融合混沌灰狼优化算法的K-均值聚类算法
K-Means Algorithm Merged with Chaotic Grey Wolf Optimization Algorithm
李金 1李素 1王祖荣 1姜缘平1
作者信息
- 1. 北京工商大学计算机学院,北京 10048
- 折叠
摘要
针对K-均值聚类(K-means)算法对初始聚类中心位置敏感、容易陷入局部最优的缺点,提出一种融合混沌灰狼优化算法的K-means算法.算法利用混沌系统的随机性和遍历性产生分布较均匀的Tent混沌序列来初始化灰狼种群,获得分布较均匀且多样性较高的初始解,提高了算法的全局搜索能力;在搜索全局最优聚类中心的过程中引入基于精英个体的变异操作,维持种群的多样性,提高了算法的的局部搜索能力,避免算法陷入局部最优.实验结果表明,与基本K-means、基于粒子群算法(PSO)改进的K-means、传统灰狼优化算法(GWO)改进的K-means相比,以上算法具有更优的聚类效果,更强的寻优能力.
Abstract
The K-means clustering algorithm is sensitive to the location of the initial clustering center and is easy to trap into the local optimal.To overcome these disadvantages of the K-means algorithm,a K-means algorithm mer-ged with a chaotic grey wolf optimization algorithm is proposed.The features of chaotic randomness and ergodicity are applied to generate a uniformly distributed Tent chaotic sequence for initializing the grey wolf population,achieving u-niformly distributed initial solutions and high diversity of population,which can enhance the global search ability.In the process of searching cluster centers of the global optimum,elite-based mutation operator is applied to maintain the diversity of the population,which can enhance the local search ability and avoid trapping into the local optimal.Com-pared with K-means,PSO,and GWO,the experiment results show that the proposed algorithm has a better cluster effect and stronger optimization ability.
关键词
灰狼优化算法/混沌序列/全局最优/局部最优/变异Key words
Grey wolf optimization algorithm/Tent chaotic sequence/Global optimal/Local optimal/Mutation引用本文复制引用
基金项目
国家自然科学基金青年基金(42101470)
出版年
2024
NETL
NSTL
万方数据