.png){kind=icon}
.png){kind=icon}
Return
A sinusoidal differential evolution algorithm for numerical optimisation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.asoc.2014.11.003.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper presents a new variant of the Differential Evolution (DE) algorithm called Sinusoidal Differential Evolution (SinDE). The key idea of the proposed SinDE is the use of new sinusoidal formulas to automatically adjust the values of the DE main parameters: the scaling factor and the crossover rate. The objective of using the proposed sinusoidal formulas is the search for a good balance between the exploration of non visited regions of the search space and the exploitation of the already found good solutions. By applying it on the recently proposed CEC-2013 set of benchmark functions, the proposed approach is statistically compared with the classical DE, the linearly parameter adjusting DE and 10 other state-of-the-art metaheuristics. The obtained results have proven the superiority of the proposed SinDE, it outperformed other approaches especially for multimodal and composition functions. (C) 2014 Elsevier B.V. All rights reserved.
Keywords:
Differential evolution
Sinusoidal parameter adjustment
Exploration
Exploitation
Optimisation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.6
Papers:
1.4W
Citations:
4.8W
Organization
No organization information available