Capturing waste collection planning expert knowledge in a fitness function through preference learning
作者: Laura Fernández Díaz, Miriam Fernández Díaz, José Ramón Quevedo, Elena Montañés
分类: cs.LG, cs.AI
发布日期: 2024-02-02
期刊: Engineering Applications of Artificial Intelligence 2021 Volume 99 104113
DOI: 10.1016/j.engappai.2020.104113
💡 一句话要点
通过偏好学习构建废物收集规划的适应度函数
🎯 匹配领域: 支柱二：RL算法与架构 (RL & Architecture)
关键词: 废物收集 适应度函数 偏好学习 规划优化 关键绩效指标 专家知识 特征选择
📋 核心要点
- 现有废物收集规划方法依赖专家经验，缺乏全局优化，导致效率低下。
- 本文通过偏好学习构建适应度函数，利用专家知识和关键绩效指标来优化规划过程。
- 实验结果显示，选取6或8个指标时，C-index提升至98%，明显优于其他方法。
📝 摘要（中文）
本文针对COGERSA废物收集过程进行研究。以往专家通过试错机制手动设计该过程，导致规划未能全局优化。规划优化算法通常需要适应度函数来评估路线规划质量，但由于过程复杂，专家难以直接提出有效的适应度函数。本文旨在通过偏好框架构建适应度函数，充分利用专家知识。根据专家意见，建立多个关键绩效指标及其偏好判断，特别是指标的可加性使得处理路线变得更加可行。实验结果表明，当选取6或8个指标时，最佳C-index达到98%，显著优于现有方法。
🔬 方法详解
问题定义：本文解决的是废物收集过程中的适应度函数构建问题。现有方法依赖专家经验，缺乏系统性和全局优化，导致规划效果不佳。
核心思路：论文提出通过偏好学习构建适应度函数，利用专家的知识和经验来定义关键绩效指标，并通过偏好判断来优化规划过程。这样的设计使得复杂的适应度函数构建变得更加可行和有效。
技术框架：整体架构包括数据收集、专家偏好判断、关键绩效指标的选择与分析、适应度函数的构建及优化算法的应用。主要模块包括专家访谈、指标分析和优化算法实现。
关键创新：最重要的创新在于通过偏好学习方法构建适应度函数，充分利用专家知识，且通过可加性特性简化了处理过程，与传统方法相比，显著提升了规划效果。
关键设计：在指标选择中，进行了特征选择分析，发现6或8个指标的组合效果最佳。关键绩效指标包括卡车负载和非主干道路的行驶距离，设计了相应的评估标准和损失函数以优化适应度函数。
🖼️ 关键图片
📊 实验亮点
实验结果显示，所提出的方法在C-index评估中达到了98%，相比于传统方法的72%至90%有显著提升，证明了偏好学习在废物收集规划中的有效性。
🎯 应用场景
该研究的潜在应用领域包括城市废物管理、物流优化和智能交通系统。通过构建有效的适应度函数，可以显著提高废物收集的效率，降低运营成本，未来可能对城市环境管理产生积极影响。
📄 摘要（原文）
This paper copes with the COGERSA waste collection process. Up to now, experts have been manually designed the process using a trial and error mechanism. This process is not globally optimized, since it has been progressively and locally built as council demands appear. Planning optimization algorithms usually solve it, but they need a fitness function to evaluate a route planning quality. The drawback is that even experts are not able to propose one in a straightforward way due to the complexity of the process. Hence, the goal of this paper is to build a fitness function though a preference framework, taking advantage of the available expert knowledge and expertise. Several key performance indicators together with preference judgments are carefully established according to the experts for learning a promising fitness function. Particularly, the additivity property of them makes the task be much more affordable, since it allows to work with routes rather than with route plannings. Besides, a feature selection analysis is performed over such indicators, since the experts suspect of a potential existing (but unknown) redundancy among them. The experiment results confirm this hypothesis, since the best $C-$index ($98\%$ against around $94\%$) is reached when 6 or 8 out of 21 indicators are taken. Particularly, truck load seems to be a highly promising key performance indicator, together to the travelled distance along non-main roads. A comparison with other existing approaches shows that the proposed method clearly outperforms them, since the $C-$index goes from $72\%$ or $90\%$ to $98\%$.