基于DBSCAN算法的郑洛地区史前聚落遗址聚类分析

发布时间：2018-05-26 18:02

本文选题：郑洛地区 + 聚落遗址　；参考：《科学技术与工程》2014年32期

【摘要】：为了解决判别聚落群过于依赖考古专家人工划分的问题,以郑洛地区新石器时代聚落遗址为例,采用基于密度的DBSCAN(density-based spatial clustering of applications with noise)算法对聚落遗址进行空间聚类研究。通过对郑洛地区四个文化时期聚落遗址的分布分析,发现郑洛地区的主体聚落群从研究区东部的嵩山以南地区,转移到郑洛地区中部的伊洛河流域,并且在伊洛河流域长期定居下来,不断发展扩大;大型聚落遗址主要分布在主体聚落群里,除了裴李岗文化时期部分大型聚落较孤立;从仰韶文化后期到龙山文化时期,聚落遗址分布呈主从式环状分布格局;大多数聚落群的走向都和河流分布一致。研究表明,利用DBSCAN算法进行聚落遗址聚类是可行的,通过聚类得到郑洛地区新石器时代四个文化时期聚落遗址的分布特征。
[Abstract]:In order to solve the problem that the discrimination of settlement group is too dependent on artificial division by archaeologists, taking Neolithic settlement sites in Zhengluo area as an example, the density based DBSCAN(density-based spatial clustering of applications with noise) algorithm is used to study the spatial clustering of settlement sites. By analyzing the distribution of settlement sites in the four cultural periods in Zhengluo area, it is found that the main settlement group in Zhengluo area is transferred from the south of Songshan to the Yiluo River basin in the central part of Zhengluo area. Large settlement sites are mainly distributed in the main settlement groups, except for some large settlements in the period of Peiligang culture, which are isolated; from the late Yangshao culture to the Longshan culture period, The distribution of settlement sites is in the pattern of principal and subordinate annular distribution, and the trend of most settlement groups is consistent with the distribution of rivers. The research shows that it is feasible to cluster settlement sites with DBSCAN algorithm, and the distribution characteristics of settlement sites in four cultural periods of Neolithic period in Zhengluo area are obtained by clustering.
【作者单位】：南京信息工程大学地理与遥感学院;
【基金】：国家自然科学基金项目(41071253;41271410)资助
【分类号】：TP311.13;K878

【参考文献】