for the former and 98.69% for the latter in identifying high-potassium glass or lead-barium glass. |
| first_indexed | 2024-03-12T17:07:20Z |
| format | Article |
| id | doaj.art-a0f36bf5ce114a5bbf04bb3c30ebb1df |
| institution | Directory Open Access Journal |
| issn | 2050-7445 |
| language | English |
| last_indexed | 2024-03-12T17:07:20Z |
| publishDate | 2023-08-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Heritage Science |
| spelling | doaj.art-a0f36bf5ce114a5bbf04bb3c30ebb1df2023-08-06T11:22:01ZengSpringerOpenHeritage Science2050-74452023-08-0111111010.1186/s40494-023-00999-0Identification of ancient glass categories based on distance discriminant analysisShuyu Wu0Jingyang Zhong1Hui Ye2Xusheng Kang3School of Computer and Computing Science, Hangzhou City UniversitySchool of Business, Hangzhou City UniversitySchool of Information and Electrical Engineering, Hangzhou City UniversitySchool of Computer and Computing Science, Hangzhou City UniversityAbstract It is crucial for archaeological investigations to identify the category of cultural relics by analyzing their chemical composition. This study analyzed the chemical composition distribution of glass cultural relics and applied distance discriminant analysis methods to classify them into two categories. Through stepwise regression, four key feature factors ( $${SiO}_{2}, {K}_{2}O, PbO$$ SiO 2 , K 2 O , P b O , and the presence of weathering on the artifact's surface) were selected from a total of 15 features, including surface weathering. Aside from using columnar table analysis to determine weathering on the surface of the artifact and correlations between categories, and using Spearman correlation coefficients to select key feature factors such as $${SiO}_{2}, {K}_{2}O, PbO, BaO, and \,SrO$$ SiO 2 , K 2 O , P b O , B a O , a n d S r O from 14 total feature factors (excluding weathering on the surface), we established a Mahalanobis distance discriminant model to differentiate unknown glass artifacts. Results indicate that Spearman-Mahalanobis distance discrimination outperformed stepwise regression-Mahalanobis distance discrimination, with an overall accuracy of 99.10% for the former and 98.69% for the latter in identifying high-potassium glass or lead-barium glass.https://doi.org/10.1186/s40494-023-00999-0Mahalanobis distance discriminantStepwise regression analysisGlass category identificationSpearman correlation coefficient |
| spellingShingle | Shuyu Wu Jingyang Zhong Hui Ye Xusheng Kang Identification of ancient glass categories based on distance discriminant analysis Heritage Science Mahalanobis distance discriminant Stepwise regression analysis Glass category identification Spearman correlation coefficient |
| title | Identification of ancient glass categories based on distance discriminant analysis |
| title_full | Identification of ancient glass categories based on distance discriminant analysis |
| title_fullStr | Identification of ancient glass categories based on distance discriminant analysis |
| title_full_unstemmed | Identification of ancient glass categories based on distance discriminant analysis |
| title_short | Identification of ancient glass categories based on distance discriminant analysis |
| title_sort | identification of ancient glass categories based on distance discriminant analysis |
| topic | Mahalanobis distance discriminant Stepwise regression analysis Glass category identification Spearman correlation coefficient |
| url | https://doi.org/10.1186/s40494-023-00999-0 |
| work_keys_str_mv | AT shuyuwu identificationofancientglasscategoriesbasedondistancediscriminantanalysis AT jingyangzhong identificationofancientglasscategoriesbasedondistancediscriminantanalysis AT huiye identificationofancientglasscategoriesbasedondistancediscriminantanalysis AT xushengkang identificationofancientglasscategoriesbasedondistancediscriminantanalysis |