Abstract
The efficient discovery of significant group patterns from large-scale spatiotemporal trajectory data is a primary challenge, particularly in the context of urban traffic management. Existing studies on group pattern discovery mainly focus on the spatial gathering and moving continuity of vehicles or animals; these studies either set too many limitations in the shape of the cluster and time continuity or only focus on the characteristic of the gathering. Meanwhile, little attention has been paid to the equidirectional movement of the aggregated objects and their loose coherence moving. In this study, we propose the concept of loosely moving congestion patterns that represent a group of moving objects together with similar movement tendency and loose coherence moving, which exhibit a potential congestion characteristic. Meanwhile, we also develop an accelerated algorithm called parallel equidirectional cluster-recombinant (PDCLUR) that runs on graphics processing units (GPUs) to detect congestion patterns from large-scale raw taxi-trajectory data. The case study results demonstrate the performance of our approach and its applicability to large trajectory dataset, and we can discover some significant loosely moving congesting patterns and when and where the most congested road segments are observed. The developed algorithm PDCLUR performs satisfactorily, affording an acceleration ratio of over 65 relative to the traditional sequential algorithms.
Highlights
We introduce the concept of a new moving group pattern with similar movement tendency and loose consistency moving of vehicles, which we call the loosely moving congestion pattern (LMCP)
We propose the concept and generating rules of loosely moving congestion pattern
We proposed an algorithm to efficiently discover LMCPs from large-scale trajectory datasets for extracting congested roads, congestion levels, congestion time periods, and directions
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Two objects, which only clustered together at some time points, would be considered as moving together their trajectories may be quite different. We attempt to detect congestion patterns by exploring group pattern from large-scale, raw taxi-trajectory data. According to the formed features of traffic congestion, such as slight movement, high density, direction, and duration, here we explore a new approach to discover new group patterns for the identification of congestion from the large-scale, raw taxi-trajectory data. Different from the previous group patterns, which were basically used to detect moving object clusters instead of traffic congestion, our proposed.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have