A parallel compact Marine Predators Algorithm applied in time series prediction of Backpropagation neural network (BNN) and engineering optimization

This study introduces a novel approach for integrating a compact mechanism into the Marine Predator Algorithm (MPA), subsequently proposing innovative parallel and communication strategies. The synergistic combination of these methodologies substantially augments the global search efficiency and acc...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Mathematics and computers in simulation Ročník 220; s. 65 - 88
Hlavní autori: Pan, Jeng-Shyang, Zhang, Zhen, Chu, Shu-Chuan, Zhang, Si-Qi, Wu, Jimmy Ming-Tai
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 01.06.2024
Predmet:
BNN (Backpropagation neural network)
Compact strategy
Engineering optimization
Marine Predators Algorithm
Parallel communication strategy
Parallel communication strategy
Marine Predators Algorithm
BNN (Backpropagation neural network)
Compact strategy
Engineering optimization
ISSN:0378-4754, 1872-7166
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This study introduces a novel approach for integrating a compact mechanism into the Marine Predator Algorithm (MPA), subsequently proposing innovative parallel and communication strategies. The synergistic combination of these methodologies substantially augments the global search efficiency and accelerates the convergence rate of the original MPA. The paper culminates in presenting an enhanced version of the Marine Predator Algorithm, termed PCMPA, which leverages compact parallel technology. The performance of PCMPA, alongside a range of comparative algorithms, is rigorously evaluated using the CEC2013 benchmark test functions. These comparative algorithms encompass recent variants of MPA, PSO, DE, and other newly developed algorithms. Evaluation results reveal that PCMPA outperforms its counterparts in a more extensive array of test functions. To corroborate PCMPA’s efficacy in real-world scenarios, the algorithm is applied to parameter optimization in Backpropagation neural network (BNN) and targeted engineering optimization challenges. This application demonstrates that PCMPA consistently achieves enhanced performance in practical implementations. •The study presents a novel variant of the Marine Predators Algorithm, dubbed PCMPA.•The paper benchmarks PCMPA against other Marine Predators Algorithm variants and other Algorithms.•The research applies PCMPA to optimize parameters of BNNs and to tackle engineering optimization challenges.
ISSN:0378-4754
1872-7166
DOI:10.1016/j.matcom.2024.01.012