Three Fuzzy c-Shapes Clustering Algorithms for Series Data

IF 0.7 Q4 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Mizuki Fujita, Yuchi Kanzawa
{"title":"Three Fuzzy <i>c</i>-Shapes Clustering Algorithms for Series Data","authors":"Mizuki Fujita, Yuchi Kanzawa","doi":"10.20965/jaciii.2023.p0976","DOIUrl":null,"url":null,"abstract":"Various fuzzy clustering algorithms have been proposed for vectorial data. However, most of these methods have not been applied to series data. This study presents three fuzzy clustering algorithms for series data based on shape-based distances. The first algorithm involves Shannon entropy regularization of the k-shape objective function. The second algorithm is similar to the revised Bezdek-type fuzzy c -means algorithm obtained by replacing the membership of the hard c -means objective function with its power. The third algorithm involves Tsallis entropy regularization of the objective function of the second algorithm. Theoretical observations revealed that the third algorithm is a generalization of the first and second algorithms, which was validated by numerical experiments. Furthermore, numerical experiments were performed using 11 benchmark datasets to demonstrate that the third algorithm outperforms the others in terms of accuracy.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"57 1","pages":"0"},"PeriodicalIF":0.7000,"publicationDate":"2023-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Advanced Computational Intelligence and Intelligent Informatics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.20965/jaciii.2023.p0976","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Various fuzzy clustering algorithms have been proposed for vectorial data. However, most of these methods have not been applied to series data. This study presents three fuzzy clustering algorithms for series data based on shape-based distances. The first algorithm involves Shannon entropy regularization of the k-shape objective function. The second algorithm is similar to the revised Bezdek-type fuzzy c -means algorithm obtained by replacing the membership of the hard c -means objective function with its power. The third algorithm involves Tsallis entropy regularization of the objective function of the second algorithm. Theoretical observations revealed that the third algorithm is a generalization of the first and second algorithms, which was validated by numerical experiments. Furthermore, numerical experiments were performed using 11 benchmark datasets to demonstrate that the third algorithm outperforms the others in terms of accuracy.
序列数据的三种模糊c形聚类算法
针对向量数据,已经提出了各种模糊聚类算法。然而,这些方法大多尚未应用于序列数据。提出了三种基于形状距离的序列数据模糊聚类算法。第一种算法涉及k形目标函数的香农熵正则化。第二种算法类似于修正的bezdek型模糊c均值算法,将硬c均值目标函数的隶属度替换为其幂次。第三种算法对第二种算法的目标函数进行了Tsallis熵正则化。理论观察表明,第三种算法是第一种和第二种算法的推广,数值实验验证了这一点。此外,使用11个基准数据集进行了数值实验,以证明第三种算法在准确性方面优于其他算法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
1.50
自引率
14.30%
发文量
89
期刊介绍: JACIII focuses on advanced computational intelligence and intelligent informatics. The topics include, but are not limited to; Fuzzy logic, Fuzzy control, Neural Networks, GA and Evolutionary Computation, Hybrid Systems, Adaptation and Learning Systems, Distributed Intelligent Systems, Network systems, Multi-media, Human interface, Biologically inspired evolutionary systems, Artificial life, Chaos, Complex systems, Fractals, Robotics, Medical applications, Pattern recognition, Virtual reality, Wavelet analysis, Scientific applications, Industrial applications, and Artistic applications.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信