Research On Community Detection Algorithm Of Weighted Network Based On Average Mutual Information

With the rapid development of mobile Internet,Internet of things and other technologies,the problem of acquiring community structures in complex networks has gradually become a research hotspot.The community structure of complex networks is helpful to understand the topological structure of networks and provides important basis for the further study of complex networks.Therefore,it is of great significance to obtain the community structure of a complex network.Community detection algorithm is a kind of algorithm that can accurately divide the community structure of complex network.At present,most researches on community detection algorithms focus on unweighted complex networks,but in real life,weighted networks have more practical application value.In addition,there is a Resolution Limit in the current mainstream evaluation criteria,which makes some algorithms unable to find smaller communities in the network.Therefore,in view of the problems mentioned above,the thesis carries out relevant research on the community detection algorithm of complex networks.The main content includes the following aspects:(1)Based on the idea of the modularity optimization algorithm and combining average mutual information and modularity as the objective function,the thesis proposes an AMI-CDW discovery algorithm for weighted network community based on average mutual information,which is applicable to both unweighted network and weighted network.Then the main idea of the algorithm and its implementation process are expounded.Finally,the algorithm is compared with other unweighted network community detection algorithms and weighted network community detection algorithms.The experimental results show that the algorithm has a high accuracy in community division on both weighted network and unweighted network.In addition,the experimental results on some datasets show that the average mutual information evaluation criteria can alleviate the problem of Resolution Limit to some extent.(2)In order to further improve the operation efficiency of the AMI-CDW algorithm,the AMI-CDW algorithm was analyzed in detail to find the time-consuming stages in the execution process.Parallel processing is carried out in the time-consuming phase using JUC framework,and the multi-core performance of modern computers is fully utilized to improve the operation efficiency of the algorithm.The experimental results show that the parallel algorithm can improve the efficiency of the original algorithm on the premise of ensuring the accuracy of the results.Overall,the AMI-CDW algorithm is effective for community division on unweighted and weighted networks.Parallelization of the algorithm can also effectively improve the efficiency of the algorithm.