Visualizing anomalies in sensor networks

Qi Liao, Lei Shi, Yuan He, Rui Li, Zhong Su, Aaron Striegel, Yunhao Liu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations


Diagnosing a large-scale sensor network is a crucial but challenging task due to the spatiotemporally dynamic network behaviors of sensor nodes. In this demo, we present Sensor Anomaly Visualization Engine (SAVE), an integrated system that tackles the sensor network diagnosis problem using both visualization and anomaly detection analytics to guide the user quickly and accurately diagnose sensor network failures. Temporal expansion model, correlation graphs and dynamic projection views are proposed to effectively interpret the topological, correlational and dimensional sensor data dynamics and their anomalies. Through a real-world large-scale wireless sensor network deployment (GreenOrbs), we demonstrate that SAVE is able to help better locate the problem and further identify the root cause of major sensor network failures.

Original languageEnglish
Title of host publicationProceedings of the ACM SIGCOMM 2011 Conference, SIGCOMM'11
PublisherAssociation for Computing Machinery
Number of pages2
ISBN (Print)9781450307970
StatePublished - 2011

Publication series

NameProceedings of the ACM SIGCOMM 2011 Conference, SIGCOMM'11


  • Anomaly detection and analysis
  • Diagnosing
  • Visualization
  • Wireless sensor networks


Dive into the research topics of 'Visualizing anomalies in sensor networks'. Together they form a unique fingerprint.

Cite this