author：
Shi, Zhaoyin
(Shi, Zhaoyin.)
[1]
|
Chen, Long
(Chen, Long.)
[2]
|
Ding, Weiping
(Ding, Weiping.)
[3]
|
Zhong, Xiaopin
(Zhong, Xiaopin.)
[4]
|
Wu, Zongze
(Wu, Zongze.)
[5]
|
Chen, Guang-Yong
(Chen, Guang-Yong.)
[6]
|
Zhang, Chuanbin
(Zhang, Chuanbin.)
[7]
|
Wang, Yingxu
(Wang, Yingxu.)
[8]
|
Philip Chen, C.L.
(Philip Chen, C.L..)
[9]
Unfold
Abstract：
The graph-information-based fuzzy clustering has shown promising results in various datasets. However, its performance is hindered when dealing with high-dimensional data due to challenges related to redundant information and sensitivity to the similarity matrix design. To address these limitations, this article proposes an implicit fuzzy k-means (FKMs) model that enhances graph-based fuzzy clustering for high-dimensional data. Instead of explicitly designing a similarity matrix, our approach leverages the fuzzy partition result obtained from the implicit FKMs model to generate an effective similarity matrix. We employ a projection-based technique to handle redundant information, eliminating the need for specific feature extraction methods. By formulating the fuzzy clustering model solely based on the similarity matrix derived from the membership matrix, we mitigate issues, such as dependence on initial values and random fluctuations in clustering results. This innovative approach significantly improves the competitiveness of graph-enhanced fuzzy clustering for high-dimensional data. We present an efficient iterative optimization algorithm for our model and demonstrate its effectiveness through theoretical analysis and experimental comparisons with other state-of-the-art methods, showcasing its superior performance. © 2024 IEEE.
Keyword：
Cluster analysis
Extraction
Feature extraction
Fuzzy clustering
Graphic methods
Image segmentation
Iterative methods
K-means clustering
Matrix algebra
Classification
723 Computer Software, Data Handling and Applications - 802.3 Chemical Operations - 903.1 Information Sources and Analysis - 921.1 Algebra - 921.6 Numerical Methods
Type
This work was supported in part by the Guangdong-Hong Kong-Macao Joint Innovation Project under Grant 023A0505030016; in part by the Science and Technology Development Fund, Macau, under Grant 0046/2023/RIA1; in part by the University of acau and the University of Macau Development Foundation under Grant MYRG-GRG2023-00106-FST-UMDF; in part by the Youth Foundation of henzhen University under Grant 868-000001032407; in part by the National Natural Science Foundation of China under Grant 61976120 and Grant 62173091; in part by the Natural Science Foundation of Jiangsu Province under Grant BK20231337; in part by the Natural Science Key Foundation of Jiangsu Education Department under Grant 21KJA510004; in part by the Shenzhen Fundamental Research Fund under Grant CYJ20230808105212023; and in part by the National Key Research and Development Program of China under Grant 2020AAA0108300. This article was recommended by Associate Editor S. Y. S. Ong.Manuscript received 22 October 2023; revised 14 January 2024 and 3 April 2024; accepted 15 April 2024. Date of publication 30 May 2024; date of current version 27 November 2024. This work was supported in part by the Guangdong-Hong Kong-Macao Joint Innovation Project under Grant 2023A0505030016; in part by the Science and Technology Development Fund, Macau, under Grant 0046/2023/RIA1; in part by the University of Macau and the University of Macau Development Foundation under Grant MYRG-GRG2023-00106-FST-UMDF; in part by the Youth Foundation of Shenzhen University under Grant 868-000001032407; in part by the National Natural Science Foundation of China under Grant 61976120 and Grant 62173091; in part by the Natural Science Foundation of Jiangsu Province under Grant BK20231337; in part by the Natural Science Key Foundation of Jiangsu Education Department under Grant 21KJA510004; in part by the Shenzhen Fundamental Research Fund under Grant JCYJ20230808105212023; and in part by the National Key Research and Development Program of China under Grant 2020AAA0108300. This article was recommended by Associate Editor Y. S. Y. S. Ong. (Corresponding authors: Long Chen; Xiaopin Zhong.) Please see the Acknowledgment section of this article for the author affiliations.
Access Number
EI:20242316205334
