论文部分内容阅读
采用基于遗传算法的模糊聚类划分城市快速路交通流状态,借助模糊相关度函数分析聚类结果的有效性,以寻找交通流状态的最佳分类数。遗传算法的引入,有效改善了传统模糊聚类对初始化敏感以及容易陷入局部最优解的问题。经上海市城市快速路实测数据验证,此算法对交通流状态的划分具有可行性,且聚类有效性分析能够合理确定交通流状态最佳分类数。上述研究成果可用于城市快速路交通信息发布、服务水平评价以及交通设施的控制与管理。
The fuzzy clustering based on genetic algorithm is used to divide the urban expressway traffic flow state, and the fuzzy correlation function is used to analyze the validity of the clustering result to find the best classification number of the traffic flow state. The introduction of genetic algorithm effectively improves the traditional fuzzy clustering sensitivity to initialisation and easy to fall into the local optimal solution. According to the measured data from Shanghai Urban Expressway, this algorithm is feasible for the classification of traffic flow status, and the cluster validity analysis can reasonably determine the best classification number of traffic flow status. The above research results can be used for traffic information release, service level evaluation and traffic facility control and management of urban expressways.