Applying time series analysis and neighbourhood voting in a decentralised approach for fault detection and classification in WSNs

Tuan Anh Nguyen, Doina Bucur, Marco Aiello, Kenji Tei

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

16 Citations (Scopus)

Abstract

In pervasive computing environments, wireless sensor networks play an important infrastructure role, collecting reliable and accurate context information so that applications are able to provide services to users on demand. In such environments, sensors should be self-adaptive by taking correct decisions based on sensed data in real-time in a decentralised manner; however, sensed data is often faulty. We thus design a decentralised scheme for fault detection and classification in sensor data in which each sensor node does localised fault detection. A combination of neighbourhood voting and time series data analysis techniques are used to detect faults. We also study the comparative accuracy of both the union and the intersection of the two techniques. Then, detected faults are classified into known fault categories. An initial evaluation with SensorScope, an outdoor temperature dataset, confirms that our solution is able to detect and classify faulty readings into four fault types, namely, 1) random, 2) malfunction, 3) bias, and 4) drift with accuracy up to 95%. The results also show that, with the experimental dataset, the time series data analysis technique performs comparable well in most of the cases, whilst in some other cases the support from neighbourhood voting technique and histogram analysis helps our hybrid solution to successfully detects the faults of all types.

Original languageEnglish
Title of host publicationProceedings of the 4th Symposium on Information and Communication Technology, SoICT 2013
Pages234-241
Number of pages8
DOIs
Publication statusPublished - 2013 Dec 1
Externally publishedYes
Event4th Symposium on Information and Communication Technology, SoICT 2013 - Da Nang, Viet Nam
Duration: 2013 Dec 52013 Dec 6

Other

Other4th Symposium on Information and Communication Technology, SoICT 2013
CountryViet Nam
CityDa Nang
Period13/12/513/12/6

Fingerprint

Time series analysis
Fault detection
Time series
Sensors
Ubiquitous computing
Sensor nodes
Wireless sensor networks
Temperature

Keywords

  • Decentralised fault tolerance
  • Online sensory data fault handling
  • Wireless sensor networks

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Cite this

Nguyen, T. A., Bucur, D., Aiello, M., & Tei, K. (2013). Applying time series analysis and neighbourhood voting in a decentralised approach for fault detection and classification in WSNs. In Proceedings of the 4th Symposium on Information and Communication Technology, SoICT 2013 (pp. 234-241) https://doi.org/10.1145/2542050.2542080

Applying time series analysis and neighbourhood voting in a decentralised approach for fault detection and classification in WSNs. / Nguyen, Tuan Anh; Bucur, Doina; Aiello, Marco; Tei, Kenji.

Proceedings of the 4th Symposium on Information and Communication Technology, SoICT 2013. 2013. p. 234-241.

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

Nguyen, TA, Bucur, D, Aiello, M & Tei, K 2013, Applying time series analysis and neighbourhood voting in a decentralised approach for fault detection and classification in WSNs. in Proceedings of the 4th Symposium on Information and Communication Technology, SoICT 2013. pp. 234-241, 4th Symposium on Information and Communication Technology, SoICT 2013, Da Nang, Viet Nam, 13/12/5. https://doi.org/10.1145/2542050.2542080
Nguyen TA, Bucur D, Aiello M, Tei K. Applying time series analysis and neighbourhood voting in a decentralised approach for fault detection and classification in WSNs. In Proceedings of the 4th Symposium on Information and Communication Technology, SoICT 2013. 2013. p. 234-241 https://doi.org/10.1145/2542050.2542080
Nguyen, Tuan Anh ; Bucur, Doina ; Aiello, Marco ; Tei, Kenji. / Applying time series analysis and neighbourhood voting in a decentralised approach for fault detection and classification in WSNs. Proceedings of the 4th Symposium on Information and Communication Technology, SoICT 2013. 2013. pp. 234-241
@inproceedings{4fdee93d007e4218b8206729b5fabfc5,
title = "Applying time series analysis and neighbourhood voting in a decentralised approach for fault detection and classification in WSNs",
abstract = "In pervasive computing environments, wireless sensor networks play an important infrastructure role, collecting reliable and accurate context information so that applications are able to provide services to users on demand. In such environments, sensors should be self-adaptive by taking correct decisions based on sensed data in real-time in a decentralised manner; however, sensed data is often faulty. We thus design a decentralised scheme for fault detection and classification in sensor data in which each sensor node does localised fault detection. A combination of neighbourhood voting and time series data analysis techniques are used to detect faults. We also study the comparative accuracy of both the union and the intersection of the two techniques. Then, detected faults are classified into known fault categories. An initial evaluation with SensorScope, an outdoor temperature dataset, confirms that our solution is able to detect and classify faulty readings into four fault types, namely, 1) random, 2) malfunction, 3) bias, and 4) drift with accuracy up to 95{\%}. The results also show that, with the experimental dataset, the time series data analysis technique performs comparable well in most of the cases, whilst in some other cases the support from neighbourhood voting technique and histogram analysis helps our hybrid solution to successfully detects the faults of all types.",
keywords = "Decentralised fault tolerance, Online sensory data fault handling, Wireless sensor networks",
author = "Nguyen, {Tuan Anh} and Doina Bucur and Marco Aiello and Kenji Tei",
year = "2013",
month = "12",
day = "1",
doi = "10.1145/2542050.2542080",
language = "English",
isbn = "9781450324540",
pages = "234--241",
booktitle = "Proceedings of the 4th Symposium on Information and Communication Technology, SoICT 2013",

