摘要
挖掘用户的移动行为,可以通过对交通出行方式进行识别来实现。传统的交通方式识别方法在交通堵塞或多种交通方式结合的情况下,识别效果并不理想。针对这种情况,提出基于轨迹分段和监督式学习相结合的识别方法,首先利用速度小于某一阈值的数据点将原始GPS轨迹划分为交通方式单一的子轨迹段,然后对子轨迹段分别抽取特征,采用监督式学习方法建立推断模型对不同子轨迹的交通方式进行识别。实验结果表明,提出的算法能够有效地识别不同交通方式,达到较为理想的效果。同时在交通堵塞的情况下也能够很好地识别。
Mining users' mobility behaviours can be achieved through the identification of transportation modes. Traditional transportation identification methods do not have ideal effect in traffic jam or the circumstances of various transportation modes combination. In view of this situation, we proposed the identification method which is based on the combination of trajectory segmentation and supervised learning. First, it divides the original GPS trajectory into sub-trajectory sections in single transportation mode using the data points with the speed less than a certain threshold. Then it extracts the features of sub-trajectories sections separately. By building an inference model using the supervised learning method it identifies the transportation modes in different sub-trajectories. Experimental result shows that the proposed algorithm can identify different transportation modes effectively, and achieves rather ideal effect. At the same time, this algorithm can identify well in traffic jam circumstances.
出处
《计算机应用与软件》
CSCD
2015年第11期83-87,共5页
Computer Applications and Software
基金
国家自然科学基金项目(61262089
61262087)
新疆教育厅高校教师科研计划重点项目(XJEDU2012I09)
关键词
数据挖掘
GPS轨迹
用户移动行为
交通方式识别
特征抽取
监督式学习
Data mining
GPS trajectory
Users' mobility behaviours
Transportation mode identification
Feature extraction
Super-vised learning