The performance of k-means clustering method based on robust principal components
The k-means clustering method is the most widely used method to group n observations into k clusters. It is now evident that clustering results can be improved by applying classical principal component analysis (PCA) with the k-means clustering algorithm. However, the clustering results of PCA with...
Saved in:
Main Authors: | , , |
---|---|
Format: | Article |
Published: |
Pushpa Publishing House
2018
|
Online Access: | http://psasir.upm.edu.my/id/eprint/74236/ http://www.pphmj.com/abstract/11654.htm |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Universiti Putra Malaysia |
id |
my.upm.eprints.74236 |
---|---|
record_format |
eprints |
spelling |
my.upm.eprints.742362024-05-16T07:11:30Z http://psasir.upm.edu.my/id/eprint/74236/ The performance of k-means clustering method based on robust principal components Kadom, Ahmed Midi, Habshah Rana, Sohel The k-means clustering method is the most widely used method to group n observations into k clusters. It is now evident that clustering results can be improved by applying classical principal component analysis (PCA) with the k-means clustering algorithm. However, the clustering results of PCA with k-means are adversely affected by the presence of outliers in a data set. To remedy this problem, we proposed to integrate robust principal component analysis (RPCA) with the k-means algorithm. Simulation study and real examples are carried out to compare the performance of the classical k-means, k-means based on PCA and k-means based on RPCA. The findings indicate that the k-means based on RPCA outperforms the other two methods. Pushpa Publishing House 2018 Article PeerReviewed Kadom, Ahmed and Midi, Habshah and Rana, Sohel (2018) The performance of k-means clustering method based on robust principal components. Far East Journal of Mathematical Sciences (FJMS), 103 (11). 1757 - 1767. ISSN 0972-0871 http://www.pphmj.com/abstract/11654.htm 10.17654/ms103111757 |
institution |
Universiti Putra Malaysia |
building |
UPM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Putra Malaysia |
content_source |
UPM Institutional Repository |
url_provider |
http://psasir.upm.edu.my/ |
description |
The k-means clustering method is the most widely used method to group n observations into k clusters. It is now evident that clustering results can be improved by applying classical principal component analysis (PCA) with the k-means clustering algorithm. However, the clustering results of PCA with k-means are adversely affected by the presence of outliers in a data set. To remedy this problem, we proposed to integrate robust principal component analysis (RPCA) with the k-means algorithm. Simulation study and real examples are carried out to compare the performance of the classical k-means, k-means based on PCA and k-means based on RPCA. The findings indicate that the k-means based on RPCA outperforms the other two methods. |
format |
Article |
author |
Kadom, Ahmed Midi, Habshah Rana, Sohel |
spellingShingle |
Kadom, Ahmed Midi, Habshah Rana, Sohel The performance of k-means clustering method based on robust principal components |
author_facet |
Kadom, Ahmed Midi, Habshah Rana, Sohel |
author_sort |
Kadom, Ahmed |
title |
The performance of k-means clustering method based on robust principal components |
title_short |
The performance of k-means clustering method based on robust principal components |
title_full |
The performance of k-means clustering method based on robust principal components |
title_fullStr |
The performance of k-means clustering method based on robust principal components |
title_full_unstemmed |
The performance of k-means clustering method based on robust principal components |
title_sort |
performance of k-means clustering method based on robust principal components |
publisher |
Pushpa Publishing House |
publishDate |
2018 |
url |
http://psasir.upm.edu.my/id/eprint/74236/ http://www.pphmj.com/abstract/11654.htm |
_version_ |
1800093756652781568 |