Scholarlink

<p>In this study, we developed a revolutionary algorithm called Quantum-inspired Multi-Objective Seahorse Optimizer (MOQSHO) for tackling Numerical Association Rule Mining (NARM) problem, which is a particular case of Association Rule Mining (ARM). The challenge inherent in NARM can be approached along three distinct axes: distribution, discretization, and optimization. Traditional single-objective SHO, a bio-inspired metaheuristic optimization method, has shown competitive performance in many complex problems. Still, it needs to tackle multiple objectives of the NARM problem and tends to be stuck in local optima. We propose an optimization-based MOQSHO algorithm to overcome SHO deficiencies by integrating the quantum mechanics in traditional SHO and enhancing its ability to simultaneously handle multiple objectives of the NARM problem. Quantum mechanics helps to improve traditional SHO algorithms’ exploitation and exploration abilities. To evaluate the performance of the MOQSHO algorithm, we undertook a series of tests, using measures such as generational distance (GD), inverse generational distance (IGD), hypervolume (HV), spacing, spread, and <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12559_2025_10486_Article_IEq1.gif" Format="GIF" Height="19" Rendition="HTML" Resolution="72" Type="Linedraw" Width="22" /> </InlineMediaObject> <EquationSource Format="TEX">\(\Delta _p\)</EquationSource> <EquationSource Format="MATHML"><math> <msub> <mi mathvariant="normal">Δ</mi> <mi>p</mi> </msub> </math></EquationSource> </InlineEquation>. This experimental evaluation conclusively demonstrates that the MOQSHO method generates significantly superior results. In the next step, we validated the performance of the MOQSHO on the real-world biparty multi-objective UAV path planning (BP-UAVPP) problem, where it showed good results over the baseline multi-objective techniques. Finally, we extended our investigation by applying the MOQSHO algorithm to the NARM problem and comparing it with other innovative and successful algorithms. The results of this comparison reveal that the proposed MOQSHO algorithm significantly outperforms its counterparts, demonstrating its exceptional efficiency and relevance in the context of numerical association rule mining.</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

Quantum-Inspired Multi-Objective Seahorse Optimizer for Predictive Maintenance Analysis Using Numerical Association Rule Mining

  • 期刊论文

  • 发表日期：

    2025年7月9日

查看全文
  • Salma Yacoubi,
  • Ghaith Manita,
  • Amit Chhabra,
  • Diego Oliva,
  • Ouajdi Korbaa

摘要

In this study, we developed a revolutionary algorithm called Quantum-inspired Multi-Objective Seahorse Optimizer (MOQSHO) for tackling Numerical Association Rule Mining (NARM) problem, which is a particular case of Association Rule Mining (ARM). The challenge inherent in NARM can be approached along three distinct axes: distribution, discretization, and optimization. Traditional single-objective SHO, a bio-inspired metaheuristic optimization method, has shown competitive performance in many complex problems. Still, it needs to tackle multiple objectives of the NARM problem and tends to be stuck in local optima. We propose an optimization-based MOQSHO algorithm to overcome SHO deficiencies by integrating the quantum mechanics in traditional SHO and enhancing its ability to simultaneously handle multiple objectives of the NARM problem. Quantum mechanics helps to improve traditional SHO algorithms’ exploitation and exploration abilities. To evaluate the performance of the MOQSHO algorithm, we undertook a series of tests, using measures such as generational distance (GD), inverse generational distance (IGD), hypervolume (HV), spacing, spread, and \(\Delta _p\) Δ p . This experimental evaluation conclusively demonstrates that the MOQSHO method generates significantly superior results. In the next step, we validated the performance of the MOQSHO on the real-world biparty multi-objective UAV path planning (BP-UAVPP) problem, where it showed good results over the baseline multi-objective techniques. Finally, we extended our investigation by applying the MOQSHO algorithm to the NARM problem and comparing it with other innovative and successful algorithms. The results of this comparison reveal that the proposed MOQSHO algorithm significantly outperforms its counterparts, demonstrating its exceptional efficiency and relevance in the context of numerical association rule mining.