论文部分内容阅读
针对K-means聚类算法过度依赖初始聚类中心、局部收敛、稳定性差等问题,提出一种基于变异精密搜索的蜂群聚类算法.该算法利用密度和距离初始化蜂群,并根据引领蜂的适应度和密度求解跟随蜂的选择概率P;然后通过变异精密搜索法产生的新解来更新侦查蜂,以避免陷入局部最优;最后结合蜂群与粗糙集来优化K-means.实验结果表明,该算法不仅能有效抑制局部收敛、减少对初始聚类中心的依赖,而且准确率和稳定性均有较大的提高.
In order to overcome the problems of over-reliance on initial clustering center, local convergence and poor stability of K-means clustering algorithm, this paper proposes a swarm clustering algorithm based on mutation precision search, which initializes the bee population by density and distance, The fitness and density of the bees follow the choice probability P of the bees; then, the investigation bees are updated by the new solutions generated by the mutation precision search to avoid falling into the local optimum; Finally, the K-means are optimized by combining the bees and the rough sets. It is shown that this algorithm can not only effectively restrain the local convergence but also reduce the dependence on the initial clustering center, and the accuracy and stability are greatly improved.