@prefix prodottidellaricerca: . @prefix istituto: . @prefix prodotto: . istituto:CDS057 prodottidellaricerca:prodotto prodotto:ID35172 . @prefix rdf: . @prefix retescientifica: . prodotto:ID35172 rdf:type retescientifica:ProdottoDellaRicerca , prodotto:TIPO1101 . @prefix rdfs: . prodotto:ID35172 rdfs:label "Dynamic clusters recognition with multiple self-organization maps (Articolo in rivista)"@en . @prefix xsd: . @prefix pubblicazioni: . prodotto:ID35172 pubblicazioni:anno "2002-01-01T00:00:00+01:00"^^xsd:gYear . @prefix skos: . prodotto:ID35172 skos:altLabel "
Distante C., Siciliano P., Persaud K. (2002)
Dynamic clusters recognition with multiple self-organization maps
in Pattern analysis and applications (Print)
"^^rdf:HTML ; pubblicazioni:autori "Distante C., Siciliano P., Persaud K."^^xsd:string ; pubblicazioni:paginaInizio "306"^^xsd:string ; pubblicazioni:paginaFine "315"^^xsd:string ; pubblicazioni:numeroVolume "5"^^xsd:string . @prefix ns9: . prodotto:ID35172 pubblicazioni:rivista ns9:ID176601 ; skos:note "ISI Web of Science (WOS)"^^xsd:string ; pubblicazioni:titolo "Dynamic clusters recognition with multiple self-organization maps"^^xsd:string ; prodottidellaricerca:abstract "A neural architecture, based on several self-organising maps, is presented \nwhich counteracts the parameter drift problem for an array of conducting \npolymer gas sensors when used for odour sensing. The neural architecture \nis named mSom, where m is the number of odours to be recognised, and is \nmainly constituted of m maps; each one approximates the statistical \ndistribution of a given odour. Competition occurs both within each map and \nbetween maps for the selection of the minimum map distance in the \neuclidean space. The network (mSom) is able to adapt itself to new changes\nof the input probability distribution by repetitive self-training \nprocesses based on its experience. This architecture has been tested and \ncompared with other neural architectures, such as RBF and Fuzzy ARTMAP. \nThe network shows long-term stable behaviour, and is completely autonomous \nduring the testing phase, where re-adaptation of the neurons is needed due \nto the changes of the input probability distribution of the given data \nset." ; prodottidellaricerca:prodottoDi istituto:CDS057 . ns9:ID176601 pubblicazioni:rivistaDi prodotto:ID35172 .