计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (32): 54-55.

• 研究、探讨 • 上一篇    下一篇

多信息结合离散粒子群算法及其应用

任小波1,陈舒骅2   

  1. 1.宁波工程学院 电子与信息工程学院,浙江 宁波 315016
    2.武汉大学 计算机学院,武汉 430072
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-11-11 发布日期:2011-11-11

More information with discrete particle swarm algorithm and its application

REN Xiaobo1,CHEN Shuhua2   

  1. 1.College of Electronic and Information Engineering,Ningbo University of Technology,Ningbo,Zhejiang 315016,China
    2.School of Computer,Wuhan University,Wuhan 430072,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-11-11 Published:2011-11-11

摘要: 为提高粒子群算法的搜索性能,提出了一种改进的离散粒子群算法:多信息结合离散粒子群算法。该算法在粒子群算法的基础上借鉴蚁群算法的信息素机制,重新定义了粒子的速度位置更新公式,并且引入双曲正切函数对粒子群进行初始化。通过求解背包问题对算法进行验证,实验结果表明所提算法性能较优。

关键词: 离散粒子群算法, 信息素机制, 双曲正切函数, 背包问题

Abstract: To improve the search capability of particle swarm algorithm,an improved discrete particle swarm optimization algorithm is proposed and named as More Information with discrete Particle Swarm algorithm(MIPSO).The idea of pheromone refresh mechanism of ant colony algorithm is used and the update equations of the speed and position of particles are redefined and a hyperbolic tangent function is used to initialize the particle swarm on the basis of PSO algorithm.This algorithm is verified by solving knapsack problem,the results of the experiment show that the proposed algorithm can result in better profits.

Key words: discrete particle swarm algorithm, pheromone refresh, hyperbolic tangent function, knapsack problem