聚类不确定性的三支决策方法综述  

Summary on Three-way Decision Method for Clustering Uncertainty

在线阅读下载全文

作  者:聂斌[1] 靳海科 张玉超 郑学鹏 陈星鑫 苗震 李欢 NIE Bin;JIN Haike;ZHANG Yuchao;ZHENG Xuepeng;CHEN Xingxin;MIAO Zhen;LI Huan(College of Computer Science,Jiangxi University of Chinese Medicine,Nanchang 330004,China)

机构地区:[1]江西中医药大学计算机学院,江西南昌330004

出  处:《现代信息科技》2024年第18期25-32,38,共9页Modern Information Technology

基  金:国家自然科学基金(82260849,61562045);江西省教育厅科技计划研究项目(GJJ211256);江西中医药大学校级科技创新团队发展计划(CXTD22015)。

摘  要:由于数据有复杂性、多样性和不确定性的特点,聚类通常存在不确定性,这种不确定性是指聚类结果的不一致性,从而影响分析的准确性,而通过三支决策方法构建不确定域,对不确定域进行延迟决策,能够带来一系列的优势。近些年来,这个研究热点涌现许多重要的工作。对聚类不确定的三支决策方法模型和研究方向进行介绍,按照三支聚类构建过程中遇到的问题进行总结。首先,给出三支聚类的表现形式。其次,分别阐述如何构建三支聚类的核心域和边界域,如何确定阈值,如何设计有效性指标,并介绍其中具有代表性的工作。最后,对聚类不确定的三支决策方法进行总结,并展望未来的研究方向。Due to the characteristic of complexity,diversity and uncertainty of data,clustering usually has uncertainty,which refers to the inconsistency of clustering results,thus affecting the accuracy of analysis.The Three-way Decision method can bring a series of advantages by constructing an uncertain domain and making delayed decision on the uncertain domain.In recent years,a lot of important work has emerged from this research hotspot.This paper introduces the model and the research direction of Three-way Decision method with clustering uncertainty,and summarizes the problems encountered in the construction process of Three-way Clustering.Firstly,the expression form of the Three-way Clustering is given.Secondly,the paper describes how to construct the core domain and boundary domain of the Three-way Clustering,how to determine the threshold value and how to design the validity index,respectively.It also introduces the representative work among them.Finally,the paper summarizes the Three-way Decision method of clustering uncertainty,and looks forward to the future research direction.

关 键 词:聚类 不确定性 三支聚类 核心域 边界域 阈值 有效性指标 

分 类 号:TP391[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象