ANVAS

Artificial neural variables adaptation system for descriptor selection

Paolo Mazzatorta, Marjan Vračko, Emilio Benfenati

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

A new algorithm model-oriented for variable selection is presented in this study. It is based on the combination of genetic algorithms (GA) for hyperspace exploration, and counterpropagation artificial neural network (CP ANN) for deriving the fitness score. The proposed method performed very well on both well defined synthetic data sets and real academic data sets.

Original languageEnglish
Pages (from-to)335-346
Number of pages12
JournalJournal of Computer-Aided Molecular Design
Volume17
Issue number5-6
DOIs
Publication statusPublished - May 2003

Fingerprint

hyperspaces
fitness
genetic algorithms
Genetic algorithms
Neural networks
Datasets

Keywords

  • Counterpropagation
  • Genetic algorithm
  • Neural networks
  • QSAR
  • Variable selection

ASJC Scopus subject areas

  • Molecular Medicine

Cite this

ANVAS : Artificial neural variables adaptation system for descriptor selection. / Mazzatorta, Paolo; Vračko, Marjan; Benfenati, Emilio.

In: Journal of Computer-Aided Molecular Design, Vol. 17, No. 5-6, 05.2003, p. 335-346.

Research output: Contribution to journalArticle

@article{3dda05a532dc4ad18cc6acd1ea41defc,
title = "ANVAS: Artificial neural variables adaptation system for descriptor selection",
abstract = "A new algorithm model-oriented for variable selection is presented in this study. It is based on the combination of genetic algorithms (GA) for hyperspace exploration, and counterpropagation artificial neural network (CP ANN) for deriving the fitness score. The proposed method performed very well on both well defined synthetic data sets and real academic data sets.",
keywords = "Counterpropagation, Genetic algorithm, Neural networks, QSAR, Variable selection",
author = "Paolo Mazzatorta and Marjan Vračko and Emilio Benfenati",
year = "2003",
month = "5",
doi = "10.1023/A:1026132402754",
language = "English",
volume = "17",
pages = "335--346",
journal = "Journal of Computer-Aided Molecular Design",
issn = "0920-654X",
publisher = "Springer Netherlands",
number = "5-6",

}

TY - JOUR

T1 - ANVAS

T2 - Artificial neural variables adaptation system for descriptor selection

AU - Mazzatorta, Paolo

AU - Vračko, Marjan

AU - Benfenati, Emilio

PY - 2003/5

Y1 - 2003/5

N2 - A new algorithm model-oriented for variable selection is presented in this study. It is based on the combination of genetic algorithms (GA) for hyperspace exploration, and counterpropagation artificial neural network (CP ANN) for deriving the fitness score. The proposed method performed very well on both well defined synthetic data sets and real academic data sets.

AB - A new algorithm model-oriented for variable selection is presented in this study. It is based on the combination of genetic algorithms (GA) for hyperspace exploration, and counterpropagation artificial neural network (CP ANN) for deriving the fitness score. The proposed method performed very well on both well defined synthetic data sets and real academic data sets.

KW - Counterpropagation

KW - Genetic algorithm

KW - Neural networks

KW - QSAR

KW - Variable selection

UR - http://www.scopus.com/inward/record.url?scp=0242691110&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0242691110&partnerID=8YFLogxK

U2 - 10.1023/A:1026132402754

DO - 10.1023/A:1026132402754

M3 - Article

VL - 17

SP - 335

EP - 346

JO - Journal of Computer-Aided Molecular Design

JF - Journal of Computer-Aided Molecular Design

SN - 0920-654X

IS - 5-6

ER -