Exploring traffic flow databases using space-time plots and data cubes

Ying Song, Harvey J. Miller

Research output: Contribution to journalArticlepeer-review

23 Scopus citations

Abstract

Local departments of transportation and metropolitan planning organizations have been collecting traffic data for many decades. However, these data are rarely exploited to their full potential. In this paper, we describe an exploratory visualization toolkit for large traffic flow databases. The visualization toolkit is based on the concept of the traffic cube: an extension of the data cube in data mining. The traffic cube organizes traffic flow data across different spatial and temporal dimensions and with respect to user-specified aggregation levels. The toolkit allows the user to perform data cube operations to select, summarize and cross-tabulate the traffic data prior to visualization as two-dimensional space-time plots. We demonstrate a prototype system using MATLAB, ArcGIS and MS Access database software. Example visualizations of a large database of hourly traffic flows along major highways in the state of Utah (USA) over a 10-year period illustrate the potential for the toolkit to reveal patterns about traffic flows and trends hidden in the database.

Original languageEnglish (US)
Pages (from-to)215-234
Number of pages20
JournalTransportation
Volume39
Issue number2
DOIs
StatePublished - Mar 2012
Externally publishedYes

Keywords

  • Data cubes
  • Exploratory analysis
  • Space-time plots
  • Traffic cubes
  • Traffic data
  • Visualization

Fingerprint

Dive into the research topics of 'Exploring traffic flow databases using space-time plots and data cubes'. Together they form a unique fingerprint.

Cite this