Visual Exploration of Big Spatio-Temporal Urban Data


Taxis are valuable sensors and information associated with taxi trips can provide unprecedented insight into many different aspects of city life, from economic activity and human behavior to mobility patterns. But analyzing these data presents many challenges. 


Authors: Nivan Ferreira, Jorge Poco, Huy T. Vo, Juliana Freire, and Claúdio T. Silva 
Organization: New York University

Enable domain experts to freely explore a large number of urban data sets and interactively analyze the many different facets of these data 


-    Propose a new visual query model that supports complex spatio-temporal queries over origin-destination (OD) data. 
-    Implement an analysis environment using the previous visual model. 
-    Demonstrate the usefulness of our system through a series of case studies motivated by traffic engineers and economists whose needs have driven our design. 


-    We have built a scalable system that implements our visual query model which supports interactive response times; makes use of an adaptive level-of-detail rendering strategy to generate clutter-free visualization for large results; and shows hidden details to the users in a summary through the use of overlay heat maps. 
-    We present a series of case studies motivated by traffic engineers and economists that show how our model and system enable domain experts to perform tasks that were previously unattainable for them. 


What is new?
-    Instead of requiring users to sketch queries, our model allows them to directly (and visually) manipulate the data. 
-    To deal with scalability, the system implements a number of strategies to support interactive response times and the rendering of a large number of graphical primitives on a map. 
-    We have presented a series of case studies, using a large data set consisting of over 520 million taxi trips in NYC, which illustrates the capabilities and effectiveness of our system and design decisions 

Future work
-    We would like to use this tool as based to incorporate automatic identification of patterns and anomalies. 
-    Propose some mechanisms that could guide the user in the exploration. For instance, in the current version, the user needs to know what time period to select in order to do a deeper analysis. We should be able to provide interesting time periods for the user to explore.
-    Integrate taxi data with other urban datasets in order to identify some correlations, for example, weather and number of taxis.