Convex fuzzy k-medoids clustering

被引：9
|
作者：
Pinheiro, Daniel N. [1 ]
Aloise, Daniel [2 ]
Blanchard, Simon J. [3 ]
机构：
[1] Univ Fed Rio Grande do Norte, Ctr Technol, BR-59078970 Natal, RN, Brazil
[2] Polytech Montreal, Dept Comp & Software Engn, Montreal, PQ H3C 3A7, Canada
[3] Georgetown Univ, McDonough Sch Business, Washington, DC 20057 USA
来源：
FUZZY SETS AND SYSTEMS | 2020年 / 389卷
基金：
加拿大自然科学与工程研究理事会; 瑞典研究理事会;
关键词：
Fuzzy clustering; Unsupervised learning; Categorization; MODEL;
D O I：
10.1016/j.fss.2020.01.001
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
K-medoids clustering is among the most popular methods for cluster analysis despite its use requiring several assumptions about the nature of the latent clusters. In this paper, we introduce the Convex Fuzzy k-Medoids (CFKM) model, which not only relaxes the assumption that objects must be assigned entirely to one and only one medoid, but also that medoids must be assigned entirely to one and only one cluster. The resulting model is convex, thus its resolution is completely robust to initialization. To illustrate the usefulness of the CFKM model, we compare it with two fuzzy k-medoids clustering models: the Fuzzy k-Medoids (FKM) and the Fuzzy Clustering with Multi-Medoids (FMMdd), both solved approximately by heuristics because of their hard computational complexity. Our experiments with both synthetic and real-world data as well as a user survey reveal that the model is not only more robust to the choice hyperparameters of the fuzzy clustering task, but also that it can uniquely discover important aspects of data inherently fuzzy in nature. (C) 2020 Elsevier B.V. All rights reserved.
引用
收藏
页码：66 / 92
页数：27
相关论文
共 50 条
  • [21] Clustering Time Series with k-Medoids Based Algorithms
    Holder, Christopher
    Guijo-Rubio, David
    Bagnall, Anthony
    [J]. ADVANCED ANALYTICS AND LEARNING ON TEMPORAL DATA, AALTD 2023, 2023, 14343 : 39 - 55
  • [22] The K-medoids clustering algorithm by a class of P system
    Zhao, Yuzhen
    Liu, Xiyu
    Qu, Jianhua
    [J]. Journal of Information and Computational Science, 2012, 9 (18): : 5777 - 5790
  • [23] Genetic K-Medoids spatial clustering with obstacles constraints
    Zhang, Xueping
    Wang, Jiayao
    Wu, Fang
    Fan, Zhongshan
    Xu, Wenbo
    [J]. 2006 3RD INTERNATIONAL IEEE CONFERENCE INTELLIGENT SYSTEMS, VOLS 1 AND 2, 2006, : 809 - 814
  • [24] Optimization of K-medoids Algorithm for Initial Clustering Center
    Wang Yan E
    An Jian
    Liang Yan
    Wang HongGang
    [J]. 2020 4TH INTERNATIONAL CONFERENCE ON CONTROL ENGINEERING AND ARTIFICIAL INTELLIGENCE (CCEAI 2020), 2020, 1487
  • [25] An Effective VNS Algorithm for k-Medoids Clustering Problem
    de Moura Brito, Jose Andre
    Semaan, Gustavo Silva
    Fadel, Augusto Cesar
    [J]. IEEE LATIN AMERICA TRANSACTIONS, 2022, 20 (05) : 710 - 717
  • [26] A Parallel K-Medoids Algorithm for Clustering based on MapReduce
    Shafiq, M. Omair
    Torunski, Eric
    [J]. 2016 15TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2016), 2016, : 502 - 507
  • [27] Clustering Big Data Based on Distributed Fuzzy K-Medoids: An Application to Geospatial Informatics
    Madbouly, Magda M.
    Darwish, Saad M.
    Bagi, Noha A.
    Osman, Mohamed A.
    [J]. IEEE ACCESS, 2022, 10 : 20926 - 20936
  • [28] Kernel Based K-Medoids for Clustering Data with Uncertainty
    Yang, Baoguo
    Zhang, Yang
    [J]. ADVANCED DATA MINING AND APPLICATIONS, ADMA 2010, PT I, 2010, 6440 : 246 - 253
  • [29] Comparison between K-Means and K-Medoids Clustering Algorithms
    Madhulatha, Tagaram Soni
    [J]. ADVANCES IN COMPUTING AND INFORMATION TECHNOLOGY, 2011, 198 : 472 - 481
  • [30] MPDP k-medoids: Multiple partition differential privacy preserving k-medoids clustering for data publishing in the Internet of Medical Things
    Zhang, Zekun
    Wu, Tongtong
    Sun, Xiaoting
    Yu, Jiguo
    [J]. INTERNATIONAL JOURNAL OF DISTRIBUTED SENSOR NETWORKS, 2021, 17 (10)
12345