Parameter-setting-free harmony search algorithm

Various phenomenon-mimicking algorithms, such as genetic algorithm, simulated annealing, tabu search, ant colony optimization, and particle swarm optimization, have their own algorithm parameters. These parameters need to be skillfully assigned in order to obtain good results. It is burdensome, espe...

Full description

Saved in:
Bibliographic Details
Published in:Applied mathematics and computation Vol. 217; no. 8; pp. 3881 - 3889
Main Authors: Geem, Zong Woo, Sim, Kwee-Bo
Format: Journal Article
Language:English
Published: Amsterdam Elsevier Inc 15.12.2010
Elsevier
Subjects:
ISSN:0096-3003, 1873-5649
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Various phenomenon-mimicking algorithms, such as genetic algorithm, simulated annealing, tabu search, ant colony optimization, and particle swarm optimization, have their own algorithm parameters. These parameters need to be skillfully assigned in order to obtain good results. It is burdensome, especially to novice users, to assign these parameters. The same is true for the harmony search algorithm which was inspired by music performance. Thus, this study proposes a novel technique to eliminate tedious and experience-requiring parameter assigning efforts. The new parameter-setting-free (PSF) technique which this study suggests contains one additional matrix which contains an operation type (random selection, memory consideration, or pitch adjustment) for every variable in harmony memory. Three examples illustrate that the PSF technique can find good solutions robustly.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0096-3003
1873-5649
DOI:10.1016/j.amc.2010.09.049