摘要
针对层次聚类算法高维度数据计算复杂度较高、抗干扰性较差、误差较大等不足,在结合基因表达式编程(GEP)非线性演化优越性能的基础上,提出一种基于GEP计算模型的层次聚类算法(GEPHCA),寻找经过基因遗传进化适应度最高的聚类中心.通过试验对比验证可知:基于基因表达式编程的自适应层次聚类方法在实际应用中是有效的,不仅能够实现自动聚类,而且和一般的聚类方法进行比较,具有自适应迭代、速度较快、稳定高效等优点.
Aiming at the disadvantages of the hierarchical clustering algorithm has toward the high-dimension data in the respects of high computational complexity,poor anti-interference and large error.Based on the superior performance of nonlinear evolution of gene expression programming（GEP）,a kind of gene expression programmed hierarchical clustering algorithm（GEPHCA）is proposed to discover the most suitable cluster centers through gene genetic evolutionary adaptation.Through the experimental verification,the adaptive hierarchical clustering method based on gene expression programming is effective in practical application.It not only can realize automatic clustering,but also have the advantages of adaptive iteration operating speed,faster operating speed,stable and efficient compared with the general clustering method.
作者
姜代红
尹洪胜
张三友
JIANG Daihong;YIN Hongsheng;ZHANG Sanyou(School of Information and Electronic Engineering, Xuzhou Institute of Technology, Xuzhou 221008, China;School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou 221008, China)
出处
《华侨大学学报（自然科学版）》
CAS
北大核心
2018年第3期435-438,共4页
Journal of Huaqiao University(Natural Science)
基金
国家自然科学基金资助项目(61379100)
国家星火计划项目(2015GA690085)
江苏省徐州市省科技计划项目(KC16SQ178)
关键词
基因表达式编程
层次聚类
自适应方法
选择算子
gene expression programming
hierarchical clustering
self-adaptive method
selection operation
