An Improved Three-Way Clustering Based on Ensemble Strategy
As a powerful data analysis technique, clustering plays an important role in data mining. Traditional hard clustering uses one set with a crisp boundary to represent a cluster, which cannot solve the problem of inaccurate decision-making caused by inaccurate information or insufficient data. In orde...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-04-01
|
Series: | Mathematics |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-7390/10/9/1457 |
_version_ | 1797503894147825664 |
---|---|
author | Tingfeng Wu Jiachen Fan Pingxin Wang |
author_facet | Tingfeng Wu Jiachen Fan Pingxin Wang |
author_sort | Tingfeng Wu |
collection | DOAJ |
description | As a powerful data analysis technique, clustering plays an important role in data mining. Traditional hard clustering uses one set with a crisp boundary to represent a cluster, which cannot solve the problem of inaccurate decision-making caused by inaccurate information or insufficient data. In order to solve this problem, three-way clustering was presented to show the uncertainty information in the dataset by adding the concept of fringe region. In this paper, we present an improved three-way clustering algorithm based on an ensemble strategy. Different to the existing clustering ensemble methods by using various clustering algorithms to produce the base clustering results, the proposed algorithm randomly extracts a feature subset of samples and uses the traditional clustering algorithm to obtain the diverse base clustering results. Based on the base clustering results, labels matching is used to align all clustering results in a given order and voting method is used to obtain the core region and the fringe region of the three way clustering. The proposed algorithm can be applied on the top of any existing hard clustering algorithm to generate the base clustering results. As examples for demonstration, we apply the proposed algorithm on the top of K-means and spectral clustering, respectively. The experimental results show that the proposed algorithm is effective in revealing cluster structures. |
first_indexed | 2024-03-10T03:56:53Z |
format | Article |
id | doaj.art-b8a044b96d2c4ca29e77e5e67f9507ff |
institution | Directory Open Access Journal |
issn | 2227-7390 |
language | English |
last_indexed | 2024-03-10T03:56:53Z |
publishDate | 2022-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Mathematics |
spelling | doaj.art-b8a044b96d2c4ca29e77e5e67f9507ff2023-11-23T08:44:37ZengMDPI AGMathematics2227-73902022-04-01109145710.3390/math10091457An Improved Three-Way Clustering Based on Ensemble StrategyTingfeng Wu0Jiachen Fan1Pingxin Wang2School of Computer, Jiangsu University of Science and Technology, Zhenjiang 212003, ChinaSchool of Computer, Jiangsu University of Science and Technology, Zhenjiang 212003, ChinaSchool of Science, Jiangsu University of Science and Technology, Zhenjiang 212003, ChinaAs a powerful data analysis technique, clustering plays an important role in data mining. Traditional hard clustering uses one set with a crisp boundary to represent a cluster, which cannot solve the problem of inaccurate decision-making caused by inaccurate information or insufficient data. In order to solve this problem, three-way clustering was presented to show the uncertainty information in the dataset by adding the concept of fringe region. In this paper, we present an improved three-way clustering algorithm based on an ensemble strategy. Different to the existing clustering ensemble methods by using various clustering algorithms to produce the base clustering results, the proposed algorithm randomly extracts a feature subset of samples and uses the traditional clustering algorithm to obtain the diverse base clustering results. Based on the base clustering results, labels matching is used to align all clustering results in a given order and voting method is used to obtain the core region and the fringe region of the three way clustering. The proposed algorithm can be applied on the top of any existing hard clustering algorithm to generate the base clustering results. As examples for demonstration, we apply the proposed algorithm on the top of K-means and spectral clustering, respectively. The experimental results show that the proposed algorithm is effective in revealing cluster structures.https://www.mdpi.com/2227-7390/10/9/1457ensemble clusteringthree-way decisionthree-way clusteringvoting |
spellingShingle | Tingfeng Wu Jiachen Fan Pingxin Wang An Improved Three-Way Clustering Based on Ensemble Strategy Mathematics ensemble clustering three-way decision three-way clustering voting |
title | An Improved Three-Way Clustering Based on Ensemble Strategy |
title_full | An Improved Three-Way Clustering Based on Ensemble Strategy |
title_fullStr | An Improved Three-Way Clustering Based on Ensemble Strategy |
title_full_unstemmed | An Improved Three-Way Clustering Based on Ensemble Strategy |
title_short | An Improved Three-Way Clustering Based on Ensemble Strategy |
title_sort | improved three way clustering based on ensemble strategy |
topic | ensemble clustering three-way decision three-way clustering voting |
url | https://www.mdpi.com/2227-7390/10/9/1457 |
work_keys_str_mv | AT tingfengwu animprovedthreewayclusteringbasedonensemblestrategy AT jiachenfan animprovedthreewayclusteringbasedonensemblestrategy AT pingxinwang animprovedthreewayclusteringbasedonensemblestrategy AT tingfengwu improvedthreewayclusteringbasedonensemblestrategy AT jiachenfan improvedthreewayclusteringbasedonensemblestrategy AT pingxinwang improvedthreewayclusteringbasedonensemblestrategy |