A Particle Swarm Optimizer with Randomized Quasi-Random and General Recognition

摘要：

In order to improve the convergent speed and raise the accurate level of solutions further, in this study, we present a novel particle swarm optimizer, called Particle Swarm Optimizer with randomized quasi-random initialization and general recog- nition. The proposed algorithm uses Quasi-random sequence to initialize the population for a more uniform population distribu- tion. Cauchy distribution and general recognition are employed to enrich the diversity of particles in runs. The experimental results show that the accurate level of the optima and the convergent speed both are outperformed than the algorithms initialize with a pseudo-random sequence.

关键词： Particle Swarm Optimizer Initialization Strat-egy Quasi-Random Sequence Cauchy Distribution General Recognition

作者: Hao Li Xinan Wu

作者单位: Department of Computer ScienceZhejiang University of TechnologyHangzhou, China Department of Research Nanjing Fujitsu Nanda Software Tech. Co., Ltd. Nanjing, China

会议类型: 国际会议

会议名称: 2010 3rd International Conference on Advanced Computer Theory and Engineering(2010年第三届先进计算机理论与工程国际会议 ICACTE 2010)

会议地点: 成都

会议语种:英文

页码: 1-5

在线出版日期: 2010-08-20（万方平台首次上网日期，不代表论文的发表时间）