Improved Boundary Support Vector Clustering with Self-Adaption Support
Concerning the good description of arbitrarily shaped clusters, collecting accurate support vectors (SVs) is critical yet resource-consuming for support vector clustering (SVC). Even though SVs can be extracted from the boundaries for efficiency, boundary patterns with too much noise and inappropria...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-06-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/11/12/1854 |
_version_ | 1797487952046063616 |
---|---|
author | Huina Li Yuan Ping Bin Hao Chun Guo Yujian Liu |
author_facet | Huina Li Yuan Ping Bin Hao Chun Guo Yujian Liu |
author_sort | Huina Li |
collection | DOAJ |
description | Concerning the good description of arbitrarily shaped clusters, collecting accurate support vectors (SVs) is critical yet resource-consuming for support vector clustering (SVC). Even though SVs can be extracted from the boundaries for efficiency, boundary patterns with too much noise and inappropriate parameter settings, such as the kernel width, also confuse the connectivity analysis. Thus, we propose an improved boundary SVC (IBSVC) with self-adaption support for reasonable boundaries and comfortable parameters. The first self-adaption is in the movable edge selection (MES). By introducing a divide-and-conquer strategy with the <i>k</i>-means++ support, it collects local, informative, and reasonable edges for the minimal hypersphere construction while rejecting pseudo-borders and outliers. Rather than the execution of model learning with repetitive training and evaluation, we fuse the second self-adaption with the flexible parameter selection (FPS) for direct model construction. FPS automatically selects the kernel width to meet a conformity constraint, which is defined by measuring the difference between the data description drawn by the model and the actual pattern. Finally, IBSVC adopts a convex decomposition-based strategy to finish cluster checking and labeling even though there is no prior knowledge of the cluster number. Theoretical analysis and experimental results confirm that IBSVC can discover clusters with high computational efficiency and applicability. |
first_indexed | 2024-03-09T23:56:08Z |
format | Article |
id | doaj.art-11ea455b1c5e407dabbe6db6c72b013a |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-09T23:56:08Z |
publishDate | 2022-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-11ea455b1c5e407dabbe6db6c72b013a2023-11-23T16:24:48ZengMDPI AGElectronics2079-92922022-06-011112185410.3390/electronics11121854Improved Boundary Support Vector Clustering with Self-Adaption SupportHuina Li0Yuan Ping1Bin Hao2Chun Guo3Yujian Liu4School of Information Engineering, Xuchang University, Xuchang 461000, ChinaSchool of Information Engineering, Xuchang University, Xuchang 461000, ChinaHere Data Technology, Shenzhen 518000, ChinaGuizhou Provincial Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, ChinaSchool of Information Engineering, Xuchang University, Xuchang 461000, ChinaConcerning the good description of arbitrarily shaped clusters, collecting accurate support vectors (SVs) is critical yet resource-consuming for support vector clustering (SVC). Even though SVs can be extracted from the boundaries for efficiency, boundary patterns with too much noise and inappropriate parameter settings, such as the kernel width, also confuse the connectivity analysis. Thus, we propose an improved boundary SVC (IBSVC) with self-adaption support for reasonable boundaries and comfortable parameters. The first self-adaption is in the movable edge selection (MES). By introducing a divide-and-conquer strategy with the <i>k</i>-means++ support, it collects local, informative, and reasonable edges for the minimal hypersphere construction while rejecting pseudo-borders and outliers. Rather than the execution of model learning with repetitive training and evaluation, we fuse the second self-adaption with the flexible parameter selection (FPS) for direct model construction. FPS automatically selects the kernel width to meet a conformity constraint, which is defined by measuring the difference between the data description drawn by the model and the actual pattern. Finally, IBSVC adopts a convex decomposition-based strategy to finish cluster checking and labeling even though there is no prior knowledge of the cluster number. Theoretical analysis and experimental results confirm that IBSVC can discover clusters with high computational efficiency and applicability.https://www.mdpi.com/2079-9292/11/12/1854support vector clusteringcluster boundaryedge selectionparameter adaptionconvex decomposition |
spellingShingle | Huina Li Yuan Ping Bin Hao Chun Guo Yujian Liu Improved Boundary Support Vector Clustering with Self-Adaption Support Electronics support vector clustering cluster boundary edge selection parameter adaption convex decomposition |
title | Improved Boundary Support Vector Clustering with Self-Adaption Support |
title_full | Improved Boundary Support Vector Clustering with Self-Adaption Support |
title_fullStr | Improved Boundary Support Vector Clustering with Self-Adaption Support |
title_full_unstemmed | Improved Boundary Support Vector Clustering with Self-Adaption Support |
title_short | Improved Boundary Support Vector Clustering with Self-Adaption Support |
title_sort | improved boundary support vector clustering with self adaption support |
topic | support vector clustering cluster boundary edge selection parameter adaption convex decomposition |
url | https://www.mdpi.com/2079-9292/11/12/1854 |
work_keys_str_mv | AT huinali improvedboundarysupportvectorclusteringwithselfadaptionsupport AT yuanping improvedboundarysupportvectorclusteringwithselfadaptionsupport AT binhao improvedboundarysupportvectorclusteringwithselfadaptionsupport AT chunguo improvedboundarysupportvectorclusteringwithselfadaptionsupport AT yujianliu improvedboundarysupportvectorclusteringwithselfadaptionsupport |