Authors: Zhaosong Huang, Ye Zhao, Wei Chen, Shengjie Gao, Kejie Yu, Weixia Xu, Mingjie Tang, Minfeng Zhu, Mingliang Xu
Abstract: Querying is essential for exploring massive trajectory data. However, the data uncertainty imposes profound challenges to fulfill advanced analytics requirements. On the one hand, many underlying data does not contain accurate geographic coordinates, e.g., positions of a mobile phone only refer to the regions (i.e., mobile cell towers) in which it resides, instead of accurate GPS coordinates. It is hard to determine a unique destination of trajectory. On the other hand, domain experts and general users prefer a natural way, such as using a natural-language-based sentence, to analyze massive movement data. In this paper, we propose a visual analytics approach that can extract spatial-temporal constraints from a textual sentence and support an effective fuzzy query over uncertain mobile trajectory data. Our implemented visual interface facilitates condition specification, situation-aware analysis, and semantic exploration of large trajectory data. Experimental studies on real datasets demonstrate the effectiveness of our approach.