A Hybrid PBIL-Based Krill Herd Algorithm

被引：5
作者：
Wang, Gai-Ge [1 ]
Deb, Suash [2 ]
Gandomi, Amir H. [3 ]
Alavi, Amir H. [4 ]
机构：
[1] Jiangsu Normal Univ, Sch Comp Sci & Technol, Xuzhou, Peoples R China
[2] Cambridge Inst Technol, Dept Comp Sci & Engn, Ranchi, Bihar, India
[3] Michigan State Univ, BEACON Ctr Study Evolut Act, E Lansing, MI 48824 USA
[4] Michigan State Univ, Dept Civil & Environm Engn, E Lansing, MI 48824 USA
来源：
2015 3RD INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL AND BUSINESS INTELLIGENCE (ISCBI 2015) | 2015年
关键词：
Global optimization problem; Krill herd; Population-based incremental learning; Multimodal function; PARTICLE SWARM OPTIMIZATION; BIOGEOGRAPHY-BASED OPTIMIZATION; HARMONY SEARCH ALGORITHM; DIFFERENTIAL EVOLUTION; FIREFLY ALGORITHM; BAT ALGORITHM; DESIGN; STRATEGY;
D O I：
10.1109/ISCBI.2015.14
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
When krill herd (KH) is used to solve complicated multimodal functions, sometimes it fails to find the best solutions and cannot converge fast. Herein, we propose a hybrid KH method, called PBILKH, by integrating the KH with the population-based incremental learning (PBIL). In addition, a type of elitism is applied to memorize the krill with the best fitness when finding the best solution. The effectiveness of the PBILKH is verified by various benchmarks and experimental results demonstrate that our PBILKH is well capable of overtaking the KH algorithm and other optimization methods in solving nonlinear problems.
引用
收藏
页码：39 / 44
页数：6
相关论文
共 74 条
  • [1] [Anonymous], NEURAL COMPUTING APP
  • [2] [Anonymous], 1995, CMUCS95193
  • [3] [Anonymous], SOFT COMPUTING
  • [4] [Anonymous], 2012, INT J BIOINSPIRED CO
  • [5] [Anonymous], 2013, NEURAL COMPUT APPL, DOI DOI 10.1007/s00521-011-0684-5
  • [6] [Anonymous], NEURAL COMPUTING APP
  • [7] [Anonymous], P 5 INT C PAR PROBL
  • [8] [Anonymous], 2014, BIORESOUR BIOPROCESS
  • [9] [Anonymous], CUCKOO SEARCH VIA LE
  • [10] [Anonymous], THEORY EVOLUTION STR
12345678