针对标准粒子群算法在求解路网问题时显现出易陷入局部极值的问题,根据高校地理数据,提出一种求解高校路网的逆序变异的新混合PSO算法。为平衡算法的全局和局部搜索能力及增强种群多样性,将一种自平衡策略作为变异条件,在产生新的群体...针对标准粒子群算法在求解路网问题时显现出易陷入局部极值的问题,根据高校地理数据,提出一种求解高校路网的逆序变异的新混合PSO算法。为平衡算法的全局和局部搜索能力及增强种群多样性,将一种自平衡策略作为变异条件,在产生新的群体中按照逆序变异率算子对粒子进行位置变异,从而使得粒子摆脱局部极值后继续进行迭代更新操作。以Visual Studio 2005中C++编程实现实验仿真,结果表明此算法不但能有效求解高校路网问题,而且新算法收敛精度高,有效克服了早熟收敛问题。展开更多
For the question that fuzzy c-means(FCM)clustering algorithm has the disadvantages of being too sensitive to the initial cluster centers and easily trapped in local optima,this paper introduces a new metric norm in FC...For the question that fuzzy c-means(FCM)clustering algorithm has the disadvantages of being too sensitive to the initial cluster centers and easily trapped in local optima,this paper introduces a new metric norm in FCM and particle swarm optimization(PSO)clustering algorithm,and proposes a parallel optimization algorithm using an improved fuzzy c-means method combined with particle swarm optimization(AF-APSO).The experiment shows that the AF-APSO can avoid local optima,and get the best fitness and clustering performance significantly.展开更多
文摘针对标准粒子群算法在求解路网问题时显现出易陷入局部极值的问题,根据高校地理数据,提出一种求解高校路网的逆序变异的新混合PSO算法。为平衡算法的全局和局部搜索能力及增强种群多样性,将一种自平衡策略作为变异条件,在产生新的群体中按照逆序变异率算子对粒子进行位置变异,从而使得粒子摆脱局部极值后继续进行迭代更新操作。以Visual Studio 2005中C++编程实现实验仿真,结果表明此算法不但能有效求解高校路网问题,而且新算法收敛精度高,有效克服了早熟收敛问题。
基金the China Agriculture Research System(No.CARS-49)Jiangsu College of Humanities and Social Sciences Outside Campus Research Base & Chinese Development of Strategic Research Base for Internet of Things
文摘For the question that fuzzy c-means(FCM)clustering algorithm has the disadvantages of being too sensitive to the initial cluster centers and easily trapped in local optima,this paper introduces a new metric norm in FCM and particle swarm optimization(PSO)clustering algorithm,and proposes a parallel optimization algorithm using an improved fuzzy c-means method combined with particle swarm optimization(AF-APSO).The experiment shows that the AF-APSO can avoid local optima,and get the best fitness and clustering performance significantly.