A New Approach to Define the Number of Clusters for Partitional Clustering Algorithms
Data clustering consists of grouping similar objects according to some characteristic. In the literature, there are several clustering algorithms, among which stands out the Fuzzy C-Means (FCM), one of the most discussed algorithms, being used in different applications. Although it is a...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Islamic Azad University, Bandar Abbas Branch
2024-05-01
|
| Series: | Transactions on Fuzzy Sets and Systems |
| Subjects: | |
| Online Access: | https://sanad.iau.ir/journal/tfss/Article/977417 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846172729795936256 |
|---|---|
| author | Huliane Silva Benjamın Ren Callejas Bedregal Anne Canuto Thiago Batista Ronildo Moura |
| author_facet | Huliane Silva Benjamın Ren Callejas Bedregal Anne Canuto Thiago Batista Ronildo Moura |
| author_sort | Huliane Silva |
| collection | DOAJ |
| description | Data clustering consists of grouping similar objects according to some characteristic. In the literature, there are several clustering algorithms, among which stands out the Fuzzy C-Means (FCM), one of the most discussed algorithms, being used in different applications. Although it is a simple and easy to manipulate clustering method, the FCM requires as its initial parameter the number of clusters. Usually, this information is unknown, beforehand and this becomes a relevant problem in the data cluster analysis process. In this context, this work proposes a new methodology to determine the number of clusters of partitional algorithms, using subsets of the original data in order to define the number of clusters. This new methodology, is intended to reduce the side effects of the cluster definition phase, possibly making the processing time faster and decreasing the computational cost. To evaluate the proposed methodology, different cluster validation indices will be used to evaluate the quality of the clusters obtained by the FCM algorithms and some of its variants, when applied to different databases. Through the empirical analysis, we can conclude that the results obtained in this article are promising, both from an experimental point of view and from a statistical point of view. |
| format | Article |
| id | doaj-art-39cb639f186442ebaf6ce4ee271521fa |
| institution | Kabale University |
| issn | 2821-0131 |
| language | English |
| publishDate | 2024-05-01 |
| publisher | Islamic Azad University, Bandar Abbas Branch |
| record_format | Article |
| series | Transactions on Fuzzy Sets and Systems |
| spelling | doaj-art-39cb639f186442ebaf6ce4ee271521fa2024-11-09T06:36:33ZengIslamic Azad University, Bandar Abbas BranchTransactions on Fuzzy Sets and Systems2821-01312024-05-01316787A New Approach to Define the Number of Clusters for Partitional Clustering AlgorithmsHuliane Silva0Benjamın Ren Callejas Bedregal1Anne Canuto2Thiago Batista3Ronildo Moura4Departamento de Engenharias e Tecnologias, Universidade Federal Rural do Semi-rido, Pau dos Ferros, Brasil.Departamento de Inform´atica e Matem´atica Aplicada, Universidade Federal do Rio Grande do Norte, Natal, Brasil.Departamento de Inform´atica e Matem´atica Aplicada, Universidade Federal do Rio Grande do Norte, Natal, Brasil.Departamento de Inform´atica e Matem´atica Aplicada, Universidade Federal do Rio Grande do Norte, Natal, Brasil.Departamento de Inform´atica e Matem´atica Aplicada, Universidade Federal do Rio Grande do Norte, Natal, Brasil.Data clustering consists of grouping similar objects according to some characteristic. In the literature, there are several clustering algorithms, among which stands out the Fuzzy C-Means (FCM), one of the most discussed algorithms, being used in different applications. Although it is a simple and easy to manipulate clustering method, the FCM requires as its initial parameter the number of clusters. Usually, this information is unknown, beforehand and this becomes a relevant problem in the data cluster analysis process. In this context, this work proposes a new methodology to determine the number of clusters of partitional algorithms, using subsets of the original data in order to define the number of clusters. This new methodology, is intended to reduce the side effects of the cluster definition phase, possibly making the processing time faster and decreasing the computational cost. To evaluate the proposed methodology, different cluster validation indices will be used to evaluate the quality of the clusters obtained by the FCM algorithms and some of its variants, when applied to different databases. Through the empirical analysis, we can conclude that the results obtained in this article are promising, both from an experimental point of view and from a statistical point of view.https://sanad.iau.ir/journal/tfss/Article/977417partitional clustering algorithms clustering fuzzy number of cluster |
| spellingShingle | Huliane Silva Benjamın Ren Callejas Bedregal Anne Canuto Thiago Batista Ronildo Moura A New Approach to Define the Number of Clusters for Partitional Clustering Algorithms Transactions on Fuzzy Sets and Systems partitional clustering algorithms clustering fuzzy number of cluster |
| title | A New Approach to Define the Number of Clusters for Partitional Clustering Algorithms |
| title_full | A New Approach to Define the Number of Clusters for Partitional Clustering Algorithms |
| title_fullStr | A New Approach to Define the Number of Clusters for Partitional Clustering Algorithms |
| title_full_unstemmed | A New Approach to Define the Number of Clusters for Partitional Clustering Algorithms |
| title_short | A New Approach to Define the Number of Clusters for Partitional Clustering Algorithms |
| title_sort | a new approach to define the number of clusters for partitional clustering algorithms |
| topic | partitional clustering algorithms clustering fuzzy number of cluster |
| url | https://sanad.iau.ir/journal/tfss/Article/977417 |
| work_keys_str_mv | AT hulianesilva anewapproachtodefinethenumberofclustersforpartitionalclusteringalgorithms AT benjamınrencallejasbedregal anewapproachtodefinethenumberofclustersforpartitionalclusteringalgorithms AT annecanuto anewapproachtodefinethenumberofclustersforpartitionalclusteringalgorithms AT thiagobatista anewapproachtodefinethenumberofclustersforpartitionalclusteringalgorithms AT ronildomoura anewapproachtodefinethenumberofclustersforpartitionalclusteringalgorithms |