基于DBSCAN算法的郑洛地区史前聚落遗址聚类分析

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。

Clustering Analysis of the Neolithic Settlement Sites in Zhengzhou-Luoyang Area Based on DBSCAN

In this paper, to solve the problem that the classes are manually divided, the method of DBSCAN which is a spatial clustering algorithm based on density is used to analyze the sites in Zhengzhou-Luoyang area. It is found out that the main part of settlement in Zhengzhou-Luoyang area moved from the southern part of Songshan Mountain to Yiluohe basin, where the ancient people settled down and kept developing. Most of the large settlement sites distributed together, except the large settlement sites during Peiligang culture period, which are more isolated. The main classes distributed as a pattern of the master-slave ring from late Yangshao culture to Longshan culture. Besides, the trend of most classes is the same as the distribution of the river. The results of the clustering analysis suggested that using DBSCAN algorithm to divide the settlement sites into classes is feasible, and the clustering results revealed the spatial distribution pattern of the Neolithic settlement sites in Zhengzhou-Luoyang area.