解决高维优化和特征选择的多策略改进正弦余弦算法
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

TP301.6

基金项目:

国家自然科学基金(61463009);贵州省科学技术基金(黔科合基础[2020]1Y012);贵州省教育厅创新群体重大研究项目(黔教合KY字[2021]015)


Multi-strategy Improved Sine Cosine Algorithm for Solving High-dimensional Optimization and Feature Selection
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对基本正弦余弦算法(Sine cosine algorithm, SCA)求解高维复杂优化问题时存在精度低、收敛慢和易陷入局部最优等缺点,提出一种改进的SCA(简记为iSCA)。首先,该算法设计出一种基于倒S型函数的非线性转换参数规则替代原有线性策略,以获得从勘探到开发的良好过渡;其次,嵌入个体历史最佳信息修改位置搜索方程以指导寻优过程,进一步改善算法的解精度和加快收敛;最后,引入翻筋斗觅食机制生成新的位置以增加群体多样性,从而降低算法陷入局部最优的概率。选取10个高维基准测试函数和10个UCI高维数据集进行仿真实验,并与基本SCA和其他改进SCA方法比较,结果表明,本文算法在精度和收敛指标上均优于其他比较方法。

    Abstract:

    The basic sine cosine algorithm (SCA) has some shortcomings such as low accuracy, slow convergence and easy to fall into local optima when using it solve high-dimensional complex optimization problems. An improved SCA (iSCA) is proposed. First, a nonlinear conversion parameter rule based on inverted sigmoid function is designed to replace the original linear strategy. This rule obtains a good transition from exploration to exploitation. Then, the personal historical best information is embedded into the position search equation to guide the optimization process. The modified equation further improves the solution precision and accelerates convergence. Finally, a somersault foraging mechanism is introduced to generate a new position to increase the population diversity, thereby reducing the probability of falling into local optima. Selecting 10 high-dimensional benchmark test functions and 10 high-dimensional UCI datasets for experiments, and the results of iSCA are compared with the basic SCA and other improved SCA methods. The results show that iSCA has better performance than other methods in terms of solution precision and convergence speed. The proposed algorithm is effective for solving the high-dimensional optimization problems.

    参考文献
    相似文献
    引证文献
引用本文

徐明,羊洋,龙文. 解决高维优化和特征选择的多策略改进正弦余弦算法[J]. 科学技术与工程, 2023, 23(13): 5632-5640.
Xu Ming, Yang Yang, Long Wen. Multi-strategy Improved Sine Cosine Algorithm for Solving High-dimensional Optimization and Feature Selection[J]. Science Technology and Engineering,2023,23(13):5632-5640.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2022-06-16
  • 最后修改日期:2023-02-09
  • 录用日期:2022-12-01
  • 在线发布日期: 2023-05-29
  • 出版日期:
×
律回春渐,新元肇启|《科学技术与工程》编辑部恭祝新岁!
亟待确认版面费归属稿件,敬请作者关注