Scholarlink

<p>Artificial intelligence is revolutionizing construction management by enhancing productivity, safety, and decision-making in building projects. This research advances the fields of construction management and optimization by introducing the Opposition-Based Giant Pacific Octopus Optimizer (ObGPOO), a novel hybrid algorithm that integrates the Giant Pacific Octopus Optimizer with Opposition-Based Learning. This combination improves population initialization and updating mechanisms to effectively address the complex time–cost–quality–risk trade-off in construction projects. The ObGPOO was evaluated against state-of-the-art algorithms, including the Adaptive Opposition Slime Mold Algorithm and the Opposition-Based Salp Swarm Algorithm, using performance metrics such as Spacing Metric, Diversification Metric, Hypervolume, and Computational Time. Results demonstrate that ObGPOO exhibits superior convergence and diversification, providing a more robust and optimal solution compared to existing hybrid models. This study highlights the transformative potential of metaheuristic algorithms like ObGPOO in construction management, particularly in improving efficiency, adaptability, and sustainability while ensuring effective risk management. The findings underscore the significance of leveraging advanced optimization techniques to enhance decision-making and operational performance in complex construction scenarios.</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

Balancing the trade-off between quad-factors in construction management: a opposition-based Giant Pacific Octopus optimizer method

  • 期刊论文

  • 发表日期：

    2025年4月28日

查看全文
  • Pham Vu Hong Son,
  • Luu Ngoc Quynh Khoi

摘要

Artificial intelligence is revolutionizing construction management by enhancing productivity, safety, and decision-making in building projects. This research advances the fields of construction management and optimization by introducing the Opposition-Based Giant Pacific Octopus Optimizer (ObGPOO), a novel hybrid algorithm that integrates the Giant Pacific Octopus Optimizer with Opposition-Based Learning. This combination improves population initialization and updating mechanisms to effectively address the complex time–cost–quality–risk trade-off in construction projects. The ObGPOO was evaluated against state-of-the-art algorithms, including the Adaptive Opposition Slime Mold Algorithm and the Opposition-Based Salp Swarm Algorithm, using performance metrics such as Spacing Metric, Diversification Metric, Hypervolume, and Computational Time. Results demonstrate that ObGPOO exhibits superior convergence and diversification, providing a more robust and optimal solution compared to existing hybrid models. This study highlights the transformative potential of metaheuristic algorithms like ObGPOO in construction management, particularly in improving efficiency, adaptability, and sustainability while ensuring effective risk management. The findings underscore the significance of leveraging advanced optimization techniques to enhance decision-making and operational performance in complex construction scenarios.