Efficient Mining of Hotspot Regional Patterns with Multi-Semantic Trajectories

Abstract

Due to the explosive growth in trajectory data with multi-semantic labels, mining hotspots based on extracted sequential patterns from multi-semantic trajectories are an emerging need in various applications of crowd behavior analysis, such as location-based advertising, business location, and urban planning. However, most existing regional pattern mining methods only focus on temporal continuity, spatial compactness, and a single semantics. Outdated or nonhot regions may be discovered if the timeliness, multi-semantic features, and user activity of trajectory patterns are not taken into consideration. To address this issue, this paper studies a hotspot regional multi-semantic trajectory pattern mining problem, with the aim of identifying the hotspot pattern of a social crowd in the trajectory data. Specifically, 1) we propose a new spatiotemporal density scheme to quantify the frequency and heat of a specific pattern in space, and to discover all regions where movement behaviors occur densely and have high heat; 2) we develop a trajectory mining algorithm, effective hotspot regional multi-semantic trajectory pattern mining (tHRM), which effectively reveals the hot movement patterns in a region that are not necessarily dominant in intensity. Experiments using real trajectory data sets show that tHRM is able to discover regional hotspot regional patterns, which are difficult to discover with state-of-the-art regional pattern mining methods. Furthermore, tHRM runs 3-4 times faster, and the mining quality is an order of magnitude higher than that of the rival methods.