A Novel Linguistic Relational Fuzzy C-Means

In real-world applications, sometimes there are uncertainties in the data sets whether from the collection process or from the natural languages. Moreover, the data may come in the form of fuzzy relation. To analyze data, one might use one of popular tools, i.e., a clustering method. There are sever...

Full description

Saved in:
Bibliographic Details
Main Authors: Peerawich Phaknonkul, Sansanee Auephanwiriyakul, Nipon Theera-Umpon
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11003957/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850255684617109504
author Peerawich Phaknonkul
Sansanee Auephanwiriyakul
Nipon Theera-Umpon
author_facet Peerawich Phaknonkul
Sansanee Auephanwiriyakul
Nipon Theera-Umpon
author_sort Peerawich Phaknonkul
collection DOAJ
description In real-world applications, sometimes there are uncertainties in the data sets whether from the collection process or from the natural languages. Moreover, the data may come in the form of fuzzy relation. To analyze data, one might use one of popular tools, i.e., a clustering method. There are several types of clustering including clustering on information from objects themselves or clustering on a relational data. Currently, there are few researches on a fuzzy data clustering and a fuzzy relational data clustering. However, those algorithms are either defuzzifying the data or the relation of the data before implementing the clustering Therefore, in this paper, we develop a linguistic relational fuzzy C-means (LRFCM) that works with fuzzy relation of vectors of fuzzy numbers directly. The algorithm is an extension of the regular relational fuzzy C-means (RFCM). The proposed algorithm does not defuzzify fuzzy attributes beforehand. We found that the results from the LRFCM are similar to that from the RFCM. However, the results from the LRFCM can provide information that contains all the uncertainties from the inputs while the RFCM cannot. We also compare the results with the fuzzy C-means clustering. These comparisons show that the LRFCM behaves the same way as the RFCM and the FCM in partitioning the input space into clusters.
format Article
id doaj-art-593060a8d2144b488b969ddbbccb9b19
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-593060a8d2144b488b969ddbbccb9b192025-08-20T01:56:48ZengIEEEIEEE Access2169-35362025-01-0113893328934210.1109/ACCESS.2025.357001411003957A Novel Linguistic Relational Fuzzy C-MeansPeerawich Phaknonkul0https://orcid.org/0009-0004-4979-9180Sansanee Auephanwiriyakul1https://orcid.org/0000-0002-6639-7165Nipon Theera-Umpon2Department of Computer Engineering, Faculty of Engineering, Chiang Mai University, Chiang Mai, ThailandDepartment of Computer Engineering, Faculty of Engineering, Chiang Mai University, Chiang Mai, ThailandBiomedical Engineering and Innovation Research Center, Biomedical Engineering Institute, Chiang Mai University, Chiang Mai, ThailandIn real-world applications, sometimes there are uncertainties in the data sets whether from the collection process or from the natural languages. Moreover, the data may come in the form of fuzzy relation. To analyze data, one might use one of popular tools, i.e., a clustering method. There are several types of clustering including clustering on information from objects themselves or clustering on a relational data. Currently, there are few researches on a fuzzy data clustering and a fuzzy relational data clustering. However, those algorithms are either defuzzifying the data or the relation of the data before implementing the clustering Therefore, in this paper, we develop a linguistic relational fuzzy C-means (LRFCM) that works with fuzzy relation of vectors of fuzzy numbers directly. The algorithm is an extension of the regular relational fuzzy C-means (RFCM). The proposed algorithm does not defuzzify fuzzy attributes beforehand. We found that the results from the LRFCM are similar to that from the RFCM. However, the results from the LRFCM can provide information that contains all the uncertainties from the inputs while the RFCM cannot. We also compare the results with the fuzzy C-means clustering. These comparisons show that the LRFCM behaves the same way as the RFCM and the FCM in partitioning the input space into clusters.https://ieeexplore.ieee.org/document/11003957/Relational fuzzy C-meanslinguistic algorithmlinguistic vectortype-2 fuzzy vectorlinguistic clustering
spellingShingle Peerawich Phaknonkul
Sansanee Auephanwiriyakul
Nipon Theera-Umpon
A Novel Linguistic Relational Fuzzy C-Means
IEEE Access
Relational fuzzy C-means
linguistic algorithm
linguistic vector
type-2 fuzzy vector
linguistic clustering
title A Novel Linguistic Relational Fuzzy C-Means
title_full A Novel Linguistic Relational Fuzzy C-Means
title_fullStr A Novel Linguistic Relational Fuzzy C-Means
title_full_unstemmed A Novel Linguistic Relational Fuzzy C-Means
title_short A Novel Linguistic Relational Fuzzy C-Means
title_sort novel linguistic relational fuzzy c means
topic Relational fuzzy C-means
linguistic algorithm
linguistic vector
type-2 fuzzy vector
linguistic clustering
url https://ieeexplore.ieee.org/document/11003957/
work_keys_str_mv AT peerawichphaknonkul anovellinguisticrelationalfuzzycmeans
AT sansaneeauephanwiriyakul anovellinguisticrelationalfuzzycmeans
AT nipontheeraumpon anovellinguisticrelationalfuzzycmeans
AT peerawichphaknonkul novellinguisticrelationalfuzzycmeans
AT sansaneeauephanwiriyakul novellinguisticrelationalfuzzycmeans
AT nipontheeraumpon novellinguisticrelationalfuzzycmeans