Back to Search Start Over

KNOB Particle Swarm Optimizer.

Authors :
Zhang, Junqi
Liu, Kun
Tan, Ying
Source :
Advances in Swarm Intelligence: First International Conference, ICSI 2010, Beijing, China, June 12-15, 2010, Proceedings, Part I; 2010, p78-85, 8p
Publication Year :
2010

Abstract

It is not trivial to tune the swarm behavior just by parameter setting because of the randomness, complexity and dynamic involved in particle swarm optimizer (PSO). Hundreds of variants in the literature of last decade, brought various mechanism or ideas, sometimes also from outside of the traditional metaheuristics field, to tune the swarm behavior. While, in the same time, additional parameters have to be afforded. This paper proposes a new mechanism, named KNOB, to directly tune the swarm behavior through parameter setting of PSO. KNOB is defined as the first principal component of the statistical probability sequence of exploration and exploitation allocation along the search process. The using of the KNOB to tune PSO by parameter setting is realized through a statistical mapping, between the parameter set and the KNOB, learned by a radial basis function neural network (RBFNN) simulation model. In this way, KNOB provides an easy way to tune PSO directly by its parameter setting. A simple application of KNOB to promote is presented to verify the mechanism of KNOB. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISBNs :
9783642134944
Database :
Complementary Index
Journal :
Advances in Swarm Intelligence: First International Conference, ICSI 2010, Beijing, China, June 12-15, 2010, Proceedings, Part I
Publication Type :
Book
Accession number :
76848904
Full Text :
https://doi.org/10.1007/978-3-642-13495-1_10