Extract Human Mobility Patterns Powered by City Semantic Diagram

Abstract

With widespread deployment of GPS devices, massive spatiotemporal trajectories became more accessible. This booming trend paved the solid data ground for researchers to discover the regularities or patterns of human mobility. However, there are still three challenges in semantic pattern extraction including semantic absence, semantic bias and semantic complexity. In this paper, we invent and apply a novel data structure namely <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">City Semantic Diagram</i> to overcome above three challenges. First, our approach resolves semantic absence by exactly identifying semantic behaviours from raw trajectories. Second, the design of semantic purification helps us to detect semantic complexity from human mobility. Third, we avoid semantic bias using objective data source such as ubiquitous GPS trajectories. Comprehensive and massive experiments have been conducted based on real taxi trajectories and points of interest in Shanghai. Compared with existing approaches, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">City Semantic Diagram</i> is able to discover fine-grained semantic patterns effectively and accurately.