J4 ›› 2012, Vol. 30 ›› Issue (1): 56-59.

• 论文 • 上一篇    下一篇

混合群智能算法在模体识别中的应用

杨柳1,刘铁英2,李雪莲3   

  1. (1.吉林工商学院 信息工程分院|长春 130062;2.长春职业技术学院 信息分院|长春 130033;3.吉林省财政厅 吉林省财税信息中心|长春 130021)
  • 收稿日期:2011-09-01 出版日期:2012-01-29 发布日期:2012-03-20
  • 作者简介:杨柳 (1979—)|女|长春人|吉林工商学院讲师|硕士|主要从事智能算法研究|(Tel)86-15584279857(E-mail)yangliu7025@sina.com。
  • 基金资助:

    吉林省教育厅“十二五”科学技术研究基金资助项目(吉教科合字[2012]第371号)

Application of |Hybrid Swarm Intelligence Alogrithm on Finding Motif Problem

YANG Liu1,LIU Tie-ying2,LI Xue-lian3   

  1. 1.Department of Information Engineering,Jilin Business and Technology College,Changchun 130062,China;2.School of Information Technology|Changchun Vocational Institute of Technology|Changchun 130033,China;3.Jilin Taxation Information Center,Jilin Provincial Finance Department|Changchun 130021,China
  • Received:2011-09-01 Online:2012-01-29 Published:2012-03-20

摘要:

为了避免传统吉布斯算法的诸多缺陷,提高算法的求解能力,对蚁群算法(ACO:Ant Colony Optimization)进行了改进:引入粒子群算法(PSO:Particle Swarm Optimization)动态调节ACO函数中的参数获得最优解。在奔腾PC机的实验平台上、Windows 2003 Server操作系统下、开发工具为VB的模拟实验中,结果证明,混合的群智能算法使经典旅行商问题求解的计算时间缩短,提高了算法的收敛速度,有较好的发展前景。利用PSO处理连续优化问题的优点,将混合算法应用于生物信息学的模体识别中,可实现更加快速的基序发现处理。

关键词: 吉布斯算法, 粒子群算法, 模体识别

Abstract:

In order to avoid many Gibbs algorithm defects,improve the ability of problem solving,improvements the ACO (Ant Colony Optimization):PSO (Particle Swarm Optimization) is made to optimize the parameters in the ACO.Pentium PC machine is the  experiment platform,operating system is Windows 2003 Server,development tools is  VB,the  traveling salesman problem is tsimalated.Results show that the computing time of the algorithm can be reduced by new methods.It had great effects in practicality and rapid processing of motif discovary.

Key words: Gibbs algorithn, particle swarm optimization, finding motif

中图分类号: 

  • TP313