1/10/2024 0 Comments Comso.org mailist social network![]() Machine learning algorithms for ancient pottery classification are also applied in. In a robust methodology for classification of archaeological ceramic data described by elemental concentration is proposed, and experiments are carried out using k-nearest neighbors, learning vector quantization (LVQ) and decision trees. In a wide set of supervised and unsupervised learning algorithms are considered for archaeometric data analysis. In particular, X-ray fluorescence (XRF) analysis coupled with unsupervised methods for data analysis has proved to be a useful tool to check for the presence of the same raw materials. The classical approach in archeometric data analysis is to use unsupervised methods such as principal component analysis (PCA), hierarchical cluster analysis (HCA) and K-means clustering. ![]() Clays can have a different composition within the same quarry and, on the other hand, be quite similar in different sites for this reason, it is generally necessary to pay particular attention to minor and trace elements. The knowledge of the elemental chemical composition can be exploited to find out different geographical proveniences allowing to confirm the existence of fabric groups and supporting the hypothesis of a common origin for some fragments. Pottery sherds are the most abundant materials in archaeological excavations and are widely used to help in gathering knowledge of local furnace presence and commercial trades.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |