基于路网的不确定性轨迹预测

Uncertain Path Prediction of Moving Objects on Road Networks

移动对象的轨迹预测研究已成为当前移动对象研究中关注的热点,移动对象的轨迹预测技术具有高度的研究价值及广阔的应用前景.目前移动对象的轨迹预测方法主要是针对历史轨迹确定的欧氏空间轨迹预测,但有相当一部分的应用要求预测历史轨迹存在不确定性的移动对象在受限路网中的轨迹.为了解决这一问题,首先提出了不确定性轨迹的生成方法及其表示形式,然后提出了一种基于路网的不确定性轨迹频繁模式挖掘算法,最后给出了利用索引快速查找轨迹模式并进行预测的方法.实验结果表明该方法具有较高的预测准确率、较好的查询效率以及较低的存储空间.

With the advancement of mobile computing technology and the widespread use of GPS-enabled mobile devices,the location-based services have received more and more attentions,and the path prediction of moving objects is one of the most important issues. The existing prediction methods of moving objects focus mainly on the precise historic trajectory in Euclidean space. However,in the real world,there are a lot of applications which require predicting network-constrained trajectory based on the uncertain historic trajectory. As yet,there has been no research on uncertain path prediction of moving objects on road networks. In order to solve this problem,a method of generating the uncertain trajectory is proposed firstly,the definition of path probability and an uncertain path prefix tree are used to generate the uncertain trajectory,and a corresponding data format of the uncertain trajectory is given. Then an uncertain trajectory pattern mining algorithm is proposed,and a data structure named id-list is used in the algorithm. Finally trajectory patterns which are mined from the uncertain trajectory pattern mining algorithm are indexed by a novel access method for efficient query processing. The experiment shows good performance of the system,and the results demonstrate that the proposed techniques are accurate,efficient and of low storage capacity.