17.08.2018 | Original Article
Integrating mutation scheme into monarch butterfly algorithm for global numerical optimization
Erschienen in: Neural Computing and Applications | Ausgabe 7/2020
EinloggenAktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
MBO
) has recently been proposed as a robust metaheuristic optimization algorithm for solving numerical global optimization problems. To enhance the performance of MBO
algorithm, harmony search (HS
) is introduced as a mutation operator during the adjusting operator of MBO
. A novel hybrid metaheuristic optimization method, the so-called HMBO
, is introduced to find the best solution for the global optimization problems. HMBO
combines HS
exploration with MBO
exploitation, and therefore, it produces potential candidate solutions. The implementation process for enhancing MBO
method is also presented. To evaluate the effectiveness of this improvement, fourteen standard benchmark functions are used. The mean and the best performance of these benchmark functions in 20, 50, and 100 dimensions demonstrated that HMBO
often performs better than the original MBO
and other population-based optimization algorithms such as ACO
, BBO
, DE
, ES
, GA
PBIL
, PSO
and SGA
. Moreover, the t-test result proved that the performance differences between the enhanced HMBO
and the original MBO
as well as the other optimization methods are statistically significant.