eprintid: 1024
rev_number: 8
eprint_status: archive
dir: disk0/00/00/10/24
datestamp: 2011-12-05 10:30:11
lastmod: 2011-12-05 10:30:11
status_changed: 2011-12-05 10:30:11
type: article
metadata_visibility: show
creators_name: Patrinos, Panagiotis
creators_name: Alexandridis, Alex
creators_name: Ninos, Konstantinos
creators_name: Sarimveis, Haralambos
creators_id: panagiotis.patrinos@imtlucca.it
creators_id: 
creators_id: 
creators_id: 
title: Variable selection in nonlinear modeling based on RBF networks and evolutionary computation
ispublished: pub
subjects: QA
subjects: QA76
divisions: CSA
full_text_status: none
keywords: Variable selection; radial basis functions; neural networks; evolutionary computation; gas furnace data; Mackey glass data; quantitative structure activity relationship (QSAR)
abstract: In this paper a novel variable selection method based on Radial Basis Function (RBF) neural networks and genetic algorithms is presented. The fuzzy means algorithm is utilized as the training method for the RBF networks, due to its inherent speed, the deterministic approach of selecting the hidden node centers and the fact that it involves only a single tuning parameter. The trade-off between the accuracy and parsimony of the produced model is handled by using Final Prediction Error criterion, based on the RBF training and validation errors, as a fitness function of the proposed genetic algorithm. The tuning parameter required by the fuzzy means algorithm is treated as a free variable by the genetic algorithm. The proposed method was tested in benchmark data sets stemming from the scientific communities of time-series prediction and medicinal chemistry and produced promising results.
date: 2010
date_type: published
publication: International journal of neural systems
volume: 20
number: 5
publisher: World Scientific Publishing
pagerange: 365-379
id_number: 10.1142/S0129065710002474
refereed: TRUE
issn: 0129-0657
official_url: http://www.worldscinet.com/ijns/20/2005/S0129065710002474.html
citation:   Patrinos, Panagiotis and Alexandridis, Alex and Ninos, Konstantinos and Sarimveis, Haralambos  Variable selection in nonlinear modeling based on RBF networks and evolutionary computation.  International journal of neural systems, 20 (5).  pp. 365-379.  ISSN 0129-0657      (2010)