2014
DOI: 10.5121/ijdkp.2014.4502
|View full text |Cite
|
Sign up to set email alerts
|

Experiments on Hypothesis "Fuzzy K-Means is Better than K-Means for Clustering"

Abstract: Clustering is one of the data mining techniques that have been around to discover business intelligence by

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
15
0

Year Published

2015
2015
2023
2023

Publication Types

Select...
6
2

Relationship

0
8

Authors

Journals

citations
Cited by 21 publications
(18 citation statements)
references
References 12 publications
1
15
0
Order By: Relevance
“…FCM is an algorithm based on more iterative fuzzy calculations, so its execution was found comparatively higher as it is expected. Similar results were reported by Panda et al (2012) for Iris, Wine and Lens datasets; by Jipkate & Gohokar (2012) for segmentation of images; by Ghosh & Dubey (2013) for Iris dataset; by Bora & Gupta (2014) for Iris dataset; by Sivarathri & Govardhan (2014) for diabetes data; and by Madhukumar & Santhiyakumari (2015) for brain MR images data.…”
Section: Discussionsupporting
confidence: 74%
See 1 more Smart Citation
“…FCM is an algorithm based on more iterative fuzzy calculations, so its execution was found comparatively higher as it is expected. Similar results were reported by Panda et al (2012) for Iris, Wine and Lens datasets; by Jipkate & Gohokar (2012) for segmentation of images; by Ghosh & Dubey (2013) for Iris dataset; by Bora & Gupta (2014) for Iris dataset; by Sivarathri & Govardhan (2014) for diabetes data; and by Madhukumar & Santhiyakumari (2015) for brain MR images data.…”
Section: Discussionsupporting
confidence: 74%
“…Testing the proposed approaches on real data with different ellipsoidal shapes of clusters may be helpful for a precise decision between the algorithms. Sivarathri & Govardhan (2014) revealed that FCM is better than KM in term of accuracy of clusters on the diabetes dataset obtained from the UCI repository. However, in our study, neither KM nor FCM were successful to find the concave and other kind of arbitrary shaped clusters when they are not well separated.…”
Section: Discussionmentioning
confidence: 99%
“…FCM is widely applied as the clustering and classification method in many fields such as data mining, image processing, and bioinformatics. Research often compares K-means, FCM, and other partitive clustering algorithms in data classification (see, eg, the papers by Gosh and Dubey, 14 Velmurugan and Santhanam, 15 Yin et al, 16 and Sivarathri and Govardhan, 17 ). Results obtained on different datasets show that although FCM requires necessarily more computation time than K-Means clustering, it produces better results than K-means in terms of accuracy of clusters.…”
Section: The Efcm Algorithmmentioning
confidence: 99%
“…Clustering is an unsupervised learning method decomposing a given set of objects into subgroups (i.e. clusters) based on object similarities [ 9]. The objective is to divide the data set in such a way that objects belonging to the same cluster are as similar as possible whereas objects belonging to different clusters are as dissimilar as possible [10].…”
Section: Clusteringmentioning
confidence: 99%