A graph-based immune-inspired constraint satisfaction search

María Cristina Riff, Marcos Zúñiga, Elizabeth Montero

Resultado de la investigación: Article

9 Citas (Scopus)

Resumen

We propose an artificial immune algorithm to solve constraint satisfaction problems (CSPs). Recently, bio-inspired algorithms have been proposed to solve CSPs. They have shown to be efficient in solving hard problem instances. Given that recent publications indicate that immune-inspired algorithms offer advantages to solve complex problems, our main goal is to propose an efficient immune algorithm which can solve CSPs. We have calibrated our algorithm using relevance estimation and value calibration (REVAC), which is a new technique recently introduced to find the parameter values for evolutionary algorithms. The tests were carried out using randomly generated binary constraint satisfaction problems and instances of the three-colouring problem with different constraint networks. The results suggest that the technique may be successfully applied to solve CSPs.

Idioma originalEnglish
Páginas (desde-hasta)1133-1142
Número de páginas10
PublicaciónNeural Computing and Applications
Volumen19
N.º8
DOI
EstadoPublished - 30 jun 2010

Huella dactilar

Constraint satisfaction problems
Coloring
Evolutionary algorithms
Calibration

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Citar esto

Riff, María Cristina ; Zúñiga, Marcos ; Montero, Elizabeth. / A graph-based immune-inspired constraint satisfaction search. En: Neural Computing and Applications. 2010 ; Vol. 19, N.º 8. pp. 1133-1142.
@article{8e43f23714af4b21b52b9d63b1f4a4b3,
title = "A graph-based immune-inspired constraint satisfaction search",
abstract = "We propose an artificial immune algorithm to solve constraint satisfaction problems (CSPs). Recently, bio-inspired algorithms have been proposed to solve CSPs. They have shown to be efficient in solving hard problem instances. Given that recent publications indicate that immune-inspired algorithms offer advantages to solve complex problems, our main goal is to propose an efficient immune algorithm which can solve CSPs. We have calibrated our algorithm using relevance estimation and value calibration (REVAC), which is a new technique recently introduced to find the parameter values for evolutionary algorithms. The tests were carried out using randomly generated binary constraint satisfaction problems and instances of the three-colouring problem with different constraint networks. The results suggest that the technique may be successfully applied to solve CSPs.",
author = "Riff, {Mar{\'i}a Cristina} and Marcos Z{\'u}{\~n}iga and Elizabeth Montero",
year = "2010",
month = "6",
day = "30",
doi = "10.1007/s00521-010-0390-8",
language = "English",
volume = "19",
pages = "1133--1142",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer London",
number = "8",

}

A graph-based immune-inspired constraint satisfaction search. / Riff, María Cristina; Zúñiga, Marcos; Montero, Elizabeth.

En: Neural Computing and Applications, Vol. 19, N.º 8, 30.06.2010, p. 1133-1142.

Resultado de la investigación: Article

TY - JOUR

T1 - A graph-based immune-inspired constraint satisfaction search

AU - Riff, María Cristina

AU - Zúñiga, Marcos

AU - Montero, Elizabeth

PY - 2010/6/30

Y1 - 2010/6/30

N2 - We propose an artificial immune algorithm to solve constraint satisfaction problems (CSPs). Recently, bio-inspired algorithms have been proposed to solve CSPs. They have shown to be efficient in solving hard problem instances. Given that recent publications indicate that immune-inspired algorithms offer advantages to solve complex problems, our main goal is to propose an efficient immune algorithm which can solve CSPs. We have calibrated our algorithm using relevance estimation and value calibration (REVAC), which is a new technique recently introduced to find the parameter values for evolutionary algorithms. The tests were carried out using randomly generated binary constraint satisfaction problems and instances of the three-colouring problem with different constraint networks. The results suggest that the technique may be successfully applied to solve CSPs.

AB - We propose an artificial immune algorithm to solve constraint satisfaction problems (CSPs). Recently, bio-inspired algorithms have been proposed to solve CSPs. They have shown to be efficient in solving hard problem instances. Given that recent publications indicate that immune-inspired algorithms offer advantages to solve complex problems, our main goal is to propose an efficient immune algorithm which can solve CSPs. We have calibrated our algorithm using relevance estimation and value calibration (REVAC), which is a new technique recently introduced to find the parameter values for evolutionary algorithms. The tests were carried out using randomly generated binary constraint satisfaction problems and instances of the three-colouring problem with different constraint networks. The results suggest that the technique may be successfully applied to solve CSPs.

UR - http://www.scopus.com/inward/record.url?scp=77958487594&partnerID=8YFLogxK

U2 - 10.1007/s00521-010-0390-8

DO - 10.1007/s00521-010-0390-8

M3 - Article

VL - 19

SP - 1133

EP - 1142

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

IS - 8

ER -