Research On Community Discovery In Complex Networks Based On Intelligence Algorithm

Complex networks theory is an important method of complexity science,widely favored by interdisciplinary researchers for a long time.Community structure is one of the network structure characteristics,and the network which has obvious community structure has the characteristics of local accumulation identifying the relationship between the whole and segment.The research of community mining can reveal the structural features of complex networks.We can analyze the topology of the network through community mining,and then predict network structure,analyze the influence on network communication,synchronization and control dynamics and so on.So the research of community discovery has important theoretical significance and practical value.Many algorithms are employed in community discovery,and modularity-based methods is an important branch.At present,many intelligent optimization algorithms applied in the field of community discovery,such as genetic algorithm,ant colony algorithm,particle swarm optimization algorithm,bat algorithm and so on.Aimed for the problem of slow convergence speed and low accuracy in community detection,this thesis puts forward an improved algorithms.The main research work and achievements are as follows:The basic principle and process of the whale algorithm are analyzed in detail firstly.Though this algorithm has the advantages of less parameters and simple operation,the search processing depend on the randomness of parameters to a large degree.Thus,an improved whale algorithm is proposed,that is add inertia weight operator into the basic algorithm,and its performance is tested by 23 groups of functions.Finally,the experiment verify the convergence of the improved algorithm is faster than basic algorithms and has a good modularity value,so we verify the effectiveness of the improved algorithm.Aiming at the appilication of complex networks,an improved discrete whale algorithm is proposed.The algorithm is based on the character encoding,part of whale utilized label propagation method based on node importance initialization,this method can guarantee the diversity of population.Secondly,adopt different strategies in the position updating,add inertia weight operator,enhancing the local search ability.Cooperate with a single road intersection algorithm,increasing the population diversity and global search ability.Finally immune clonal selection operator is used to improve the search efficiency of the algorithm.Comparing with other algorithms,the simulation experiment firstly performed on seven real networks verify the convergence of the improved algorithm is faster than other algorithms and has a good modularity value,then verify the validity of the algorithm,finally gives the visual analysis of Karate network and Dolphin network.