Odontological patients clustering based on art2 neural network

This work presents the application of Artificial Neural Networks, in particular the ART2, for the customer clustering of a dentistry room. The input data used in the application is based on the odontological anamn esis that is a form with a questionnaire applied about the professional to identify th...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Thiry, Marcello, Borges, Paulo Sérgio da Silva, Soares, Andrey
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2001
Materias:
Ciencias Informáticas
Clustering
Odontología
ARTIFICIAL INTELLIGENCE
Neural nets
Anamnesis
Adaptative Resonance Theory
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/23381
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-23381
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Clustering
Odontología
ARTIFICIAL INTELLIGENCE
Neural nets
Anamnesis
Adaptative Resonance Theory
spellingShingle Ciencias Informáticas
Clustering
Odontología
ARTIFICIAL INTELLIGENCE
Neural nets
Anamnesis
Adaptative Resonance Theory
Thiry, Marcello
Borges, Paulo Sérgio da Silva
Soares, Andrey
Odontological patients clustering based on art2 neural network
topic_facet Ciencias Informáticas
Clustering
Odontología
ARTIFICIAL INTELLIGENCE
Neural nets
Anamnesis
Adaptative Resonance Theory
description This work presents the application of Artificial Neural Networks, in particular the ART2, for the customer clustering of a dentistry room. The input data used in the application is based on the odontological anamn esis that is a form with a questionnaire applied about the professional to identify the customer case history. The three proposed customer clustering (good, medium, bad) were created with basis on the buccal hygiene care and the similar habits among the cu stomers. The network is trained using non -supervised learning that can be fast or slow learning. Each input data line is formed by the number of interviewed customers (rows) and by the answered questions (columns). However, the first step was to transform the answers into binary cells.
format Objeto de conferencia
Objeto de conferencia
author Thiry, Marcello
Borges, Paulo Sérgio da Silva
Soares, Andrey
author_facet Thiry, Marcello
Borges, Paulo Sérgio da Silva
Soares, Andrey
author_sort Thiry, Marcello
title Odontological patients clustering based on art2 neural network
title_short Odontological patients clustering based on art2 neural network
title_full Odontological patients clustering based on art2 neural network
title_fullStr Odontological patients clustering based on art2 neural network
title_full_unstemmed Odontological patients clustering based on art2 neural network
title_sort odontological patients clustering based on art2 neural network
publishDate 2001
url http://sedici.unlp.edu.ar/handle/10915/23381
work_keys_str_mv AT thirymarcello odontologicalpatientsclusteringbasedonart2neuralnetwork
AT borgespaulosergiodasilva odontologicalpatientsclusteringbasedonart2neuralnetwork
AT soaresandrey odontologicalpatientsclusteringbasedonart2neuralnetwork
bdutipo_str Repositorios
_version_ 1764820465779474434

Ejemplares similares