Abstract
Genetic algorithms that utilise floating pointencoded chromosomes instead of the traditional binary or Gary code have become wide spread in recent years. This paper introduces new floatingpoint crossover and mutation operators for such genetic algorithms. The operators are derived from examining the implicit constraints that traditional binary crossover and mutation operators impose on the values of the parameters being affected. It is shown by an example that a genetic algorithm using these operators does converge and they should be considered for general use in floating-point genetic algorithms.
Original language | English |
---|---|
Title of host publication | Proceedings 19th European Conference on Modelling and Simulation |
Editors | Yuri Merkuryev, Richard Zobel, Eugene Kerckhoffs |
Publisher | ECMS |
Number of pages | 5 |
ISBN (Print) | 1-84233-112-4 |
Publication status | Published - 2005 |
Event | 19th European Conference on Modelling and Simulation - Riga, Latvia Duration: 1 Jun 2005 → 4 Jun 2005 |
Conference
Conference | 19th European Conference on Modelling and Simulation |
---|---|
Abbreviated title | ECMS 2005 |
Country/Territory | Latvia |
City | Riga |
Period | 1/06/05 → 4/06/05 |