一种融合免疫接种机制的改进鱼群聚类算法

传统的K-均值聚类方法，在聚类过程中过度依赖初始聚类中心的选择，同时由于全局搜索能力的不足，很难得到精确的聚类中心。鱼群算法在解决优化问题中表现出良好的并行性和全局搜索特性，但由于人为设置参数的影响可能会陷入局部最优。针对聚类问题的特征，将鱼群算法运用到聚类问题中，在使用自适应步长的鱼群算法的基础上，进一步融合免疫接种机制，加强算法对精确解的搜索性能，通过UCI数据集上的实验分析和比较，表明算法具有更好的有效性和稳定性。

Improved fish swarm clustering algorithm combined with immunity-vaccination mecha-nism

The traditional K-means algorithm is over-dependent on the choice of the initial cluster centers during the clustering process. Meanwhile, due to the lack of global search capability, it is difficult to get the accurate cluster centers. Fish-school algorithm shows good parallelism and global search feature in solving optimization problems, but may fall into local optimal solution because of the artificial parameters. In this paper, it applies fish-school algorithm to the clustering problems according to their characteristics and combines immunity-vaccination mechanism with the fish-school algorithm using adaptive step to strengthen the search performance of the algorithm for the exact solution. The experimental analysis and comparison results on UCI datasets show that the algorithm has better validity and stability.