基于分数阶调整动态边界的蜣螂优化算法  

Dung beetle optimizer with dynamic boundary of fractional order adjustment

作　　者：夏煌智 陈丽敏 许宏文 常云鹏 XIA Huang-zhi;CHEN Li-min;XU Hong-wen;CHANG Yun-peng(School of Mathematical Science,Mudanjiang Normal University,Mudanjiang 157009,China;School of Computer and Information Technology,Mudanjiang Normal University,Mudanjiang 157009,China)

机构地区：[1]牡丹江师范学院数学科学学院,黑龙江牡丹江157009 [2]牡丹江师范学院计算机与信息技术学院,黑龙江牡丹江157009

出　　处：《计算机工程与设计》2024年第12期3657-3666,共10页Computer Engineering and Design

基　　金：黑龙江省自然科学基金项目(LH2019F051);牡丹江师范学院科技创新重点基金项目(kjcx2023-126mdjnu);牡丹江师范学院科技创新基金项目(kjcx2023-123mdjnu、kjcx2023-124mdjnu)。

摘　　要：针对蜣螂优化算法在全局优化问题中易陷入局部最优与收敛精度低的问题,提出一种改进的蜣螂优化算法。采用佳点集序列取代原始算法中随机产生的初始种群提升种群的多样性;引入分数阶微积分方法调整区域动态边界,分离重叠的种群个体,提升算法的局部开采性能;提出探路蜣螂更新机制对全局最佳位置进行更新,防止其陷入局部最优。通过24个基准测试函数的全局优化实验与5个经典数据集的特征选择实验验证了改进算法相比同类型算法具有更好的寻优性能。Aiming at the problems that the dung beetle optimizer is prone to local optimization and low convergence accuracy in global optimization,an improved dung beetle optimization algorithm was proposed.By replacing the initial population randomly generated in the original algorithm using the good nodes set sequence,the diversity of the population was improved.The fractional calculus method was introduced to adjust regional dynamic boundary to separate overlapping population individuals and improve the local mining performance of the algorithm.A mechanism was proposed to update the global optimal position,preventing it from falling into the local optimal position.The global optimization experiments of 24 benchmark functions and the feature selection experiments of 5 data sets show that the improved algorithm has better optimization performance than the same type of algorithms.

关 键 词：蜣螂优化算法 全局优化 佳点集 分数阶微积分 动态边界 探路者算法 特征选择 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]