Improved normalization and standardization techniques for higher purity in K-means clustering

Clustering is basically one of the major sources of primary data mining tools, which make researchers understand the natural grouping of attributes in datasets. Clustering is an unsupervised classification method with aim of partitioning, where objects in the same cluster are similar, and objects be...

Full description

Bibliographic Details
Main Authors: Dalatu, Paul Inuwa, Fitrianto, Anwar, Mustapha, Aida
Format: Article
Language:English
Published: Pushpa Publishing House 2016
Subjects:
Online Access:http://psasir.upm.edu.my/id/eprint/54519/
http://psasir.upm.edu.my/id/eprint/54519/1/Improved%20normalization%20and%20standardization%20techniques%20for%20higher%20purity%20in%20K-means%20clustering.pdf
_version_ 1848852567651516416
author Dalatu, Paul Inuwa
Fitrianto, Anwar
Mustapha, Aida
author_facet Dalatu, Paul Inuwa
Fitrianto, Anwar
Mustapha, Aida
author_sort Dalatu, Paul Inuwa
building UPM Institutional Repository
collection Online Access
description Clustering is basically one of the major sources of primary data mining tools, which make researchers understand the natural grouping of attributes in datasets. Clustering is an unsupervised classification method with aim of partitioning, where objects in the same cluster are similar, and objects belong to different clusters vary significantly, with respect to their attributes. The K-means algorithm is a famous and fast technique in non-hierarchical cluster algorithms. Based on its simplicity, the K-means algorithm has been used in many fields. This paper proposes improved normalization and standardization techniques for higher purity in K-means clustering experimented with benchmark datasets from UCI machine learning repository and it was found that all the proposed techniques’ performance was much higher compared to the conventional K-means and the three classic transformations, and it is evidently shown by purity and Rand index accuracy results.
first_indexed 2025-11-15T10:40:08Z
format Article
id upm-54519
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T10:40:08Z
publishDate 2016
publisher Pushpa Publishing House
recordtype eprints
repository_type Digital Repository
spelling upm-545192018-03-27T01:36:34Z http://psasir.upm.edu.my/id/eprint/54519/ Improved normalization and standardization techniques for higher purity in K-means clustering Dalatu, Paul Inuwa Fitrianto, Anwar Mustapha, Aida Clustering is basically one of the major sources of primary data mining tools, which make researchers understand the natural grouping of attributes in datasets. Clustering is an unsupervised classification method with aim of partitioning, where objects in the same cluster are similar, and objects belong to different clusters vary significantly, with respect to their attributes. The K-means algorithm is a famous and fast technique in non-hierarchical cluster algorithms. Based on its simplicity, the K-means algorithm has been used in many fields. This paper proposes improved normalization and standardization techniques for higher purity in K-means clustering experimented with benchmark datasets from UCI machine learning repository and it was found that all the proposed techniques’ performance was much higher compared to the conventional K-means and the three classic transformations, and it is evidently shown by purity and Rand index accuracy results. Pushpa Publishing House 2016-09 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/54519/1/Improved%20normalization%20and%20standardization%20techniques%20for%20higher%20purity%20in%20K-means%20clustering.pdf Dalatu, Paul Inuwa and Fitrianto, Anwar and Mustapha, Aida (2016) Improved normalization and standardization techniques for higher purity in K-means clustering. Far East Journal of Mathematical Sciences, 100 (6). pp. 859-871. ISSN 0972-0871 http://www.pphmj.com/abstract/10134.htm Normalization; Standardization; K-means algorithm; Clustering; Purity; Rand index 10.17654/MS100060859
spellingShingle Normalization; Standardization; K-means algorithm; Clustering; Purity; Rand index
Dalatu, Paul Inuwa
Fitrianto, Anwar
Mustapha, Aida
Improved normalization and standardization techniques for higher purity in K-means clustering
title Improved normalization and standardization techniques for higher purity in K-means clustering
title_full Improved normalization and standardization techniques for higher purity in K-means clustering
title_fullStr Improved normalization and standardization techniques for higher purity in K-means clustering
title_full_unstemmed Improved normalization and standardization techniques for higher purity in K-means clustering
title_short Improved normalization and standardization techniques for higher purity in K-means clustering
title_sort improved normalization and standardization techniques for higher purity in k-means clustering
topic Normalization; Standardization; K-means algorithm; Clustering; Purity; Rand index
url http://psasir.upm.edu.my/id/eprint/54519/
http://psasir.upm.edu.my/id/eprint/54519/
http://psasir.upm.edu.my/id/eprint/54519/
http://psasir.upm.edu.my/id/eprint/54519/1/Improved%20normalization%20and%20standardization%20techniques%20for%20higher%20purity%20in%20K-means%20clustering.pdf