计算机应用 ›› 2013, Vol. 33 ›› Issue (02): 311-315.DOI: 10.3724/SP.J.1087.2013.00311

• 先进计算 • 上一篇    下一篇

改进的带经验因子的二进制粒子群优化算法

曹义亲1,张贞1,黄晓生2   

  1. 1. 华东交通大学 软件学院,南昌 330013
    2. 华东交通大学 信息工程学院,南昌 330013
  • 收稿日期:2012-08-06 修回日期:2012-09-17 出版日期:2013-02-01 发布日期:2013-02-25
  • 通讯作者: 曹义亲
  • 作者简介:曹义亲(1964-),男,江西都昌人,教授,主要研究方向:图像处理、模式识别;
    张贞(1988-),女,云南昆明人,硕士研究生,主要研究方向:粒子群优化算法、多智能体联盟形成算法;
    黄晓生(1972-),男,江西于都人,副教授,博士,主要研究方向:图像处理、机器视觉。
  • 基金资助:
    江西省教育厅科技项目;江西省自然科学基金资助项目;江西省研究生创新专项资金资助项目;江西省科技支撑计划项目

Improved binary particle swarm optimization algorithm with experience factor

CAO Yiqin1,ZHANG Zhen1,HUANG Xiaosheng2   

  1. 1. School of Software, East China Jiaotong University, Nanchang Jiangxi 330013, China
    2. School of Information Engineering, East China Jiaotong University, Nanchang Jiangxi 330013, China
  • Received:2012-08-06 Revised:2012-09-17 Online:2013-02-01 Published:2013-02-25
  • Contact: CAO Yiqin
  • Supported by:
    Research On Multi-Agent Coalition Formation Algorithm Based on Swarm Intelligence;Region-based algorithm for non-sampling morphological wavelet medical image fusion

摘要: 针对传统二进制粒子群优化(BPSO)算法未充分利用粒子位置的历史信息辅助迭代寻优,从而影响算法寻优效率的进一步提高的问题,提出一种改进的带经验因子的BPSO算法。该算法通过引入反映粒子位置历史信息的经验因子来影响粒子速度的更新,从而引导粒子寻优。为避免粒子对历史信息的过度依赖,算法通过赏罚机制和历史遗忘系数对其进行调节,最后通过经验权重决定经验因子对速度更新的影响。仿真实验结果表明,与经典BPSO算法以及相关改进算法相比,新算法无论在收敛速度还是全局搜索能力上,都能达到更好的效果。

关键词: 二进制粒子群优化, 历史信息, 赏罚机制, 经验因子, 经验权重

Abstract: The traditional Binary Particle Swarm Optimization (BPSO) algorithm does not make full use of the historical position information for its iterative optimization, which impedes further improvement on the efficiency of the algorithm. To deal with the problem, an improved BPSO algorithm with the experience factor was proposed. The new algorithm exploited the experience factor, which could reflect the historical information of particle's position, to influence the speed update of particles and therefore improved the optimization process. In order to avoid the excessive dependence on the historical experience information of particles, the algorithm regulated the historical information through the reward and punishment mechanism and a history-forgotten coefficient, and in the end, empirical weights were used to determine the final effect on the experience factor. Compared with the classic BPSO and related improved algorithm, the experimental results show that the new algorithm can achieve better effects both in convergence speed and global search ability.

Key words: Binary Particle Swarm Optimization (BPSO), historical information, reward and punishment mechanism, experience factor, empirical weight

中图分类号: