| 多目标进化算法性能评价指标综述 |
| |
| 引用本文： | 胡 涵,李振宇.多目标进化算法性能评价指标综述[J].教育技术导刊,2019,18(9):1-4. |
| |
| 作者姓名： | 胡 涵 李振宇 |
| |
| 作者单位： | 南京航空航天大学 计算机科学与技术学院，江苏 南京 210016 |
| |
| 基金项目： | 国家自然科学基金青年项目（61300159）；江苏省自然科学基金项目（SBK2018022017） |
| |
| 摘 要： | 多目标进化算法常用于解决较复杂的多目标优化问题，该类算法是基于种群的进化算法，通过产生一组近似Pareto最优解集满足决策者偏好。介绍了多目标优化问题背景知识及相关定义，根据评价指标衡量解集特性，将现有算法性能评价指标分为3类并分别进行阐述，分析、比较其特点与区别。
|
| 关 键 词： | 多目标优化 进化算法 评价指标 最优解集 |
| 收稿时间： | 2019-01-16 |
A Survey of Performance Indicators for Multi-objective Evolutionary Algorithms |
| |
| HU Han,LI Zhen-yu.A Survey of Performance Indicators for Multi-objective Evolutionary Algorithms[J].Introduction of Educational Technology,2019,18(9):1-4. |
| |
| Authors: | HU Han LI Zhen-yu |
| |
| Institution: | School of Computer Science and Technology， Nanjing University of Aeronautics and Astronautics， Nanjing 210016， China |
| |
| Abstract: | Multi-objective evolutionary algorithms are often used to solve complex multi-objective optimization problems. The algorithms are population-based evolutionary algorithms that satisfy decision makers' preferences by generating a set of approximate Pareto optimal solution sets. This paper introduces the background knowledge and related definitions in multi-objective optimization problems. According to the characteristics of the solution set measured by the evaluation indicators， the existing algorithm performance indicators are divided into three categories and elaborated separately， and their specifics are analyzed and some differences between them are compared. |
| |
| Keywords: | multi-objective optimization evolutionary algorithms performance indicator optimal solution set |
|
| 点击此处可从《教育技术导刊》浏览原始摘要信息 |
| 点击此处可从《教育技术导刊》下载免费的PDF全文 |
