|
|
【答案】应助回帖
★ ★ ★ ★ ★
感谢参与，应助指数 +1
hylz1008: 金币+5 2014-12-17 23:24:37
oven1986: LS-EPI+1, 感谢应助。 2014-12-18 18:29:50
number:
20132516429338
Title:
Hill-climbing and pattern ant colony hybrid Bayesian optimization algorithm
Authors:
Hu, Yun'an1 ; Liu, Zhen1; Song, Ruihua2; Shi, Jianguo3
Author affiliation:
1Department of Control Engineering, Naval Aeronautical and Astronautical University, Yantai 264001, Shandong, China
2Department of Training, Naval Aeronautical and Astronautical University, Yantai 264001, Shandong, China
3Department of Ordnance Science and Technology, Naval Aeronautical and Astronautical University, Yantai 264001, Shandong, China
Corresponding author:
Hu, Y. (hya507@sina.com)
Source title:
Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition)
Abbreviated source title:
Huazhong Ligong Daxue Xuebao
Volume:
41
Issue:
5
Issue date:
May 2013
Publication year:
2013
Pages:
90-95
Language:
Chinese
ISSN:
16714512
Document type:
Journal article (JA)
Publisher:
Huazhong University of Science and Technology, Wuhan, Hubei, 430074, China
Abstract:
To overcome the low evolution efficiency and long convergence time in the traditional Bayesian optimization algorithm (BOA), a new hybrid BOA was proposed. The fitness inherence and individual local search were incorporated in the new algorithm to enhance the evolution efficiency. In order to promote the construction speed of Bayesian network structure, hill-climbing and pattern ant colony was used to learn the structure of Bayesian network. The convergence of new hybrid BOA was also analyzed in the paper. The simulation results of benchmark functions show that the new hybrid algorithm performs well than before in promoting the precision and reducing the time complexity. The new algorithm was used to target allocation problem. The validity and superiority of the algorithm were also proved by the simulation results.
Number of references:
14
Main heading:
Algorithms
Controlled terms:
Bayesian networks
Uncontrolled terms:
Ant colony algorithms - Bayesian optimization algorithms - Hill-climbing methods - Local search - Pattern - Target allocations
Classification code:
723 Computer Software, Data Handling and Applications - 921 Mathematics - 921.4 Combinatorial Mathematics, Includes Graph Theory, Set Theory
Database:
Compendex
Compilation and indexing terms, © 2014 Elsevier Inc.
Full-text and Local Holdings Links |
|
回复此楼