基于决策树算法与系统聚类的玻璃制品分类研究

Classification Study of Glass Products Based on Decision Tree Algorithm and System Clustering

摘要: 本文主要研究了古代玻璃制品的成分分析和鉴别，基于决策树算法建立玻璃分类模型，对63个文物样品进行分类，并对比分类结果与真实分类结果的吻合度，得出分类规律。在高钾无风化、高钾风化、铅钡无风化、铅钡风化的分类基础上，本文考虑基于系统聚类法对每个大类进行亚分类，并对分类后的结果进行合理性、敏感性分析，实现了对未知类型玻璃制品的鉴别以及各类型玻璃的亚类划分，对文物鉴别与玻璃制品分类有重要意义。

Abstract: This paper mainly studies the composition analysis and identification of ancient glass products, es-tablishes the glass classification model based on the decision tree algorithm, and classifies 63 cul-tural relic samples. The classification rule was obtained by comparing the agreement between the classification results and the real classification results. Based on the classification of high potassium weathering, high potassium weathering, lead-barium weathering and lead-barium weathering, this paper considers the sub-classification of each major category based on the systematic clustering method, the rationality and sensitivity of the results are analyzed, and the identification of un-known types of glass and the subclassification of different types of glass are realized.