Summary
|
For Full-Text PDF, please login, if you are a member of IEICE, or go to Pay Per View on menu list, if you are a nonmember of IEICE. |
|
ATTI: Workload-Aware Query Adaptive OcTree Based Trajectory Index Xiangxu MENG Xiaodong WANG Xinye LIN Publication IEICE TRANSACTIONS on Information and Systems Vol.E96-D No.3 pp.643-654 Publication Date: 2013/03/01 Online ISSN: 1745-1361 DOI: 10.1587/transinf.E96.D.643 Print ISSN: 0916-8532 Type of Manuscript: PAPER Category: Data Engineering, Web Information Systems Keyword: spatial-temporal database, trajectory, workload-aware, adaptive, Full Text: PDF(947.2KB)>>
Summary: The GPS trajectory databases serve as bases for many intelligent applications that need to extract some trajectories for future processing or mining. When doing such tasks, spatio-temporal range queries based methods, which find all sub-trajectories within the given spatial extent and time interval, are commonly used. However, the history trajectory indexes of such methods suffer from two problems. First, temporal and spatial factors are not considered simutaneously, resulting in low performance when processing spatio-temporal queries. Second, the efficiency of indexes is sensitive to query size. The query performance changes dramatically as the query size changed. This paper proposes workload-aware Adaptive OcTree based Trajectory clustering Index (ATTI) aiming at optimizing trajectory storage and index performance. The contributions are three-folds. First, the distribution and time delay of the trajectory storage are introduced into the cost model of spatio-temporal range query; Second, the distribution of spatial division is dynamically adjusted based on GPS update workload; Third, the query workload adaptive mechanism is proposed based on virtual OcTree forest. A wide range of experiments are carried out over Microsoft GeoLife project dataset, and the results show that query delay of ATTI could be about 50% shorter than that of the nested index. | ||||||||||
| ||||||||||