Fault classification and model learning from sensory Readings - Framework for fault tolerance in wireless sensor networks

Valentina Baljak, Kenji Tei, Shinichi Honiden

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

5 Citations (Scopus)

Abstract

Primary task of wireless sensor networks is to deliver reliable and accurate information about the phenomena of interest. However, faults are a frequent occurrence and their accumulation affects the quality of service significantly. This leads to a shorter effective lifetime of the network. In this work, we propose a framework for the fault tolerance in sensory readings. The main concept is based on the observation of the pattern that faults leave in data behavior. Based on the duration, continuity and the impact, we propose a complete and consistent classification of faults as they can be observed in sensory readings independently of the underlying cause. Further, we propose that network learns a model of a fault for each faulty node from the past behavior. Each phase of the framework can be implemented with the use of different algorithms appropriate for the task. In this paper we present an instance that relies on neighborhood vote, time series analysis and statistical pattern recognition. Results so far confirm that the scheme works well for dense data-centric wireless sensor networks.

Original languageEnglish
Title of host publicationProceedings of the 2013 IEEE 8th International Conference on Intelligent Sensors, Sensor Networks and Information Processing
Subtitle of host publicationSensing the Future, ISSNIP 2013
Pages408-413
Number of pages6
Volume1
DOIs
Publication statusPublished - 2013 Aug 9
Externally publishedYes
Event2013 IEEE 8th International Conference on Intelligent Sensors, Sensor Networks and Information Processing: Sensing the Future, ISSNIP 2013 - Melbourne, VIC, Australia
Duration: 2013 Apr 22013 Apr 5

Other

Other2013 IEEE 8th International Conference on Intelligent Sensors, Sensor Networks and Information Processing: Sensing the Future, ISSNIP 2013
CountryAustralia
CityMelbourne, VIC
Period13/4/213/4/5

Fingerprint

Fault tolerance
Wireless sensor networks
Time series analysis
Pattern recognition
Quality of service

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Information Systems

Cite this

Baljak, V., Tei, K., & Honiden, S. (2013). Fault classification and model learning from sensory Readings - Framework for fault tolerance in wireless sensor networks. In Proceedings of the 2013 IEEE 8th International Conference on Intelligent Sensors, Sensor Networks and Information Processing: Sensing the Future, ISSNIP 2013 (Vol. 1, pp. 408-413). [6529825] https://doi.org/10.1109/ISSNIP.2013.6529825

Fault classification and model learning from sensory Readings - Framework for fault tolerance in wireless sensor networks. / Baljak, Valentina; Tei, Kenji; Honiden, Shinichi.

Proceedings of the 2013 IEEE 8th International Conference on Intelligent Sensors, Sensor Networks and Information Processing: Sensing the Future, ISSNIP 2013. Vol. 1 2013. p. 408-413 6529825.

