Scale-free Characteristics and Link Prediction in Complex Railway Network

Abstract The link-prediction of complex networks is a new method network structure mining, which different from the traditional methods based on machine learning. It reveals those existing relations and predicts possible ones, by using similarity index structure. This paper studied topology railway link-prediction. dataset was firstly obtained sampling pre-processing. Its degree obeys power-law distribution with scale-free characteristics. Then, we give some predictions for networks. These tests reached good prediction accuracy. research result has demonstrated that topological could be better choice to real