Scholarlink

<p>Multi-modal optimization assists academics, engineers, scientists and decision-makers to solve complex situations by evaluating several outcomes and configurations. The Flamingo Search Algorithm (FSA) is a relatively recent optimisation approach. The migratory and foraging habits of flamingos serve as the inspiration for this swarm intelligent algorithm. Uni-modal FSA provides a global solution to optimal design in different research areas of the optimization problems. This paper presents the multi-modal variant of the Flamingo Search Algorithm named MMFSA. The algorithm uses three clustering as niching methods to improve search. However due to randomness, the exploitation capabilities in vicinity area maybe limited. MMFSA addresses this issue. In MMFSA, best solutions obtained from each cluster are further improved using a self-augmentation process. The MMFSA’s efficiency and efficacy are confirmed by extensive multi-modal benchmark functions testing. Success rate, average optima identified, maximum peak ratio, functions evaluation and optima success performance measure algorithm&#xa0;efficacy. Comparison results of MMFSA with contemporary multi-modal algorithms reveal that MMFSA outperforms other multi-modal optimization algorithms. MMFSA is able to provide 95% accuracy for the obtained solutions. Proposed MMFSA also affirms its superiority for various performance metrics over multi-modal benchmark functions.</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

Multi-modal Flamingo Search Algorithm (MMFSA)

  • 期刊论文

  • 发表日期：

    2025年6月24日

查看全文
  • Seema,
  • Shikha Mehta,
  • Hema Banati

摘要

Multi-modal optimization assists academics, engineers, scientists and decision-makers to solve complex situations by evaluating several outcomes and configurations. The Flamingo Search Algorithm (FSA) is a relatively recent optimisation approach. The migratory and foraging habits of flamingos serve as the inspiration for this swarm intelligent algorithm. Uni-modal FSA provides a global solution to optimal design in different research areas of the optimization problems. This paper presents the multi-modal variant of the Flamingo Search Algorithm named MMFSA. The algorithm uses three clustering as niching methods to improve search. However due to randomness, the exploitation capabilities in vicinity area maybe limited. MMFSA addresses this issue. In MMFSA, best solutions obtained from each cluster are further improved using a self-augmentation process. The MMFSA’s efficiency and efficacy are confirmed by extensive multi-modal benchmark functions testing. Success rate, average optima identified, maximum peak ratio, functions evaluation and optima success performance measure algorithm efficacy. Comparison results of MMFSA with contemporary multi-modal algorithms reveal that MMFSA outperforms other multi-modal optimization algorithms. MMFSA is able to provide 95% accuracy for the obtained solutions. Proposed MMFSA also affirms its superiority for various performance metrics over multi-modal benchmark functions.