I. Sarafis, A. Zalzala, und P. Trinder. In Proceedings of the 2002 Congress on Evolutionary Computation CEC2002, Seite 1238--1243. IEEE Academic Press, (2002)
Zusammenfassung
Clustering is a hard combinatorial problem and is defined as the unsupervised classification of patterns. The formation of clusters is based on the principle of maximizing the similarity between objects of the same cluster while simultaneously minimizing the similarity between objects belonging to distinct clusters. This paper presents a tool for database clustering using a rule-based genetic algorithm (RBCGA). RBCGA evolves individuals consisting of a fixed set of clustering rules, where each rule includes d non-binary intervals, one for each feature. The investigations attempt to alleviate certain drawbacks related to the classical minimization of square-error criterion by suggesting a flexible fitness function which takes into consideration, cluster asymmetry, density, coverage and homogeny.
%0 Conference Paper
%1 Sarafis02agenetic
%A Sarafis, I
%A Zalzala, Ams
%A Trinder, P W
%B In Proceedings of the 2002 Congress on Evolutionary Computation CEC2002
%D 2002
%I IEEE Academic Press
%K 2009 clustering seminar
%P 1238--1243
%T A Genetic Rule-Based Data Clustering Toolkit
%U http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.4429
%X Clustering is a hard combinatorial problem and is defined as the unsupervised classification of patterns. The formation of clusters is based on the principle of maximizing the similarity between objects of the same cluster while simultaneously minimizing the similarity between objects belonging to distinct clusters. This paper presents a tool for database clustering using a rule-based genetic algorithm (RBCGA). RBCGA evolves individuals consisting of a fixed set of clustering rules, where each rule includes d non-binary intervals, one for each feature. The investigations attempt to alleviate certain drawbacks related to the classical minimization of square-error criterion by suggesting a flexible fitness function which takes into consideration, cluster asymmetry, density, coverage and homogeny.
@inproceedings{Sarafis02agenetic,
abstract = {Clustering is a hard combinatorial problem and is defined as the unsupervised classification of patterns. The formation of clusters is based on the principle of maximizing the similarity between objects of the same cluster while simultaneously minimizing the similarity between objects belonging to distinct clusters. This paper presents a tool for database clustering using a rule-based genetic algorithm (RBCGA). RBCGA evolves individuals consisting of a fixed set of clustering rules, where each rule includes d non-binary intervals, one for each feature. The investigations attempt to alleviate certain drawbacks related to the classical minimization of square-error criterion by suggesting a flexible fitness function which takes into consideration, cluster asymmetry, density, coverage and homogeny.},
added-at = {2009-11-12T15:48:13.000+0100},
author = {Sarafis, I and Zalzala, Ams and Trinder, P W},
biburl = {https://www.bibsonomy.org/bibtex/22bdb486ab58f0d27d4863b272d39618f/k.e.},
booktitle = {In Proceedings of the 2002 Congress on Evolutionary Computation CEC2002},
description = {A Genetic Rule-Based Data Clustering Toolkit},
interhash = {079d2349e2ee56995e29fa3190e76a6c},
intrahash = {2bdb486ab58f0d27d4863b272d39618f},
keywords = {2009 clustering seminar},
pages = {1238--1243},
publisher = {IEEE Academic Press},
timestamp = {2009-11-12T15:48:13.000+0100},
title = {A Genetic Rule-Based Data Clustering Toolkit},
url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.4429},
year = 2002
}