A model-based approach for outlier detection in sensor networks

Min Ding; Qilian Liang; Xiuzhen Cheng; Mznah Al-Rodhaan; Abdullah Al-Dhelaan; Scott C.H. Huang; Dechang Chen

A model-based approach for outlier detection in sensor networks

Min Ding^*, Qilian Liang, Xiuzhen Cheng, Mznah Al-Rodhaan, Abdullah Al-Dhelaan, Scott C.H. Huang, Dechang Chen

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

In this paper, we propose a model-based approach to detect outliers insensor networks by exploring the spatial correlation among neighboringnodes. This research is motivated by the observation that sensors in closeproximity normally present similar readings.We propose to employ Gaussianmixture modeling as a statistical means to build a probability densityfunction for multivariate spatial neighborhood sensor readings. Outlyingsensors can be reliably detected since they exhibit extremely low densityvalues. Our extensive simulation evaluation validates the proposedmodel-based approach for outlier detection in sensor networks.

Original language	English
Pages (from-to)	275-293
Number of pages	19
Journal	Ad-Hoc and Sensor Wireless Networks
Volume	12
Issue number	3-4
State	Published - 2011
Externally published	Yes

Keywords

Expectation-maximimation;wireless sensor networks
Gaussian mixture model
Outlier detection

Cite this

@article{eff41a99f6e740beb3e2ee11425fd74d,

title = "A model-based approach for outlier detection in sensor networks",

abstract = "In this paper, we propose a model-based approach to detect outliers insensor networks by exploring the spatial correlation among neighboringnodes. This research is motivated by the observation that sensors in closeproximity normally present similar readings.We propose to employ Gaussianmixture modeling as a statistical means to build a probability densityfunction for multivariate spatial neighborhood sensor readings. Outlyingsensors can be reliably detected since they exhibit extremely low densityvalues. Our extensive simulation evaluation validates the proposedmodel-based approach for outlier detection in sensor networks.",

keywords = "Expectation-maximimation;wireless sensor networks, Gaussian mixture model, Outlier detection",

author = "Min Ding and Qilian Liang and Xiuzhen Cheng and Mznah Al-Rodhaan and Abdullah Al-Dhelaan and Huang, {Scott C.H.} and Dechang Chen",

year = "2011",

language = "English",

volume = "12",

pages = "275--293",

journal = "Ad-Hoc and Sensor Wireless Networks",

issn = "1551-9899",

number = "3-4",

}

TY - JOUR

T1 - A model-based approach for outlier detection in sensor networks

AU - Ding, Min

AU - Liang, Qilian

AU - Cheng, Xiuzhen

AU - Al-Rodhaan, Mznah

AU - Al-Dhelaan, Abdullah

AU - Huang, Scott C.H.

AU - Chen, Dechang

PY - 2011

Y1 - 2011

N2 - In this paper, we propose a model-based approach to detect outliers insensor networks by exploring the spatial correlation among neighboringnodes. This research is motivated by the observation that sensors in closeproximity normally present similar readings.We propose to employ Gaussianmixture modeling as a statistical means to build a probability densityfunction for multivariate spatial neighborhood sensor readings. Outlyingsensors can be reliably detected since they exhibit extremely low densityvalues. Our extensive simulation evaluation validates the proposedmodel-based approach for outlier detection in sensor networks.

AB - In this paper, we propose a model-based approach to detect outliers insensor networks by exploring the spatial correlation among neighboringnodes. This research is motivated by the observation that sensors in closeproximity normally present similar readings.We propose to employ Gaussianmixture modeling as a statistical means to build a probability densityfunction for multivariate spatial neighborhood sensor readings. Outlyingsensors can be reliably detected since they exhibit extremely low densityvalues. Our extensive simulation evaluation validates the proposedmodel-based approach for outlier detection in sensor networks.

KW - Expectation-maximimation;wireless sensor networks

KW - Gaussian mixture model

KW - Outlier detection

UR - http://www.scopus.com/inward/record.url?scp=79958695950&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:79958695950

SN - 1551-9899

VL - 12

SP - 275

EP - 293

JO - Ad-Hoc and Sensor Wireless Networks

JF - Ad-Hoc and Sensor Wireless Networks

IS - 3-4

ER -

A model-based approach for outlier detection in sensor networks

Abstract

Keywords

Fingerprint

Cite this