.png){kind=icon}
返回
An improved beetle swarm antennae search algorithm based on multiple operators
.png){kind=icon}
PRE
AI
DOI：10.1007/s00500-023-09500-2.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The beetle antennae search algorithm (BAS) is inspired by the search behavior of long-horned beetles and is widely used in optimization problems. However, in the typical BAS algorithm, there are problems such as the insufficient optimization ability of beetle individuals and the lack of consideration of historical dynamic information in the algorithm search process, resulting in sufferings from local optimum, low diversity, and imbalanced utilization, etc. To solve these problems, an improved beetle swarm antennae search algorithm based on multiple operators, dubbed MO-BSAS, is proposed. First, the elite opposition-based learning is used to initialize the beetle population, which improves the population diversity and optimization ability of the algorithm; then, the Levy Flight strategy is used to improve the traditional beetle moving operator. In addition, a multi-operator search strategy determined by the damped sinusoidal probability factor is designed to balance the exploitation and exploration capabilities of the algorithm and speed up its convergence. The MO-BSAS algorithm is compared with BSA and 8 popular or state-of-the-art smart algorithms under 14 different benchmark functions, and the experimental results show that the MO-BSAS algorithm has a shorter convergence time and better convergence accuracy than the algorithms compared, which verifies the effectiveness of the improved algorithm.
Keyword:
Beetle antennae search
Opposition-based learning
Levy flight
Differential evolution
Probability distribution
期刊
IF:
2.5
论文数:
1.0W
被引数:
2.1W
机构
引用论文
A survey on nature inspired metaheuristic algorithms for partitional clustering基于自然启发的分区聚类元启发式算法综述
PREAI
分享收藏
Clinical prediction models for mortality and functional outcome following ischemic stroke: A systematic review and meta-analysis.png)
PLOS ONE
OAAI
PLOS ONEIF0
OAAI分享收藏A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms关于使用非参数统计检验作为比较进化和群体智能算法的方法的实用教程
PREAI
分享收藏分享收藏
查看更多内容