A hybrid fault detection approach for context-aware wireless sensor networks

Ehsan Ullah Warriach, Tuan Anh Nguyen, Marco Aiello, Kenji Tei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Wireless Sensor Network (WSN) deployment experiences show that data collected is prone to be imprecise and faulty due to internal and external influences, such as battery drain, environmental interference, sensor aging. An early detection of such faults is necessary for the effective operation of the sensor network. We focus on identifying data fault types and their causes. In particular, we propose a hybrid approach to the detection of faults based on three qualitatively different classes of fault detection methods. Rule-based methods leverage domain and expert knowledge to develop heuristic rules for identifying and classifying faults. Estimation methods predict normal sensor behavior by leveraging sensor spatial and temporal correlations, identifying erroneous sensor readings as faults. Finally, learning-based methods are inferred a model for the faulty sensor readings using training data and statistically detect and identify classes of faults. We illustrate the performance of a hybrid approach on data coming from two actual sensor deployments.

Original languageEnglish
Title of host publicationMASS 2012 - 9th IEEE International Conference on Mobile Ad-Hoc and Sensor Systems
Pages281-289
Number of pages9
DOIs
Publication statusPublished - 2012 Dec 1
Externally publishedYes
Event9th IEEE International Conference on Mobile Ad-Hoc and Sensor Systems, MASS 2012 - Las Vegas, NV, United States
Duration: 2012 Oct 82012 Oct 11

Other

Other9th IEEE International Conference on Mobile Ad-Hoc and Sensor Systems, MASS 2012
CountryUnited States
CityLas Vegas, NV
Period12/10/812/10/11

Fingerprint

Fault detection
Wireless sensor networks
Sensors
Sensor networks
Aging of materials

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Warriach, E. U., Nguyen, T. A., Aiello, M., & Tei, K. (2012). A hybrid fault detection approach for context-aware wireless sensor networks. In MASS 2012 - 9th IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (pp. 281-289). [6502527] https://doi.org/10.1109/MASS.2012.6502527

A hybrid fault detection approach for context-aware wireless sensor networks. / Warriach, Ehsan Ullah; Nguyen, Tuan Anh; Aiello, Marco; Tei, Kenji.

MASS 2012 - 9th IEEE International Conference on Mobile Ad-Hoc and Sensor Systems. 2012. p. 281-289 6502527.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Warriach, EU, Nguyen, TA, Aiello, M & Tei, K 2012, A hybrid fault detection approach for context-aware wireless sensor networks. in MASS 2012 - 9th IEEE International Conference on Mobile Ad-Hoc and Sensor Systems., 6502527, pp. 281-289, 9th IEEE International Conference on Mobile Ad-Hoc and Sensor Systems, MASS 2012, Las Vegas, NV, United States, 12/10/8. https://doi.org/10.1109/MASS.2012.6502527
Warriach EU, Nguyen TA, Aiello M, Tei K. A hybrid fault detection approach for context-aware wireless sensor networks. In MASS 2012 - 9th IEEE International Conference on Mobile Ad-Hoc and Sensor Systems. 2012. p. 281-289. 6502527 https://doi.org/10.1109/MASS.2012.6502527
Warriach, Ehsan Ullah ; Nguyen, Tuan Anh ; Aiello, Marco ; Tei, Kenji. / A hybrid fault detection approach for context-aware wireless sensor networks. MASS 2012 - 9th IEEE International Conference on Mobile Ad-Hoc and Sensor Systems. 2012. pp. 281-289
@inproceedings{6fe8cf1ec0c0466eb511c9e6c0680df0,
title = "A hybrid fault detection approach for context-aware wireless sensor networks",
abstract = "Wireless Sensor Network (WSN) deployment experiences show that data collected is prone to be imprecise and faulty due to internal and external influences, such as battery drain, environmental interference, sensor aging. An early detection of such faults is necessary for the effective operation of the sensor network. We focus on identifying data fault types and their causes. In particular, we propose a hybrid approach to the detection of faults based on three qualitatively different classes of fault detection methods. Rule-based methods leverage domain and expert knowledge to develop heuristic rules for identifying and classifying faults. Estimation methods predict normal sensor behavior by leveraging sensor spatial and temporal correlations, identifying erroneous sensor readings as faults. Finally, learning-based methods are inferred a model for the faulty sensor readings using training data and statistically detect and identify classes of faults. We illustrate the performance of a hybrid approach on data coming from two actual sensor deployments.",
author = "Warriach, {Ehsan Ullah} and Nguyen, {Tuan Anh} and Marco Aiello and Kenji Tei",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/MASS.2012.6502527",
language = "English",
isbn = "9781467324335",
pages = "281--289",
booktitle = "MASS 2012 - 9th IEEE International Conference on Mobile Ad-Hoc and Sensor Systems",

}

TY - GEN

T1 - A hybrid fault detection approach for context-aware wireless sensor networks

AU - Warriach, Ehsan Ullah

AU - Nguyen, Tuan Anh

AU - Aiello, Marco

AU - Tei, Kenji

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Wireless Sensor Network (WSN) deployment experiences show that data collected is prone to be imprecise and faulty due to internal and external influences, such as battery drain, environmental interference, sensor aging. An early detection of such faults is necessary for the effective operation of the sensor network. We focus on identifying data fault types and their causes. In particular, we propose a hybrid approach to the detection of faults based on three qualitatively different classes of fault detection methods. Rule-based methods leverage domain and expert knowledge to develop heuristic rules for identifying and classifying faults. Estimation methods predict normal sensor behavior by leveraging sensor spatial and temporal correlations, identifying erroneous sensor readings as faults. Finally, learning-based methods are inferred a model for the faulty sensor readings using training data and statistically detect and identify classes of faults. We illustrate the performance of a hybrid approach on data coming from two actual sensor deployments.

AB - Wireless Sensor Network (WSN) deployment experiences show that data collected is prone to be imprecise and faulty due to internal and external influences, such as battery drain, environmental interference, sensor aging. An early detection of such faults is necessary for the effective operation of the sensor network. We focus on identifying data fault types and their causes. In particular, we propose a hybrid approach to the detection of faults based on three qualitatively different classes of fault detection methods. Rule-based methods leverage domain and expert knowledge to develop heuristic rules for identifying and classifying faults. Estimation methods predict normal sensor behavior by leveraging sensor spatial and temporal correlations, identifying erroneous sensor readings as faults. Finally, learning-based methods are inferred a model for the faulty sensor readings using training data and statistically detect and identify classes of faults. We illustrate the performance of a hybrid approach on data coming from two actual sensor deployments.

UR - http://www.scopus.com/inward/record.url?scp=84877659465&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84877659465&partnerID=8YFLogxK

U2 - 10.1109/MASS.2012.6502527

DO - 10.1109/MASS.2012.6502527

M3 - Conference contribution

SN - 9781467324335

SP - 281

EP - 289

BT - MASS 2012 - 9th IEEE International Conference on Mobile Ad-Hoc and Sensor Systems

ER -