- Title
- A priority based parental selection method for genetic algorithm
- Creator
- Nazmul, Rumana; Chetty, Madhu
- Date
- 2013
- Type
- Text; Conference paper
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/157251
- Identifier
- vital:11552
- Identifier
-
https://doi.org/10.1145/2464576.2464641
- Identifier
- ISBN:978-1-4503-1964-5
- Abstract
- Selection is an important and critical aspect in evolutionary computation. This paper presents a novel parental selection technique that includes the advantages of both the deterministic and the stochastic selection techniques and helps to reduce the loss of diversity by distributing the reproduction opportunity among all the members of the population. Moreover, the proposed selection strategy promotes the concept of non-random mating by clustering the population into groups according to the fitness values and then by persuading the mating between individuals from different groups based on performance determined dynamically over the evolution. Computational results using widely used benchmark functions show significant improvements in the convergence characteristics of the proposed selection method over two well-known selection techniques.
- Publisher
- ACM
- Relation
- GECCO '13 , Amsterdam, July 6th-10th, 2013 ; published in Proceedings of the 15th annual conference companion on Genetic and evolutionary computation pg.125-126
- Rights
- Copyright ACM
- Rights
- This metadata is freely available under a CCO license
- Subject
- Mathematics; Mathematical analysis; Theory of computation; Genetic evolutionary algorithm; Selection strategy
- Reviewed
- Hits: 590
- Visitors: 576
- Downloads: 0
| Thumbnail | File | Description | Size | Format |
|---|