Lancaster EPrints

Supplementary Crossover Operator for Genetic Algorithms based on the Center-of-Gravity Paradigm

Angelov, Plamen (2001) Supplementary Crossover Operator for Genetic Algorithms based on the Center-of-Gravity Paradigm. Control and Cybernetics, 30 (2). pp. 159-176. ISSN 0324-8569

Full text not available from this repository.

Abstract

A supplementary crossover operator for genetic algorithms (GA) is proposed in the paper. It performs specific breeding between the two fittest parental chromosomes. The new child chromosome is based on the center of gravity (CoG) paradigm, taking into account both the parental weight (measured by their fitness) and their actual value. It is designed to be used in combination with other crossover and mutation operators (it applies to the best fitted two parental chromosomes only) both in binary and real-valued (evolutionary) GA. Analytical proof of its ability to improve the result is provided for the simplest case of one variable and when elitist selection strategy is used. The new operator is validated with a number of usually used numerical test functions as well as with a practical example of supply air temperature and flow rate scheduling in a hollow core ventilated slab thermal storage system. The tests indicate that it improves results (the speed of convergence as well as the final result) without significant increasing computational expenses. (c) Control and Cybernetics

Item Type: Article
Journal or Publication Title: Control and Cybernetics
Uncontrolled Keywords: Genetic algorithms ; crossover ; mutation ; selection operators ; center of gravity ; DCS-publications-id ; art-466 ; DCS-publications-personnel-id ; 82
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments: Faculty of Science and Technology > School of Computing & Communications
ID Code: 908
Deposited By: Dr. Plamen Angelov
Deposited On: 07 Feb 2008 10:18
Refereed?: Yes
Published?: Published
Last Modified: 21 Mar 2014 10:17
Identification Number:
URI: http://eprints.lancs.ac.uk/id/eprint/908

Actions (login required)

View Item