论文部分内容阅读
研究基于模糊聚类的遗传算法应用于复杂网络社区挖掘,该算法将聚类融合引入到交叉算子中,利用父个体的聚类信息产生新个体,避免了传统交叉算子单纯交换字符串而忽略聚类内容所带来的问题。该算法采用混沌序列策略进行种群生成,使初始种群中的个体具有一定聚类精度并有较强的多样性,并将局部搜索机制用于变异算子,有效地缩小搜索空间,加快算法收敛速度。该算法与当前具有代表性的社区挖掘算法进行比较,并在仿真网络和现实网络上验证测试,实验结果表明了该算法的可行性和有效性。
The genetic algorithm based on fuzzy clustering is applied to the mining of complex network communities. The algorithm introduces clustering fusion into crossover operator, and uses the clustering information of the parent individual to generate new individuals. It avoids the simple exchange of strings by the traditional crossover operator Ignore the problems caused by clustering content. The algorithm uses the chaos sequence strategy to generate the population, which makes the individuals in the initial population have some clustering precision and strong diversity, and uses the local search mechanism for the mutation operator, effectively narrows the search space and accelerates the convergence speed of the algorithm . The algorithm is compared with the current representative community mining algorithm and validates the test on the simulation network and the real network. Experimental results show the feasibility and effectiveness of the algorithm.