Skip to main navigation Skip to search Skip to main content

Online anomaly rate parameter tracking for anomaly detection in wireless sensor networks

  • Colin O'Reilly
  • , Alex Gluhak
  • , Muhammad Imran
  • , Sutharshan Rajasegarar
  • University of Surrey
  • University of Melbourne

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

13 Scopus citations

Abstract

Anomaly detection in a Wireless Sensor Network is an important aspect of data analysis in order to facilitate intrusion and event detection. A key challenge is creating optimal classifiers constructed from training sets in which the anomaly rates are varying due to the existence of non-stationary distributions in the data. In this paper we propose an adaptive algorithm that can dynamically adjust the anomaly rate parameter, which can be represented by a model parameter of a one-class quarter-sphere support vector machine. This algorithm operates in an online, iterative manner producing an optimal model for a training set, which is presented sequentially. Our evaluations demonstrate that our algorithm is capable of constructing optimal models for a training set that minimizes the error rate on the classification set compared to a static model, where the anomaly rate is kept stationary.

Original languageEnglish
Title of host publication2012 9th Annual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks, SECON 2012
Pages191-199
Number of pages9
DOIs
StatePublished - 2012
Externally publishedYes
Event2012 9th Annual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks, SECON 2012 - Seoul, Korea, Republic of
Duration: 18 Jun 201221 Jun 2012

Publication series

NameAnnual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks workshops
Volume1
ISSN (Print)2155-5486
ISSN (Electronic)2155-5494

Conference

Conference2012 9th Annual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks, SECON 2012
Country/TerritoryKorea, Republic of
CitySeoul
Period18/06/1221/06/12

Keywords

  • Adaptive Models
  • Anomaly Detection
  • Concept Drift
  • Non-Stationary Environment
  • Security
  • Wireless Sensor Network

Fingerprint

Dive into the research topics of 'Online anomaly rate parameter tracking for anomaly detection in wireless sensor networks'. Together they form a unique fingerprint.

Cite this