Identifying Origin/Destination Hotspots in Floating Car Data for Visual Analysis of Traveling Behavior

In this paper, we present the results of developing a geo-visual analytics application to support urban services. The goal is to allow non-GIS users to explore the taxi traveler's hot spots in Shanghai extracted from one week taxi floating car data (FCD). To achieve this, we proposed a workflow based on the visualization pipeline. Firstly, we preprocess the data to extract the origins (o) and destinations (d) from the FCD and apply data mining methods to detect taxi traveler's hot spots, to which semantics are further tagged using point of interest (POI) data extracted from OpenStreetMap (OSM) project. The detected hot spots are selected to show in the application for the user to conduct further visual analysis. Furthermore, we implement a web-based interactive visual explorative system, in which the graphic user interface contains multiple views (spatial, temporal and thematic) and interactive components are built up using the current web technologies. Finally, a possible use case of the application is introduced. Our results show that the developed geo-visual analytics application enables studying traveler's activity patterns. The visual analysis can be conducted with this tool for several aspects. The visual queries help to detect when and where hot spots occur and to compare the temporal distributions for nearby hot spots.