Unsupervised Connectionist Algorithms for Clustering an environmental data set : a comparison
Identifieur interne : 002595 ( Crin/Curation ); précédent : 002594; suivant : 002596Unsupervised Connectionist Algorithms for Clustering an environmental data set : a comparison
Auteurs : Laurent Bougrain ; Frédéric AlexandreSource :
- Neurocomputing ; 1999.
English descriptors
Abstract
Various unsupervised algorithms for vector quantization can be found in the literature. Being based on different assumptions, they do not all yield exactly the same results on the same problem. To better understand these differences, this article presents an evaluation of some unsupervised neural networks, considered among the most useful for quantization, in the context of a real-world problem : radioelectric wave propagation. Radio wave propagation is highly dependent upon environmental characteristics (e.g. those of the city, country, mountains, etc.). Within the framework of a cell net planning its radiocommunication strategy, we are interested in determining a set of environmental classes, sufficiently homogeneous, to which a specific prediction model of radio electrical field can be applied. Of particular interest are techniques that allow improved analysis of results. Firstly, Mahalanobis' distance, taking data correlation into account, is used to make assignments. Secondly studies of class dispersion and homogeneity, using both a data structure mapping representation and statistical analysis, emphasize the importance of the global properties of each algorithm. In conclusion, we discuss the advantages and disadvantages of each method on real problems.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: Pour aller vers cette notice dans l'étape Curation :002595
Links to Exploration step
CRIN:bougrain99oLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="519">Unsupervised Connectionist Algorithms for Clustering an environmental data set : a comparison</title></titleStmt><publicationStmt><idno type="RBID">CRIN:bougrain99o</idno><date when="1999" year="1999">1999</date><idno type="wicri:Area/Crin/Corpus">002595</idno><idno type="wicri:Area/Crin/Curation">002595</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">002595</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Unsupervised Connectionist Algorithms for Clustering an environmental data set : a comparison</title><author><name sortKey="Bougrain, Laurent" sort="Bougrain, Laurent" uniqKey="Bougrain L" first="Laurent" last="Bougrain">Laurent Bougrain</name></author><author><name sortKey="Alexandre, Frederic" sort="Alexandre, Frederic" uniqKey="Alexandre F" first="Frédéric" last="Alexandre">Frédéric Alexandre</name></author></analytic><series><title level="j">Neurocomputing</title><imprint><date when="1999" type="published">1999</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>neural networks</term><term>radiocommunication</term><term>unsupervised learning</term><term>vector quantization</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="4014">Various unsupervised algorithms for vector quantization can be found in the literature. Being based on different assumptions, they do not all yield exactly the same results on the same problem. To better understand these differences, this article presents an evaluation of some unsupervised neural networks, considered among the most useful for quantization, in the context of a real-world problem : radioelectric wave propagation. Radio wave propagation is highly dependent upon environmental characteristics (e.g. those of the city, country, mountains, etc.). Within the framework of a cell net planning its radiocommunication strategy, we are interested in determining a set of environmental classes, sufficiently homogeneous, to which a specific prediction model of radio electrical field can be applied. Of particular interest are techniques that allow improved analysis of results. Firstly, Mahalanobis' distance, taking data correlation into account, is used to make assignments. Secondly studies of class dispersion and homogeneity, using both a data structure mapping representation and statistical analysis, emphasize the importance of the global properties of each algorithm. In conclusion, we discuss the advantages and disadvantages of each method on real problems.</div></front></TEI><BibTex type="article"><ref>bougrain99o</ref><crinnumber>99-R-265</crinnumber><category>1</category><equipe>CORTEX</equipe><author><e>Bougrain, Laurent</e><e>Alexandre, Frédéric</e></author><title>Unsupervised Connectionist Algorithms for Clustering an environmental data set : a comparison</title><journal>Neurocomputing</journal><year>1999</year><volume>28</volume><number>1-3</number><pages>177-189</pages><month>Oct</month><keywords><e>neural networks</e><e>unsupervised learning</e><e>vector quantization</e><e>radiocommunication</e></keywords><abstract>Various unsupervised algorithms for vector quantization can be found in the literature. Being based on different assumptions, they do not all yield exactly the same results on the same problem. To better understand these differences, this article presents an evaluation of some unsupervised neural networks, considered among the most useful for quantization, in the context of a real-world problem : radioelectric wave propagation. Radio wave propagation is highly dependent upon environmental characteristics (e.g. those of the city, country, mountains, etc.). Within the framework of a cell net planning its radiocommunication strategy, we are interested in determining a set of environmental classes, sufficiently homogeneous, to which a specific prediction model of radio electrical field can be applied. Of particular interest are techniques that allow improved analysis of results. Firstly, Mahalanobis' distance, taking data correlation into account, is used to make assignments. Secondly studies of class dispersion and homogeneity, using both a data structure mapping representation and statistical analysis, emphasize the importance of the global properties of each algorithm. In conclusion, we discuss the advantages and disadvantages of each method on real problems.</abstract></BibTex></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Crin/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 002595 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Crin/Curation/biblio.hfd -nk 002595 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= Crin
|étape= Curation
|type= RBID
|clé= CRIN:bougrain99o
|texte= Unsupervised Connectionist Algorithms for Clustering an environmental data set : a comparison
}}
| This area was generated with Dilib version V0.6.33. |  |