Adaptive linkage crossover

Ayed A. Salman, Kishan Mehrotra, Chilukuri K. Mohan

Research output: Chapter in Book/Entry/PoemConference contribution

7 Scopus citations

Abstract

Effective application of genetic algorithms (GAs) to difficult problems is hindered by the mismatch between the crossover operators used and the problem-specific linkages. We propose a new linkage crossover operator that utilizes problem-specific linkages, exploiting probabilistic inference methodology. A new adaptive algorithm learns the nature of such linkages, and applies the learned knowledge to solve the problem. Experimental results are given, demonstrating that solutions better than traditional crossover operators are obtained, and the linkage adaptation process converges to meaningful linkage values.

Original languageEnglish (US)
Title of host publicationProceedings of the 1998 ACM Symposium on Applied Computing, SAC 1998
PublisherAssociation for Computing Machinery
Pages338-342
Number of pages5
ISBN (Electronic)0897919696
DOIs
StatePublished - Feb 27 1998
Event1998 ACM Symposium on Applied Computing, SAC 1998 - Atlanta, United States
Duration: Feb 27 1998Mar 1 1998

Publication series

NameProceedings of the ACM Symposium on Applied Computing
Volume02-February-1998

Other

Other1998 ACM Symposium on Applied Computing, SAC 1998
Country/TerritoryUnited States
CityAtlanta
Period2/27/983/1/98

Keywords

  • Crossover
  • Genetic algorithm
  • Linkage
  • Optimization
  • Probabilistic inference

ASJC Scopus subject areas

  • Software

Fingerprint

Dive into the research topics of 'Adaptive linkage crossover'. Together they form a unique fingerprint.

Cite this