论文部分内容阅读
根据出租车行驶载客数据中提取的乘客出行模式和上下客热门区域,提出一种出租车热门区域功能发现方法。采用基于交通数据时空特性的出租车行驶数据聚类算法,实现热门区域划分。建立基于潜在Dirichlet分配的热门区域乘客出行特征发现模型,对具有相似乘客出行模式的出租车热门区域进行聚类。通过总结各热门区域的具体功能,发现在不同客流时间段内的区域功能与乘客出行模式间的关系。实验结果表明,该方法能够有效发现热门区域的功能特点。
According to the passenger travel patterns extracted from taxi driving data and the popular areas of getting on and off, this paper proposes a method to discover the hot area function of taxi. Taxi driving data clustering algorithm based on the spatio-temporal characteristics of traffic data is used to realize the hot zone division. A hot spot passenger travel feature discovery model based on potential Dirichlet distribution is established to cluster hot taxi hot spots with similar passenger travel patterns. By summarizing the specific functions of each popular area, it is found that the relationship between the regional functions and passenger travel modes in different passenger flow time periods. The experimental results show that this method can effectively find the functional characteristics of popular areas.