Improved Crayfish Optimization Algorithm for Solving Feature Selection Problem

To improve the optimization effect of the crayfish optimization algorithm. This paper proposes a singer chaotic map and population evolution improved crayfish optimization algorithm (ICOA). ICOA improves the random rate of the initial population by adding a chaotic map strategy, which helps the algo...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Chinese Control and Decision Conference s. 3514 - 3519
Hlavní autoři: Rao, Honghua, Jia, Heming, Shi, Xiaoming, You, Fangkai, Xue, Bowen, Du, Yilong
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 16.05.2025
Témata:
CEC2020 test function
Convergence
crayfish optimization algorithm
Feature extraction
feature selection
Information exchange
Optimization
population evolution strategy
ISSN:1948-9447
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:To improve the optimization effect of the crayfish optimization algorithm. This paper proposes a singer chaotic map and population evolution improved crayfish optimization algorithm (ICOA). ICOA improves the random rate of the initial population by adding a chaotic map strategy, which helps the algorithm to converge better. Then, the population evolution strategy is proposed through the crossevolution of the historical and current populations. The population evolution strategy improves the information interaction between populations and the convergence effect of the algorithm. To verify the optimization effect of ICOA, the CEC2020 test function and feature selection are used as experiments. Comparative experiments are conducted between ICOA and various algorithms. The results indicate that ICOA has better optimization effects.
ISSN:1948-9447
DOI:10.1109/CCDC65474.2025.11090177