Given a set of GPS trajectories, avoidance region discovery (ARD) finds regions that are avoided by drivers. ARD is important for applications such as sociology, city/transportation planning and crime mitigation, where it can help domain users understand the driver behavior under different concerns (e.g. rush hour, congestion, dangerous neighborhood, etc.). ARD is challenging because of the large number of trajectories with thousands of GPS points, large number of candidate avoidance regions, and the cost of evaluating those. Related work is focused on finding evasive trajectories for a given set of avoidance regions. Distinct from the related work, we propose an Avoidance Region Miner (ARM) approach that can detect both the avoidance regions and evasive trajectories just by using the trajectories in hand without the need of an additional input. A case study on real trajectory data confirms that ARM discovers such regions for further investigation by domain users. Experiments show that ARM yields substantial computational savings compared to a baseline approach.
|Original language||English (US)|
|Number of pages||9|
|State||Published - 2018|
|Event||2018 SIAM International Conference on Data Mining, SDM 2018 - San Diego, United States|
Duration: May 3 2018 → May 5 2018
|Other||2018 SIAM International Conference on Data Mining, SDM 2018|
|Period||5/3/18 → 5/5/18|
Bibliographical noteFunding Information:
In future, we envision adding a statistical significance test to eliminate chance regions. In addition, we plan to compare the trajectories with the most used routes instead of shortest paths. Finally, we plan to use larger datasets both for experiments and case studies to identify the bottlenecks of the proposed approaches under different conditions. 8 Acknowledgments This material is based upon work supported by the USDOD Grant No. HM1582-08-1-0017. We would like to thank Kim Koffolt and the University of Minnesota Spatial Computing Research Group for their comments.