Locust Behaved Particle Swarm Optimization Technique

• 作 者: WeiminZhong;XueqinXie;YiLiang;NaLuo;JuanZhang;FengQian;
• 机 构: East China University of Science and Technology,China
• 出 处: 第三届先进计算智能与智能信息学国际研讨会(The Third International Workshop on Adv
• 发表日期: 2013年期

　　The collective behavior of certain animals and insects has the characteristic of self-organization.The simple interactions among individuals can produce complex adaptive patterns at the level of the group.Recently,new scientific investigation pointed out that desert locusts show extreme phenotypic plasticity in transforming between the lonely phase and the swarming gregarious phase depending on the population density,which is controlled by a serotonin called 5-hydroxytryptamine.In this paper,based on the mechanism of the locusts collective behavior,a new particle swarm optimization technique called LBPSO is studied.The number of swarms is self-adaptively adjusted by the acquired outstanding particles coming from behind the previous global best solution.The swarm sizes are related to the corresponding serotonin 5-hydroxytryptamine which is determined by the optimization parameters such as global best,iteration number etc.And each swarm adopts one of three rules below according to its density,generalized social evolution strategy,generalized cognition evolution strategy and the independent moving strategy.A comparative study of LBPSO,SPSO,Improved SPSO and the original PSO on their ability of tracking optima is carried out.And the results under four static benchmark functions and a dynamic function generator MPB show that LBPSO outperforms the other three functions in both static and dynamic landscapes due to the introduced locusts collective behavior.