【摘要】 多时段定时控制是城市交通信号控制的重要方式之一,交通时段的合理划分是制定多时段定时控制方案的基础.为克服传统时段划分方法的局限性,实现城市交通时段的自动划分,论文提取生物免疫系统的隐喻机制,基于免疫网络理论和克隆选择原理,建立了一种人工免疫数据聚类分析算法,并详细阐述了聚类算法在城市交通时段自动划分中的具体应用.实例分析表明,该算法可以有效减少聚类数据的冗余信息,特别适合于解决分级聚类等传统方法不适应的大数据量聚类问题,对解决城市交通时段的自动划分等数据聚类问题是可行的和有效的.更多还原

【Abstract】 Time of day control is one of the important control schemes in urban traffic signal control systems.The basic problem to run time of day control schemes is to program the traffic intervals rationally. To eliminate limitations of traditional interval programming methods and to program urban traffic intervals automatically,an artificial immune algorithm for data clustering is proposed in this paper.This work is mainly based on the immune network theory and the clone selection principle extracted from vertebrate immune systems.Experiments show that the given clustering algorithm can effectively reduce the redundant information of data,and thus,especially fits to the mass data clustering applications where hierarchical clustering algorithm or other traditional clustering algorithms may be ineffective.更多还原