Application of kohonen neural network and rough approximation for overlapping clusters optimization

In this paper, the Kohonen Self Organizing Map one of the most popular tools in the exploratory phase of pattern recognition is proposed for clustering the input data. Recently researchers found that to have precise and optimized clustering operations and also to capture the ambiguity that comes fro...

Full description

Bibliographic Details
Main Authors: Mohebi, E., Md. Sap, Mohd. Noor
Format: Article
Language:English
Published: Penerbit UTM Press 2008
Subjects:
Online Access:http://eprints.utm.my/10702/
http://eprints.utm.my/10702/1/MNMSap2008_ApplicationOfKohonenNeuralNetwork.pdf
_version_ 1848892155527954432
author Mohebi, E.
Md. Sap, Mohd. Noor
author_facet Mohebi, E.
Md. Sap, Mohd. Noor
author_sort Mohebi, E.
building UTeM Institutional Repository
collection Online Access
description In this paper, the Kohonen Self Organizing Map one of the most popular tools in the exploratory phase of pattern recognition is proposed for clustering the input data. Recently researchers found that to have precise and optimized clustering operations and also to capture the ambiguity that comes from the data sets, it is not necessary to have crisp boundaries in some clustering operation. To overcome the mentioned ambiguity, two variation of cluster approximation (upper and lower) have been applied by Rough set theory. In the first stage the SOM is employed to produce the prototypes then, in the second stage the rough set is applied on the output grid of SOM to detect the ambiguity of SOM clustering. One of the most general optimization techniques (Simulated Annealing) have been adopted to assign the overlapped data to true clusters they belong to by minimizing the uncertainty criteria. Experiments show that the proposed two-level algorithm is more accurate and generates fewer errors as compared with crisp clustering operations.
first_indexed 2025-11-15T21:09:22Z
format Article
id utm-10702
institution Universiti Teknologi Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T21:09:22Z
publishDate 2008
publisher Penerbit UTM Press
recordtype eprints
repository_type Digital Repository
spelling utm-107022017-11-01T04:17:23Z http://eprints.utm.my/10702/ Application of kohonen neural network and rough approximation for overlapping clusters optimization Mohebi, E. Md. Sap, Mohd. Noor QA75 Electronic computers. Computer science In this paper, the Kohonen Self Organizing Map one of the most popular tools in the exploratory phase of pattern recognition is proposed for clustering the input data. Recently researchers found that to have precise and optimized clustering operations and also to capture the ambiguity that comes from the data sets, it is not necessary to have crisp boundaries in some clustering operation. To overcome the mentioned ambiguity, two variation of cluster approximation (upper and lower) have been applied by Rough set theory. In the first stage the SOM is employed to produce the prototypes then, in the second stage the rough set is applied on the output grid of SOM to detect the ambiguity of SOM clustering. One of the most general optimization techniques (Simulated Annealing) have been adopted to assign the overlapped data to true clusters they belong to by minimizing the uncertainty criteria. Experiments show that the proposed two-level algorithm is more accurate and generates fewer errors as compared with crisp clustering operations. Penerbit UTM Press 2008-12 Article PeerReviewed application/pdf en http://eprints.utm.my/10702/1/MNMSap2008_ApplicationOfKohonenNeuralNetwork.pdf Mohebi, E. and Md. Sap, Mohd. Noor (2008) Application of kohonen neural network and rough approximation for overlapping clusters optimization. Jurnal Teknologi Maklumat, 20 (4). pp. 17-31. ISSN 0128-3790
spellingShingle QA75 Electronic computers. Computer science
Mohebi, E.
Md. Sap, Mohd. Noor
Application of kohonen neural network and rough approximation for overlapping clusters optimization
title Application of kohonen neural network and rough approximation for overlapping clusters optimization
title_full Application of kohonen neural network and rough approximation for overlapping clusters optimization
title_fullStr Application of kohonen neural network and rough approximation for overlapping clusters optimization
title_full_unstemmed Application of kohonen neural network and rough approximation for overlapping clusters optimization
title_short Application of kohonen neural network and rough approximation for overlapping clusters optimization
title_sort application of kohonen neural network and rough approximation for overlapping clusters optimization
topic QA75 Electronic computers. Computer science
url http://eprints.utm.my/10702/
http://eprints.utm.my/10702/1/MNMSap2008_ApplicationOfKohonenNeuralNetwork.pdf