CityTracker: Citywide Individual and Crowd Trajectory Analysis Using Hidden Markov Model

Abstract

Geospatial big data analytics are changing the way that businesses operate, and have enabled various intelligent services in smart cities. User mobility plays an important role in many context-aware applications, such as location-based advertisement, traffic planning, and urban resource management. This paper proposes CityTracker, a hidden Markov model (HMM)-based framework to predict the temporal-spatial individual trajectory and analyze the representative citywide crowd mobility. After the locations are segmented into points of interests and modeled as states, HMM can find the most likely state sequence in a maximum-likelihood sense, and thus perform trajectory prediction with different orders. In addition, CityTracker can integrate the individual trajectories, achieving representative crowd mobility visualization in the target area. The proposed mechanism is evaluated on a database provided by HyXen, which contains temporal-geospatial records from thousands of smartphones in Taipei. Experimental results confirm the effectiveness of CityTracker, which achieves prediction distance errors of approximately 1.28 km and outperforms traditional probabilistic and regression-based methods. The results also show the most representative crowd mobility behaviors in the map, which is essential for citywide applications.