Building clusters for pattern recognition and analysis of geographical areas can be a useful way to provide relevant information for economic and social decisions. In this paper, we introduce a novel spatial clustering technique, called Bootstrap ClustGeo (BCG), which is a hierarchical approach, based on bootstrap techniques with spatial constraints. We evaluate the performance of the proposed approach BCG through some real case studies and simulations studies with different complexity, by computing Clustering Validation Measures (CVM) and then we compare the approach with the recently proposed ClustGeo (CG). These analyses exhibit the accuracy of BCG, also with respect to CG, in the presented applications, and highlight the great potentiality of this new clustering technique to provide meaningful information for spatial analysis.

建立用于模式识别和地理区域分析的集群可能是为经济和社会决策提供相关信息的有用方法。在本文中，我们介绍了一种新颖的空间聚类技术，称为Bootstrap ClustGeo（BCG），它是一种基于具有空间约束的自举技术的分层方法。我们通过计算具有不同复杂度的真实案例研究和模拟研究，通过计算聚类验证量度（CVM）来评估所提出方法BCG的性能，然后将其与最近提出的ClustGeo（CG）进行比较。这些分析显示了BCG的准确性，以及CG，在提出的应用中，突出了这种新的聚类技术为空间分析提供有意义的信息的巨大潜力。