【摘要】 提出了一种改进的自适应蚁群聚类算法(improved adaptive ant clustering,IAAC)。该算法改进了原来的AM(ant movement)模型,并在此基础上提出了一种网格化的移动策略来改善蚂蚁移动的随机性,使蚂蚁有意识地往模式较多的区域移动,极大地减少了蚂蚁无效的移动,使蚂蚁迅速地找到合适的位置放下模式;并提出了一种自适应调整蚂蚁运动阈值的方法以简化参数的选取,使得算法可以根据当前的聚类情况不断调整阈值,以达到更好的聚类结果。结果表明,该算法具有运行效率高、参数选取简单及自适应性等优点。更多还原

【Abstract】 This paper proposed an improved adaptive ant clustering algorithm(IAAC).IAAC was improved from AM(ant movement) model.To reduce the randomness of ant’s movement,a tactics of partitioning the area into some grids was came up to guide the ant’s movement to reach the grids including more data objects.In this way,the ant’s movement was much more effective and the ants could quickly find the suitable position.Moreover,resented a method to self-adaptively adjust the threshold of ant’s movement according to the current situation,which simplified the parameter’s selection.The results show that the proposed algorithm has high efficiency,simple parameters and adaptivity.更多还原