摘要
利用GPS轨迹宏观背景信息推断出行者出行目的方法,存在信息采集繁杂、实时处理不便等问题.提出了直接以GPS轨迹数据的语义信息为研究对象,着眼于挖掘GPS轨迹中出行者的微观活动信息,从而推断出行者出行目的的新算法.该算法通过辨识轨迹停留中的子停留,挖掘子停留的语义信息,并用活动点特征参数(时长、速度、转角)对信息进行量化,将特征参数值与在大量数据统计结果基础上构建的判别信息库进行比对,得出子停留活动类型,继而推断出行者的出行目的.真实采集的数据集验证了所提算法的有效性.
There were several issues, such as complex information collecting and untimely infor- mation processing, in inferring the traveler＇s trip purpose using the macroscopic background infor- mation of GPS trajectory. In this paper, a new algorithm was suggested which focused on mining the semantic （microscopic activity information） from GPS trajectory data, so as to infer the trip purpose of traveler. Further, the new algorithm was implemented by identifying the sub-stops from trajectory stops, mining the semantic information of sub-stops, and quantifying the informa- tion through using the characteristic parameters of activity points （such as time, speed, corner）. Additionally, the types of sub-stops activity was obtained by contrasting the characteristic param- eters＂ value to the knowledge database based on the statistical results of a large number of data. Last, the effectiveness of the proposed algorithm was verified by using real trajectory data.
出处
《山东理工大学学报（自然科学版）》
CAS
2012年第6期17-22,共6页
Journal of Shandong University of Technology:Natural Science Edition
基金
国家自然科学基金资助项目(61074140)
山东省自然科学基金资助项目(ZR2010FM007)
关键词
智能交通
出行目的
语义挖掘
GPS轨迹数据
子停留
intelligent transportation
deducing trip purpose
semantics mining
GPS trajectorydata
sub-stop
