Spatiotemporal anomaly detection in gas monitoring sensor networks

X. Rosalind Wang, Joseph T. Lizier, Oliver Obst, Mikhail Prokopenko, Peter Wang

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

60 Citations (Scopus)


In this paper, we use Bayesian Networks as a means for unsupervised learning and anomaly (event) detection in gas monitoring sensor networks for underground coal mines. We show that the Bayesian Network model can learn cyclical baselines for gas concentrations, thus reducing false alarms usually caused by flatline thresholds. Further, we show that the system can learn dependencies between changes of concentration in different gases and at multiple locations. We define and identify new types of events that can occur in a sensor network. In particular, we analyse joint events in a group of sensors based on learning the Bayesian model of the system, contrasting these events with merely aggregating single events. We demonstrate that anomalous events in individual gas data might be explained if considered jointly with the changes in other gases. Vice versa, a network-wide spatiotemporal anomaly may be detected even if individual sensor readings were within their thresholds. The presented Bayesian approach to spatiotemporal anomaly detection is applicable to a wide range of sensor networks.

Original languageEnglish
Title of host publicationWireless Sensor Networks
Subtitle of host publication5th European Conference, EWSN 2008, Bologna, Italy, January 30-February 1, 2008. Proceedings
EditorsRoberto Verdone
Place of PublicationBerlin
PublisherSpringer, Springer Nature
Number of pages16
ISBN (Electronic)9783540776901
ISBN (Print)9783540776895
Publication statusPublished - 2008
Externally publishedYes
Event5th European Conference on Wireless Sensor Networks, EWSN 2008 - Bologna, Italy
Duration: 30 Jan 20081 Feb 2008

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin Heidelberg
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Other5th European Conference on Wireless Sensor Networks, EWSN 2008


Dive into the research topics of 'Spatiotemporal anomaly detection in gas monitoring sensor networks'. Together they form a unique fingerprint.

Cite this