Enhancing Clearing-based Niching Method Using Delaunay Triangulation

被引:0
|
作者
Kalra, Shivam [1 ]
Rahnamayan, Shahryar [2 ]
Deb, Kalyanmoy [3 ]
机构
[1] Univ Waterloo, Dept Syst Design Engn, Waterloo, ON, Canada
[2] Univ Ontario Inst Technol, Dept Elect Comp & Software Engn, Oshawa, ON, Canada
[3] Michigan State Univ, Dept Elect & Comp Engn, E Lansing, MI 48824 USA
来源
2017 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC) | 2017年
基金
加拿大自然科学与工程研究理事会;
关键词
MULTIMODAL OPTIMIZATION; ALGORITHMS;
D O I
暂无
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
The interest in multi-modal optimization methods is increasing in the recent years since many of real-world optimization problems have multiple/many optima and decision makers prefer to find all of them. Multiple global/local peaks create difficulties for optimization algorithms. In this context, niching is well-known and widely used technique for finding multiple solutions in multi-modal optimization. One commonly used niching technique in evolutionary algorithms is the Clearing method. However, canonical clearing scheme reduces the exploration capacity of the evolutionary algorithms. In this paper, Delaunay Triangulation based Clearing (DT-Clearing) procedure is proposed to handle multi-modal optimizations more efficiently while preserving simplicity of canonical clearing approach. In DTC-learing, cleared individuals are reallocated in the biggest empty spaces formed within the search space which are determined through Delaunay Triangulation. The reallocation of cleared individuals discourages wasting of the resources and allows better exploration of the landscape. The algorithm also uses an external memory, an archive of the explored niches, thus preventing the redundant visiting of the individuals, henceforth finding more solutions in lesser number of generations. The method is tested using multi-modal benchmark problems proposed for the IEEE CEC 2013, Special Session on Niching Methods for Multimodal Optimization. Our method obtains promising results in comparison with the canonical clearing and demonstrates to be a competitive niching algorithm.
引用
收藏
页码:2328 / 2337
页数:10
相关论文
共 50 条
  • [41] Fingerprint indexing based on expanded Delaunay triangulation
    Khodadoust, Javad
    Khodadoust, Ali Mohammad
    EXPERT SYSTEMS WITH APPLICATIONS, 2017, 81 : 251 - 267
  • [42] Effective corner matching based on Delaunay triangulation
    Zhou, DX
    Li, GH
    Liu, YH
    2004 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1- 5, PROCEEDINGS, 2004, : 2730 - 2735
  • [43] Endpoint Triangle's Circumcircle Method in Delaunay Triangulation
    Zhao, Yuxin
    Tian, Fengmin
    INTERNATIONAL JOINT CONFERENCE ON COMPUTATIONAL SCIENCES AND OPTIMIZATION, VOL 2, PROCEEDINGS, 2009, : 264 - 268
  • [44] Tissue clearing-based method for unobstructed three-dimensional imaging of mouse penis with subcellular resolution
    Matryba, Pawel
    Wolny, Artur
    Pawlowska, Monika
    Sosnowska, Anna
    Rydzynska, Zuzanna
    Jasinski, Marcin
    Stefaniuk, Marzena
    Golab, Jakub
    JOURNAL OF BIOPHOTONICS, 2020, 13 (07)
  • [45] Market Clearing-based Dynamic Multi-agent Task Allocation
    Nelke, Sofia Amador
    Okamoto, Steven
    Zivan, Roie
    ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2020, 11 (01)
  • [46] A New Receiver Placement Scheme Using Delaunay Refinement-based Triangulation
    Basheer, Mohammed Rana
    Jagannathan, S.
    2010 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC 2010), 2010,
  • [47] Dots and Incipient based Fingerprint Matching Scheme using FMM and Delaunay Triangulation
    Swain, Satyabrata
    Majhi, Banshidhar
    Dash, Ratnakar
    Sa, Pankaj Kumar
    2014 9TH INTERNATIONAL CONFERENCE ON INDUSTRIAL AND INFORMATION SYSTEMS (ICIIS), 2014, : 168 - 173
  • [48] Classification of Endoscopic Images Using Delaunay Triangulation-Based Edge Features
    Haefner, M.
    Gangl, A.
    Liedlgruber, M.
    Uhl, A.
    Vecsei, A.
    Wrba, F.
    IMAGE ANALYSIS AND RECOGNITION, 2010, PT II, PROCEEDINGS, 2010, 6112 : 131 - +
  • [49] Clothing segmentation using foreground and background estimation based on the constrained Delaunay triangulation
    Hu, Zhilan
    Yan, Hong
    Lin, Xinggang
    PATTERN RECOGNITION, 2008, 41 (05) : 1581 - 1592
  • [50] DTNNM: A windows program for strain analysis using the Delaunay triangulation nearest neighbour method
    Mulchrone, KF
    COMPUTERS & GEOSCIENCES, 2005, 31 (08) : 978 - 988