摘要
为解决传统k-means聚类算法在聚类精度及中心点选取方面的问题,提出一种基于精英反向学习的萤火虫k-means改进算法。针对k-means算法的弱点,利用萤火虫优化算法具有较强全局搜索能力这一特性,使用精英反向学习策略对萤火虫进行改进,扩大萤火虫的搜索范围并提高收敛速度,对萤火虫的吸引度和步长因子进行改进,提升聚类效率。将改进算法运用到UCI标准数据集进行聚类仿真实验,该算法在寻优精度和收敛速度上有更好的结果,验证了其有效性。
To solve the problem of traditional k-means clustering algorithm in clustering precision and centers selection,a firefly k-means method based on elite opposition-based learning was presented.To overcome shortcomings of k-means,the firefly optimization algorithm with powerful ability of global search was used,and elite opposition-based learning strategy was used to improve the search range of fireflies,and the attracting and step factors of fireflies were improved,which improved the clustering efficiency.The clustering experimental results verify the effectiveness of the proposed algorithm and better results in optimization precision and convergence speed are achieved by using the improved algorithm based on the UCI standard data set.
作者
汤文亮
张平
汤树芳
TANG Wen-liang;ZHANG Ping;TANG Shu-fang(School of Information Engineering,East China Jiaotong University,Nanchang 330013,China;School of Software,East China Jiaotong University,Nanchang 330013,China)
出处
《计算机工程与设计》
北大核心
2019年第11期3164-3169,共6页
Computer Engineering and Design
基金
2017年省科技厅重点研发计划基金项目(20171BBH80005)
关键词
萤火虫算法
K-MEANS算法
精英反向学习
反向学习策略
精英反向解
firefly algorithm
k-means algorithm
elite opposition-based learning
opposition-based learning strategy
elite opposite solution
