Analyzing spatiotemporal anomalies through interactive visualization

Tao Zhang, Qi Liao, Lei Shi, Weishan Dong

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

As we move into the big data era, data grows not just in size, but also in complexity, containing a rich set of attributes, including location and time information, such as data from mobile devices (e.g., smart phones), natural disasters (e.g., earthquake and hurricane), epidemic spread, etc. We are motivated by the rising challenge and build a visualization tool for exploring generic spatiotemporal data, i.e., records containing time location information and numeric attribute values. Since the values often evolve over time and across geographic regions, we are particularly interested in detecting and analyzing the anomalous changes over time/space. Our analytic tool is based on geographic information system and is combined with spatiotemporal data mining algorithms, as well as various data visualization techniques, such as anomaly grids and anomaly bars superimposed on the map. We study how effective the tool may guide users to find potential anomalies through demonstrating and evaluating over publicly available spatiotemporal datasets. The tool for spatiotemporal anomaly analysis and visualization is useful in many domains, such as security investigation and monitoring, situation awareness, etc.

Original languageEnglish
Pages (from-to)100-125
Number of pages26
JournalInformatics
Volume1
Issue number1
DOIs
StatePublished - Jun 2014

Keywords

  • Anomaly detection
  • Spatiotemporal data analysis
  • Visualization

Fingerprint

Dive into the research topics of 'Analyzing spatiotemporal anomalies through interactive visualization'. Together they form a unique fingerprint.

Cite this