模式识别与人工智能
2025年4月3日 星期四   首 页     期刊简介     编委会     投稿指南     伦理声明     联系我们                                                                English
模式识别与人工智能  2020, Vol. 33 Issue (3): 191-201    DOI: 10.16451/j.cnki.issn1003-6059.202003001
论文与报告 最新目录| 下期目录| 过刊浏览| 高级检索 |
基于参考点选择策略的改进型NSGA-III算法
耿焕同1,2, 戴中斌1, 王天雷1, 许可1
1.南京信息工程大学 计算机与软件学院 南京 210044;
2.江苏省气象局 南京大气科学联合研究中心 南京 210009
Improved NSGA-III Algorithm Based on Reference Point Selection Strategy
GENG Huantong1,2, DAI Zhongbin1, WANG Tianlei1, XU Ke1
1.School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing 210044;
2.Nanjing Joint Center of Atmospheric Research, Meteorological Bureau of Jiangsu Province, Nanjing 210009

全文: PDF (1425 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 针对多目标进化算法忽视种群在决策空间的分布信息,未考虑待优化问题Pareto前沿形状的问题,文中提出基于参考点选择策略的改进型NSGA-III算法.首先,根据种群在决策空间的分布特征,借助信息论中的熵思想,计算相邻两代种群的熵差,判定种群的进化阶段.然后,根据种群在目标空间的分布特征,借助参考点关联个体数目的统计信息,评估参考点的重要性.最后,在种群进化的中后期,依据参考点的重要性特征剔除冗余的无效参考点,使保留的参考点适应种群规模与Pareto前沿面,利用筛选后的参考点引导种群进化方向,加快算法收敛及优化效率.在测试函数集上的对比实验表明,文中算法在收敛性和分布性上均较优.
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
耿焕同
戴中斌
王天雷
许可
关键词 多目标优化参考点决策空间分布目标空间分布    
Abstract:The traditional multi-objective evolutionary algorithm ignores distribution information of the population in the decision space and Pareto front shape of the optimization problem is not taken into account. To solve the problems, an improved NSGA-III algorithm based on reference point selection strategy is proposed. Firstly, according to the entropy thought in information theory, the entropy difference between two adjacent generations is calculated in line with the distribution characteristics of the population in the decision-making space, and the evolutionary status of the population is determined. Then, in the light of the distribution characteristics of the population in the target space, the importance of reference points is evaluated via statistical information of the number of the individuals associated with reference points. Finally, redundant and invalid reference points are removed according to the importance characteristics of reference points in the middle and late period of population evolution. Reserved reference points can adapt to the population size and Pareto frontier, and the selected reference points are exploited to guide the evolution direction of the population and accelerate the convergence and optimization efficiency. Experiments on test function sets indicate the significant advantages of the proposed algorithm in convergence and distribution.
Key wordsMulti-objective Optimization    Reference Point    Decision Space Distribution    Target Space Distribution   
收稿日期: 2020-01-03     
ZTFLH: TP 183  
基金资助:南京大气科学联合研究中心(No.NJCAR2018MS05)、国家自然科学基金项目(No.51977100)资助
通讯作者: 耿焕同,博士,教授,主要研究方向为计算智能、多目标优化、气象数据挖掘.E-mail:htgeng@nuist.edu.cn.   
作者简介: 戴中斌,硕士研究生,主要研究方向为多目标优化.E-mail:1209805090@qq.com. 王天雷,硕士研究生,主要研究方向为深度学习.E-mail:609294510@qq.com. 许 可,硕士研究生,主要研究方向为多目标优化.E-mail:1327381035@qq.com.
引用本文:   
耿焕同, 戴中斌, 王天雷, 许可. 基于参考点选择策略的改进型NSGA-III算法[J]. 模式识别与人工智能, 2020, 33(3): 191-201. GENG Huantong, DAI Zhongbin, WANG Tianlei, XU Ke. Improved NSGA-III Algorithm Based on Reference Point Selection Strategy. , 2020, 33(3): 191-201.
链接本文:  
http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202003001      或     http://manu46.magtech.com.cn/Jweb_prai/CN/Y2020/V33/I3/191
版权所有 © 《模式识别与人工智能》编辑部
地址:安微省合肥市蜀山湖路350号 电话:0551-65591176 传真:0551-65591176 Email:bjb@iim.ac.cn
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn