Efficient mining of regional movement patterns in semantic trajectories

• DOI: 10.14778/3151106.3151111
• Publication Date: 2017-10-19T12:30:08Z
• Authors: Dong-Wan Choi; Jian Pei; Thomas Heinis
• Keywords: 11. Sustainability; 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

Semantic trajectory pattern mining is becoming more and important with the rapidly growing volumes of semantically rich data. Extracting sequential patterns in semantic trajectories plays a key role understanding behaviour human movement, which can widely be used many applications such as location-based advertising, road capacity optimisation, urban planning. However, most existing works on focus entire spatial area, leading to missing some locally significant within region. Based this motivation, paper studies regional problem, aiming at identifying all trajectories. Specifically, we propose new density scheme quantify frequency particular space, thereby formulate problem finding regions densely occurs. For proposed develop an efficient algorithm, called RegMiner (<u>Reg</u>ional Trajectory Pattern <u>Miner</u>), effectively reveals movement that are frequent region but not necessarily dominant space. Our empirical study using real data shows finds interesting local hard find by state-of-the-art global scheme, it also runs several orders magnitude faster than algorithm.