Searching for just a few words should be enough to get started. If you need to make more complex queries, use the tips below to guide you.
Article type: Research Article
Authors: Martins, Jean P. | Delbem, Alexandre C.B.
Affiliations: Institute of Mathematics and Computer Sciences, University of São Paulo, São Carlos - SP, Brazil
Note: [] Corresponding author. Jean P. Martins, Institute of Mathematics and Computer Sciences, University of São Paulo, Trabalhador São-carlense Avenue, 400, center, CEP: 13566-590, São Carlos - SP Brazil. E-mails: [email protected] (Jean P. Martins); [email protected] (Alexandre C.B. Delbem).
Abstract: Estimation of Distribution Algorithms (EDA) are population-based meta-heuristics that use probabilistic models to describe the relationships between variables of a problem. From these models, new solutions can be sampled without disruption of Building Blocks, leading to a more effective search. The key aspect of EDAs is the model-building step and better models should enable a better exploration of the search space. However, high-quality models require computationally expensive algorithms, resulting in too costly EDAs. This paper proposes an efficient implementation of the tournament selection algorithm (TS), called Compressed Tournament Selection (CTS). CTS avoids the insertion of repeated solutions in the population during the TS. Therefore, model-building can be performed on a reduced population (equivalent to the original), improving the EDAs' performance as a whole. In the experiments the method was applied to the Extended Compact Genetic Algorithm and the results showed that by using an appropriate tournament size, CTS can lead to high speed-ups without a decrease of model quality. Besides, CTS keeps the characteristics of TS and can be easily used to enhance the efficiency of any EDA based on the tournament selection algorithm.
Keywords: Efficiency enhancement, estimation of distribution algorithms, tournament selection
DOI: 10.3233/IFS-130925
Journal: Journal of Intelligent & Fuzzy Systems, vol. 26, no. 5, pp. 2537-2545, 2014
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
USA
Tel: +1 703 830 6300
Fax: +1 703 830 2300
[email protected]
For editorial issues, like the status of your submitted paper or proposals, write to [email protected]
IOS Press
Nieuwe Hemweg 6B
1013 BG Amsterdam
The Netherlands
Tel: +31 20 688 3355
Fax: +31 20 687 0091
[email protected]
For editorial issues, permissions, book requests, submissions and proceedings, contact the Amsterdam office [email protected]
Inspirees International (China Office)
Ciyunsi Beili 207(CapitaLand), Bld 1, 7-901
100025, Beijing
China
Free service line: 400 661 8717
Fax: +86 10 8446 7947
[email protected]
For editorial issues, like the status of your submitted paper or proposals, write to [email protected]
如果您在出版方面需要帮助或有任何建, 件至: [email protected]