Abstract
The processing and analysis of trajectories are the core of many location-based applications and services, while trajectory similarity is an essential concept regularly used. To address the time-consuming problem of similarity query, an efficient algorithm based on Fréchet distance called Ordered Coverage Judge (OCJ) is proposed, which could realize the filtering query with a given Fréchet distance threshold on large-scale trajectory datasets. The OCJ algorithm can obtain the result set quickly by a two-step operation containing morphological characteristic filtering and ordered coverage judgment. The algorithm is expedient to be implemented in parallel for further increases of speed. Demonstrated by experiments over real trajectory data in a multi-core hardware environment, the new algorithm shows favorable stability and scalability besides its higher efficiency in comparison with traditional serial algorithms and other Fréchet distance algorithms.
Highlights
With the rapid development of mobile internet, various types of sensors on mobile devices record diversified information of their carriers, personnel or equipment’s track of locations, which are the most common types of data of great value in many location-based applications
There is no data dependency between the query tasks based on different target trajectory, and the single judgement operation in the same query uses the same pair of trajectories, so Ordered Coverage Judge (OCJ) algorithm is suitable to execute in a Massive Parallel Processing (MPP) environment
Fréchet distance takes into account the temporal relation of the internal nodes in the trajectory, and the similarity of the trajectories can be better described than other distance measures
Summary
With the rapid development of mobile internet, various types of sensors on mobile devices record diversified information of their carriers, personnel or equipment’s track of locations, which are the most common types of data of great value in many location-based applications. The processing and analysis of trajectory data has emerged as a critical area of development in the field of geographic information and data mining. In this case, the similarity measure and similarity query of the trajectory are the basis of many analytical processes. Due to the complexity of the trajectory similarity calculation and the large-scale of the actual trajectory dataset, the efficiency of the existing algorithm is far from practicable. Based on the summary of research status of the trajectory similarity computation, a fast query algorithm called the OCJ algorithm is proposed in this paper to address the problem of Fréchet distance threshold filtering ona large-scale trajectory dataset. It is concluded that, compared with traditional serial algorithm and other Fréchet distance algorithms, the parallel OCJ algorithm has lower computational complexity
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
