居民个体出行行为聚类及出行模式分析——以三亚市为例

Individual Travel Behavior Clustering and Travel Pattern Analysis:A Case Study of Sanya

手机信令数据不仅记录个体出行轨迹,同时也为分析城市居民出行模式提供了基础。通过提出一种基于狄利克雷过程混合模型的聚类方法,以从手机信令提取的出行OD(Origin-Destination)为基础,研究个体出行行为及群体出行模式。与其他聚类方法相比,该方法最大的优点在于无需事先指定聚类的数量,并且能够基于数据识别出新的聚类。通过将该方法应用到三亚市的居民出行行为研究中,得到15类个体行为聚类。从而进一步结合城市特征,归纳得出5种典型出行模式,较为全面地反映三亚居民活动的实际情况,为制定差异化的交通政策、精细化交通管理提供支撑。

The mobile phone data not only records the individual travel trajectory,but also provides a basis for analyzing the travel patterns of urban residents.This paper proposes a clustering method based on the Dirichlet Process Mixture Model.Based on the trip OD(Origin-Destination)extracted from the mobile phone data,this paper studies individual travel behavior and residents'travel pattern.Compared with other clustering methods,the biggest advantage of this method is that there is no need to specify the number of clusters in advance,and new clusters can be identified based on the data.This paper applies this method to Sanya,and 15 types of individual behavior clusters are obtained.Based on the characteristics of the city,five typical travel patterns are summarized,which more comprehensively reflect the actual situation of residents'activities in Sanya,and provide support for the formulation of differentiated traffic policies and refined traffic management.