Interactive Visual Analytics of Urban Trajectory Data

  Advanced sensing technologies and computing infrastructures have produced a variety of trajectory data of humans and vehicles in urban spaces. The massive population mobility data, from taxis, fleets, public transits, and mobile phones, is generated at unprecedented scale and speed with GPS, Wi-Fi, RFID, etc. The big data contains abundant knowledge about a city, a state and its citizens. Urban trajectory data can help to optimize urban planning, improve human life quality and environment, and amend city operations. We have developed interactive visual analytics systems to discover and analyze the hidden knowledge of massive taxi trajectory data within a city. First, we visualize hidden themes of taxi movement by transforming the geographic coordinates into street names. Consequently, the movement of each taxi is studied as a document consisting of the traversed street names. Urban mobility patterns and trends are identified as taxi topics (clusters) through textual topic modeling over massive taxi data. The taxi topics reflect urban mobility patterns and trends, which are displayed and analyzed through interactive visualization tools. Second, we present a visual analysis system to evaluate the real traffic situations based on taxi trajectory data. A sketch-based visual interface is designed to support dynamic query and visual reasoning of traffic situations within multiple coordinated views. In particular, we propose a novel road-based query model for analysts to interactively conduct evaluation tasks. The model is supported by a bi-directional hash structure which enables real-time responses to the data queries over a huge amount of trajectory data. We perform case studies with real GPS trajectory data acquired by city taxis (e.g., 21,360 taxis in a city) to illustrate the effectiveness of our systems. Bio: Ye Zhao is an associate professor in the Department of Computer Science at the Kent State University, Ohio. He received B.S. and M.S. degrees in computer science from the Tsinghua University of China in 1997 and 2000. He further received his PhD degree in computer science from the Stony Brook University in 2006. His research interests include physically-based simulation and visualization, data and information visualization, visual analytics, image and geometric processing, and general purpose computing on graphics hardware (GPGPU). His research has been supported by NSF, Ohio Board of Regents, and Google for fluid simulation and visualization, visual analytics, and information visualization.