Discovering latent structures with integrated propagation algorithms in geographical information networks

Abstract

The real-world exists various kinds of complex network systems, including geographical information systems (GIS) as the important components. However, it is hard to understand the functions scientifically because that the structures are latent for our eyes in these systems. In this paper, a specific model is proposed to deal with the expression of geographical information networks. And by integrating the belief propagation algorithm and label propagation algorithm, our algorithm is able to discover the latent structures and achieve some understandings of the networks without knowing the number of communities. We test the algorithm on the benchmark networks as well as the real-world subway-road networks. The results show the availability for the applications of our algorithm to the geographical information networks.