An improved mayfly algorithm and its application

An improved version of the mayfly algorithm called the golden annealing crossover-mutation mayfly algorithm (GSASMA) is proposed to address the low convergence efficiency and insufficient search capability of existing mayfly algorithms. First, the speed of individual mayflies is optimized using a si...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:AIP advances Jg. 12; H. 10; S. 105320 - 105320-11
Hauptverfasser: Zhao, Mengling, Yang, Xinlu, Yin, Xinyu
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Melville American Institute of Physics 01.10.2022
AIP Publishing LLC
Schlagworte:
Algorithms
Artificial neural networks
Convergence
Crossovers
Machine learning
Mutation
Optimization
Simulated annealing
Simulation
Support vector machines
ISSN:2158-3226, 2158-3226
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:An improved version of the mayfly algorithm called the golden annealing crossover-mutation mayfly algorithm (GSASMA) is proposed to address the low convergence efficiency and insufficient search capability of existing mayfly algorithms. First, the speed of individual mayflies is optimized using a simulated annealing algorithm to improve the update rate. The position of individuals is improved using the golden sine algorithm. Second, the impact of using different crossover and mutation methods in the algorithm is compared, and the optimal strategy is selected from the algorithm. To evaluate the performance of the algorithm, simulation experiments were carried out for 10 different test functions, and the results were compared with those of existing algorithms. The simulation results show that the algorithm developed in this paper converges faster and the solutions obtained are closer to the global optimum. Finally, GSASMA was used to optimize a support vector machine (SVM) that was used to identify the P300 signal for five subjects. The experimental results show that the SVM optimized by the algorithm proposed in this paper has higher recognition accuracy than an extreme learning machine.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2158-3226
2158-3226
DOI:10.1063/5.0108278