}

TY - GEN

T1 - Applying time series analysis and neighbourhood voting in a decentralised approach for fault detection and classification in WSNs

AU - Nguyen, Tuan Anh

AU - Bucur, Doina

AU - Aiello, Marco

AU - Tei, Kenji

PY - 2013/12/1

Y1 - 2013/12/1

N2 - In pervasive computing environments, wireless sensor networks play an important infrastructure role, collecting reliable and accurate context information so that applications are able to provide services to users on demand. In such environments, sensors should be self-adaptive by taking correct decisions based on sensed data in real-time in a decentralised manner; however, sensed data is often faulty. We thus design a decentralised scheme for fault detection and classification in sensor data in which each sensor node does localised fault detection. A combination of neighbourhood voting and time series data analysis techniques are used to detect faults. We also study the comparative accuracy of both the union and the intersection of the two techniques. Then, detected faults are classified into known fault categories. An initial evaluation with SensorScope, an outdoor temperature dataset, confirms that our solution is able to detect and classify faulty readings into four fault types, namely, 1) random, 2) malfunction, 3) bias, and 4) drift with accuracy up to 95%. The results also show that, with the experimental dataset, the time series data analysis technique performs comparable well in most of the cases, whilst in some other cases the support from neighbourhood voting technique and histogram analysis helps our hybrid solution to successfully detects the faults of all types.

AB - In pervasive computing environments, wireless sensor networks play an important infrastructure role, collecting reliable and accurate context information so that applications are able to provide services to users on demand. In such environments, sensors should be self-adaptive by taking correct decisions based on sensed data in real-time in a decentralised manner; however, sensed data is often faulty. We thus design a decentralised scheme for fault detection and classification in sensor data in which each sensor node does localised fault detection. A combination of neighbourhood voting and time series data analysis techniques are used to detect faults. We also study the comparative accuracy of both the union and the intersection of the two techniques. Then, detected faults are classified into known fault categories. An initial evaluation with SensorScope, an outdoor temperature dataset, confirms that our solution is able to detect and classify faulty readings into four fault types, namely, 1) random, 2) malfunction, 3) bias, and 4) drift with accuracy up to 95%. The results also show that, with the experimental dataset, the time series data analysis technique performs comparable well in most of the cases, whilst in some other cases the support from neighbourhood voting technique and histogram analysis helps our hybrid solution to successfully detects the faults of all types.

KW - Decentralised fault tolerance

KW - Online sensory data fault handling

KW - Wireless sensor networks

UR - http://www.scopus.com/inward/record.url?scp=84893018045&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893018045&partnerID=8YFLogxK

U2 - 10.1145/2542050.2542080

DO - 10.1145/2542050.2542080

M3 - Conference contribution

AN - SCOPUS:84893018045

SN - 9781450324540

SP - 234

EP - 241

BT - Proceedings of the 4th Symposium on Information and Communication Technology, SoICT 2013

ER -