Analyzing the composition of cities using spatial clustering

Cities all around the world are in constant evolution due to numerous factors, such as fast urbanization and new ways of communication and transportation. Since understanding the composition of cities is the key to intelligent urbanization, there is a growing need to develop urban computing and analysis tools to guide the orderly development of cities, as well as to enhance their smooth and beneficiary evolution. This paper presents a spatial clustering approach to discover interesting regions and regions which serve different functions in cities. Spatial clustering groups the objects in a spatial dataset and identifies contiguous regions in the space of the spatial attributes. We formally define the task of finding uniform regions in spatial data as a maximization problem of a plug-in measure of uniformity and introduce a prototype-based clustering algorithm named CLEVER to find such regions. Moreover, polygon models which capture the scope of a spatial cluster and histogram-style distribution signatures are used to annotate the content of a spatial cluster in the proposed methodology; they play a key role in summarizing the composition of a spatial dataset. Furthermore, algorithms for identifying popular distribution signatures and approaches for identifying regions which express a particular distribution signature will be presented. The proposed methodology is demonstrated and evaluated in a challenging real-world case study centering on analyzing the composition of the city of Strasbourg in France.