Observatorio de I+D+i UPM

Memorias de investigación
Research Publications in journals:
APPLICATION OF NEURAL NETWORKS FOR PREDICTIVE VARIABLES IN ENGINEERING
Year:2011
Research Areas
  • Artificial intelligence
Information
Abstract
This paper proposes a method in order to detect the importance of the input variables in multivariate analysis problems. When there is correlation among predictor variables, the importance of each input variable, when adding variables in the model, can be detected from the knowledge stored in Artificial Neural Network (NN) and it must be taken into account. Neural networks models have been used with the analysis of sensibility, these models predict more accurately the relationship between variables, and it is the way to find a set of forecasting variables in order to be included in the new prediction model. The obtained results have been applied in a system to forecast the volume of wood for a tree, and to detect relationships between input and output variables
International
Si
JCR
No
Title
Journal of Mathematics and System Science
ISBN
2159-5291
Impact factor JCR
Impact info
Volume
1
Journal number
From page
12
To page
22
Month
MAYO
Ranking
Participants
  • Autor: Ana Martinez Blanco (UPM)
  • Autor: Angel Luis Castellanos Peñuela (UPM)
  • Autor: Arcadio Sotto (Urjc)
Research Group, Departaments and Institutes related
  • Creador: Grupo de Investigación: Grupo de Computación Natural
  • Departamento: Ciencias Básicas Aplicadas a la Ingeniería Forestal
S2i 2019 Observatorio de investigación @ UPM con la colaboración del Consejo Social UPM
Cofinanciación del MINECO en el marco del Programa INNCIDE 2011 (OTR-2011-0236)
Cofinanciación del MINECO en el marco del Programa INNPACTO (IPT-020000-2010-22)