计算机工程与应用 ›› 2016, Vol. 52 ›› Issue (9): 126-129.

• 模式识别与人工智能 • 上一篇    下一篇

病毒进化理论人工蜂群算法研究

程  勇1,2,同向前1   

  1. 1.西安理工大学 电气工程博士后流动站,西安 710048
    2.西安科技大学,西安 710054
  • 出版日期:2016-05-01 发布日期:2016-05-16

Research on Artificial Bee Colony with virus evolution theory

CHENG Yong 1,2, TONG Xiangqian1   

  1. 1.Electric Engineering Postdoctoral Research Flow Station, Xi’an University of Technology, Xi’an 710048, China
    2.Xi’an University of Science and Technology, Xi’an 710054, China
  • Online:2016-05-01 Published:2016-05-16

摘要: 为了提高人工蜂群算法的搜索性能,引入了连续状态下的生物病毒机制和宿主与病毒基于感染操作等思想优化人工蜂群算法搜索机制。人工蜂群算法具有控制参数少、实现简单的优点,但是由于蜂群收敛采用局部搜索,使得算法易于早熟收敛或者陷入局部最优值。通过病毒进化对人工蜂群算法进化机制的分析,利用病毒的感染与进化,建立精英雇佣蜂对懒惰蜂引导,提高人工蜂群算法的搜索性能,加强群体的多样性,提高了局部搜索能力。仿真实验表明这种方法较常见的人工蜂群算法,有较明显收敛速度和搜索精度改进。

关键词: 人工蜂群算法, 病毒, 进化, 局部最优值, 收敛

Abstract: For improving searching ability of ABC(Artificial Bee Colony), this paper proposes VEABC(Virus Evolution Artificial Bee Colony) based on bio-virus mechanism and infection based operation between host and virus in continuous state. Classic ABC has fast convergent speed, but it easily falls into premature convergences and local optimal solution. Modified ABC utilizes the virus horizontal infection and vertical propagation ability to enhance its variety of bee population, which is based on virus co-evolutionary, elite and lazy employed bee base. Experiments show that the virus infection operation strengthens the local search ability in the solution space and the precision obviously outperforms several other algorithms.

Key words: Artificial Bee Colony(ABC), virus, evolution, local optimal solution, convergence