Clustering elliptical anomalies in sensor networks

James C. Bezdek; Timothy C. Havens; James M. Keller; Chris Leckie; Laurence Park; Marimuthu Palaniswami; Sutharshan Rajasegarar

doi:10.1109/FUZZY.2010.5584464

Clustering elliptical anomalies in sensor networks

James C. Bezdek, Timothy C. Havens, James M. Keller, Chris Leckie, Laurence Park, Marimuthu Palaniswami, Sutharshan Rajasegarar

Unknown

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

12 Citations (Scopus)

Abstract

We model anomalies in wireless sensor networks with ellipsoids that represent node measurements. Elliptical anomalies (EAs) are level sets of ellipsoids, and classify them as type 1, type 2 and higher order anomalies. Three measures of (dis)similarity between pairs of ellipsoids convert model ellipsoids into dissimilarity data. Clusters in the dissimilarity data may correspond to normal and anomalous measurements and nodes in the network. Assessment of (clustering) tendency is facilitated by visual inspection of (VAT/iVAT) images. Two examples illustrate the potential for anomaly detection.

Original language	English
Title of host publication	2010 IEEE World Congress on Computational Intelligence, WCCI 2010
DOIs	https://doi.org/10.1109/FUZZY.2010.5584464
Publication status	Published - 2010
Externally published	Yes
Event	2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - Barcelona, Spain Duration: 18 Jul 2010 → 23 Jul 2010

Publication series

Name	2010 IEEE World Congress on Computational Intelligence, WCCI 2010

Conference

Conference	2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010
Country/Territory	Spain
City	Barcelona
Period	18/07/10 → 23/07/10

Keywords

Anomaly detection
Elliptical similarity
Visual assessment of clustering tendency
Wireless sensor networks

Access to Document

10.1109/FUZZY.2010.5584464

Cite this

@inproceedings{11e368611f474cff8ef2281f03743982,

title = "Clustering elliptical anomalies in sensor networks",

abstract = "We model anomalies in wireless sensor networks with ellipsoids that represent node measurements. Elliptical anomalies (EAs) are level sets of ellipsoids, and classify them as type 1, type 2 and higher order anomalies. Three measures of (dis)similarity between pairs of ellipsoids convert model ellipsoids into dissimilarity data. Clusters in the dissimilarity data may correspond to normal and anomalous measurements and nodes in the network. Assessment of (clustering) tendency is facilitated by visual inspection of (VAT/iVAT) images. Two examples illustrate the potential for anomaly detection.",

keywords = "Anomaly detection, Elliptical similarity, Visual assessment of clustering tendency, Wireless sensor networks",

author = "Bezdek, {James C.} and Havens, {Timothy C.} and Keller, {James M.} and Chris Leckie and Laurence Park and Marimuthu Palaniswami and Sutharshan Rajasegarar",

year = "2010",

doi = "10.1109/FUZZY.2010.5584464",

language = "English",

isbn = "9781424469208",

series = "2010 IEEE World Congress on Computational Intelligence, WCCI 2010",

booktitle = "2010 IEEE World Congress on Computational Intelligence, WCCI 2010",

note = "2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 ; Conference date: 18-07-2010 Through 23-07-2010",

}

Bezdek, JC, Havens, TC, Keller, JM, Leckie, C, Park, L, Palaniswami, M & Rajasegarar, S 2010, Clustering elliptical anomalies in sensor networks. in 2010 IEEE World Congress on Computational Intelligence, WCCI 2010., 5584464, 2010 IEEE World Congress on Computational Intelligence, WCCI 2010, 2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010, Barcelona, Spain, 18/07/10. https://doi.org/10.1109/FUZZY.2010.5584464

TY - GEN

T1 - Clustering elliptical anomalies in sensor networks

AU - Bezdek, James C.

AU - Havens, Timothy C.

AU - Keller, James M.

AU - Leckie, Chris

AU - Park, Laurence

AU - Palaniswami, Marimuthu

AU - Rajasegarar, Sutharshan

PY - 2010

Y1 - 2010

N2 - We model anomalies in wireless sensor networks with ellipsoids that represent node measurements. Elliptical anomalies (EAs) are level sets of ellipsoids, and classify them as type 1, type 2 and higher order anomalies. Three measures of (dis)similarity between pairs of ellipsoids convert model ellipsoids into dissimilarity data. Clusters in the dissimilarity data may correspond to normal and anomalous measurements and nodes in the network. Assessment of (clustering) tendency is facilitated by visual inspection of (VAT/iVAT) images. Two examples illustrate the potential for anomaly detection.

AB - We model anomalies in wireless sensor networks with ellipsoids that represent node measurements. Elliptical anomalies (EAs) are level sets of ellipsoids, and classify them as type 1, type 2 and higher order anomalies. Three measures of (dis)similarity between pairs of ellipsoids convert model ellipsoids into dissimilarity data. Clusters in the dissimilarity data may correspond to normal and anomalous measurements and nodes in the network. Assessment of (clustering) tendency is facilitated by visual inspection of (VAT/iVAT) images. Two examples illustrate the potential for anomaly detection.

KW - Anomaly detection

KW - Elliptical similarity

KW - Visual assessment of clustering tendency

KW - Wireless sensor networks

UR - http://www.scopus.com/inward/record.url?scp=78549267848&partnerID=8YFLogxK

U2 - 10.1109/FUZZY.2010.5584464

DO - 10.1109/FUZZY.2010.5584464

M3 - Conference Paper

AN - SCOPUS:78549267848

SN - 9781424469208

T3 - 2010 IEEE World Congress on Computational Intelligence, WCCI 2010

BT - 2010 IEEE World Congress on Computational Intelligence, WCCI 2010

T2 - 2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010

Y2 - 18 July 2010 through 23 July 2010

ER -

Clustering elliptical anomalies in sensor networks

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this