Directional Pareto Front and Its Estimation to Encourage Multi-Objective Decision-Making
Directional Pareto Front and Its Estimation to Encourage Multi-Objective Decision-Making
复制标题
DOI：
10.1109/access.2023.3250238
复制
发表时间：
2023
期刊：
影响因子：
3.9
通讯作者：
Tomoaki Takagi;K. Takadama;Hiroyuki Sato
中科院分区：
文献类型：
--
作者：
Tomoaki Takagi;K. Takadama;Hiroyuki Sato
这项工作引入了以下概念的方向和估计方向帕累托前沿鼓励多目标决策，特别是当帕累托前沿存在于有限的区域中的目标空间。多目标优化的一般输出是一组近似Pareto前沿的非支配解。当帕累托前沿存在于有限的区域，很少的解决方案，并提供给决策者。代表目标值权衡的有限输出是多目标决策的障碍。本研究中引入的方向性帕累托前沿是帕累托前沿的超集，补充了帕累托前沿之间的客观价值权衡。估计的方向性帕累托前沿是使用有限数量的点来表示方向性帕累托前沿的响应表面，这些点是所获得的解的目标向量。实验结果表明，方向帕累托前沿和估计前沿提供了一个客观的价值权衡，即使在帕累托前沿不存在的地区，并提高了目标问题的目标空间的解释。
This work introduces the following concepts of directional and estimated directional Pareto front to encourage multi-objective decision making, especially when the Pareto front exists in limited regions in the objective space. The general output of multi-objective optimization is a set of non-dominated solutions to approximate the Pareto front. When the Pareto front exists in limited regions, few solutions are obtained and presented to the decision maker. The limited output representing the objective value trade-off is a barrier to multi-objective decision making. The directional Pareto front introduced in this study is a superset of the Pareto front and supplements the objective value trade-off between the Pareto fronts. The estimated directional Pareto front is a response surface that represents the directional Pareto front using a limited number of points, which are objective vectors of the obtained solutions. The experimental results show that the directional Pareto front and the estimated front provide an objective value trade-off even in areas where the Pareto front does not exist and enhances the explanation of the objective space of the target problem.