Scholarlink

<p>Hybridizing metaheuristic optimization algorithms offers a promising approach for enhancing the search performance and achieving optimal solutions. The main goal of hybridization is to combine algorithms in a manner that eliminates their disadvantages while enhancing their capabilities. The Cheetah Optimizer (CO), a bioinspired algorithm, effectively combines various strategies to navigate the search space. Despite its success in diverse engineering applications, CO faces challenges, such as slow convergence and stagnation in local optima. This study introduces a novel hybridization of the Cheetah Optimizer, incorporating Opposition-Based Learning (OBL) and diversity measures to enhance its exploratory capabilities. The OBL mechanism updates solutions by considering a counterpart in the opposite region of the search space, thereby expanding the solution range. In addition, diversity measures ensure a balance between exploration and exploitation throughout the evolutionary process. The combination of these methodologies enables the developed algorithm to achieve faster convergence rates, while simultaneously diminishing the likelihood of becoming trapped in local optimum solutions. To validate the performance of the proposed algorithm, it was compared with other optimization methods by using a representative set of functions with different degrees of complexity. The results demonstrated its ability to produce competitive results in terms of accuracy and robustness.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A novel cheetah optimizer hybrid approach based on opposition-based learning (OBL) and diversity metrics

  • 期刊论文

  • 发表日期：

    2025年1月27日

查看全文
  • Erik Cuevas,
  • Oscar Barba,
  • Héctor Escobar

摘要

Hybridizing metaheuristic optimization algorithms offers a promising approach for enhancing the search performance and achieving optimal solutions. The main goal of hybridization is to combine algorithms in a manner that eliminates their disadvantages while enhancing their capabilities. The Cheetah Optimizer (CO), a bioinspired algorithm, effectively combines various strategies to navigate the search space. Despite its success in diverse engineering applications, CO faces challenges, such as slow convergence and stagnation in local optima. This study introduces a novel hybridization of the Cheetah Optimizer, incorporating Opposition-Based Learning (OBL) and diversity measures to enhance its exploratory capabilities. The OBL mechanism updates solutions by considering a counterpart in the opposite region of the search space, thereby expanding the solution range. In addition, diversity measures ensure a balance between exploration and exploitation throughout the evolutionary process. The combination of these methodologies enables the developed algorithm to achieve faster convergence rates, while simultaneously diminishing the likelihood of becoming trapped in local optimum solutions. To validate the performance of the proposed algorithm, it was compared with other optimization methods by using a representative set of functions with different degrees of complexity. The results demonstrated its ability to produce competitive results in terms of accuracy and robustness.