Spatial And Temporal Changes Of Geographical Network Community Structure In Mobile Communication Data And Analysis Of Land-use Correlation Of Milan,Italy

The rapid development of communication has spawned a large amount of communication data with location information.Using big data technology to analyze location-based mobile communication data,we can understand the dynamic changes of communication interaction modes between different regions.By superimposing the correlation between the communication interaction mode and the feature features in the relevant geospatial,we can further understand the adaptability between the crowd activity and the urban spatial structure,thus providing auxiliary decision-making for urban sustainable development and optimization of urban management..From the perspective of network,the relationship between the attributes of the objects and the communication network can be grasped from a more macroscopic perspective.It is an important method to analyze the relationship between the network community and the attributes of the objects.This paper proposes a time-space change and feature correlation analysis based on the community structure of directed weighted geographic networks in communication data.Specifically,it includes:(1)Constructing a directed weighted geographic network from mobile communication data by using the spark big data platform.(2)Implementing the Louvain algorithm based on the Spark platform(3)Analyzing the correlation between the community generated by the mobile communication network and the characteristics of the actual object attributes.And the relationship between the variable areas and the constant areas in the changing community generated by the evolution of time and the attributes of the objects,and superimposed map information such as Open Street Map,global surface overlay map,Google historical image map to explore the movement The relationship between the network community formed by the communication network and the geographical boundaries of the actual objects.This paper selects Milan,Italy as the research area,and analyzes the mobile communication data of the region from November 1 to December 15,2013,as well as the remote sensing image of the region and the land distribution data of Milan as experimental data.The experimental results show that:(1)In the community divided by mobile phone communication network for half a month,it can be found that the density of urban structure and the distribution of cultivated land have a greater impact on the division of network communities.(2)For the community division that evolves over time,if the first-level community division is roughly the same,then the secondary and tertiary communities are also generally consistent.(3)Analysis of the volatile and unchanging areas appearing in the dynamically evolving community reveals that if the continuous urban structure in the region accounts for a large proportion,the communities in the region that are divided at different time points will appear.Volatility.If the cultivated land or discontinuous urban structural attributes of the region account for a large proportion,then there will be invariance in the community division.