高维空间数据灰色凸关联度聚类算法仿真  

Simulation of Grey Convex Correlation Degree Clustering Algorithm for High-Dimensional Spatial Data

作　　者：杨成义 熊才权[2] YANG Cheng-yi;XIONG Cai-quan(School of Information Technology,Guangdong Technology College,Zhaoqing Guangdong 526100,China;School of Computer Science,Hubei University of Technology,Hubei Wuhan 430068,China)

机构地区：[1]广东理工学院信息技术学院,广东肇庆526100 [2]湖北工业大学计算机学院,湖北武汉430068

出　　处：《计算机仿真》2023年第6期523-527,共5页Computer Simulation

摘　　要：为了提升数据聚类效果与效率,提出一种基于灰色凸关联度的高维空间数据聚类算法。采用灰色凸关联度组建截断幂基三次样条函数,根据灰色凸关联算法组建关联度模型去除高维空间数据中的噪声。选择相似度最高的两个簇类合并处理,组建一个最相似线性表,采用其表示每个簇类和最相似簇类两者之间的相似度。在聚类过程中,选择最相似的簇类合并,同时引入信息熵对聚类结果迭代寻优,最终实现高维空间数据聚类。经过具体实验测试结果分析可知,所提算法不仅能够有效降低时间复杂度,同时还能够获取精准的聚类结果。In order to improve the effect and efficiency of data clustering,this paper presented an algorithm for high-dimensional spatial data clustering based on gray convex relation.Firstly,the grey convex relation was used to construct a truncated power cubic spline function.And then,the algorithm based on grey convex relation was adopted to build a relation model,thus removing the noise in high-dimensional spatial data.Secondly,the two clusters with the highest similarity were merged to form a most similar linear table,which was used to represent the similarity between each cluster and the most similar cluster.In the clustering process,the most similar clusters were merged.Meanwhile,information entropy was introduced to iteratively optimize the clustering result.Finally,high-dimensional spatial data clustering was completed.After analyzing the specific expermental tex results,it can be seen that the proposed algo-rithm can not only effectively reduce the time complexity,but also obtain accurate clustering results.

关 键 词：灰色凸关联度 高维空间 数据聚类 信息熵 最相似线性表 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]