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

Baljak, V, Tei, K & Honiden, S 2013, Fault classification and model learning from sensory Readings - Framework for fault tolerance in wireless sensor networks. in Proceedings of the 2013 IEEE 8th International Conference on Intelligent Sensors, Sensor Networks and Information Processing: Sensing the Future, ISSNIP 2013. vol. 1, 6529825, pp. 408-413, 2013 IEEE 8th International Conference on Intelligent Sensors, Sensor Networks and Information Processing: Sensing the Future, ISSNIP 2013, Melbourne, VIC, Australia, 13/4/2. https://doi.org/10.1109/ISSNIP.2013.6529825
Baljak V, Tei K, Honiden S. Fault classification and model learning from sensory Readings - Framework for fault tolerance in wireless sensor networks. In Proceedings of the 2013 IEEE 8th International Conference on Intelligent Sensors, Sensor Networks and Information Processing: Sensing the Future, ISSNIP 2013. Vol. 1. 2013. p. 408-413. 6529825 https://doi.org/10.1109/ISSNIP.2013.6529825
Baljak, Valentina ; Tei, Kenji ; Honiden, Shinichi. / Fault classification and model learning from sensory Readings - Framework for fault tolerance in wireless sensor networks. Proceedings of the 2013 IEEE 8th International Conference on Intelligent Sensors, Sensor Networks and Information Processing: Sensing the Future, ISSNIP 2013. Vol. 1 2013. pp. 408-413
@inproceedings{6a4cee5526984158a150f46216fdc021,
title = "Fault classification and model learning from sensory Readings - Framework for fault tolerance in wireless sensor networks",
abstract = "Primary task of wireless sensor networks is to deliver reliable and accurate information about the phenomena of interest. However, faults are a frequent occurrence and their accumulation affects the quality of service significantly. This leads to a shorter effective lifetime of the network. In this work, we propose a framework for the fault tolerance in sensory readings. The main concept is based on the observation of the pattern that faults leave in data behavior. Based on the duration, continuity and the impact, we propose a complete and consistent classification of faults as they can be observed in sensory readings independently of the underlying cause. Further, we propose that network learns a model of a fault for each faulty node from the past behavior. Each phase of the framework can be implemented with the use of different algorithms appropriate for the task. In this paper we present an instance that relies on neighborhood vote, time series analysis and statistical pattern recognition. Results so far confirm that the scheme works well for dense data-centric wireless sensor networks.",
author = "Valentina Baljak and Kenji Tei and Shinichi Honiden",
year = "2013",
month = "8",
day = "9",
doi = "10.1109/ISSNIP.2013.6529825",
language = "English",
isbn = "9781467355001",
volume = "1",
pages = "408--413",
booktitle = "Proceedings of the 2013 IEEE 8th International Conference on Intelligent Sensors, Sensor Networks and Information Processing",

}

TY - GEN

T1 - Fault classification and model learning from sensory Readings - Framework for fault tolerance in wireless sensor networks

AU - Baljak, Valentina

AU - Tei, Kenji

AU - Honiden, Shinichi

PY - 2013/8/9

Y1 - 2013/8/9

N2 - Primary task of wireless sensor networks is to deliver reliable and accurate information about the phenomena of interest. However, faults are a frequent occurrence and their accumulation affects the quality of service significantly. This leads to a shorter effective lifetime of the network. In this work, we propose a framework for the fault tolerance in sensory readings. The main concept is based on the observation of the pattern that faults leave in data behavior. Based on the duration, continuity and the impact, we propose a complete and consistent classification of faults as they can be observed in sensory readings independently of the underlying cause. Further, we propose that network learns a model of a fault for each faulty node from the past behavior. Each phase of the framework can be implemented with the use of different algorithms appropriate for the task. In this paper we present an instance that relies on neighborhood vote, time series analysis and statistical pattern recognition. Results so far confirm that the scheme works well for dense data-centric wireless sensor networks.

AB - Primary task of wireless sensor networks is to deliver reliable and accurate information about the phenomena of interest. However, faults are a frequent occurrence and their accumulation affects the quality of service significantly. This leads to a shorter effective lifetime of the network. In this work, we propose a framework for the fault tolerance in sensory readings. The main concept is based on the observation of the pattern that faults leave in data behavior. Based on the duration, continuity and the impact, we propose a complete and consistent classification of faults as they can be observed in sensory readings independently of the underlying cause. Further, we propose that network learns a model of a fault for each faulty node from the past behavior. Each phase of the framework can be implemented with the use of different algorithms appropriate for the task. In this paper we present an instance that relies on neighborhood vote, time series analysis and statistical pattern recognition. Results so far confirm that the scheme works well for dense data-centric wireless sensor networks.

UR - http://www.scopus.com/inward/record.url?scp=84881088723&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881088723&partnerID=8YFLogxK

U2 - 10.1109/ISSNIP.2013.6529825

DO - 10.1109/ISSNIP.2013.6529825

M3 - Conference contribution

AN - SCOPUS:84881088723

SN - 9781467355001

VL - 1

SP - 408

EP - 413

BT - Proceedings of the 2013 IEEE 8th International Conference on Intelligent Sensors, Sensor Networks and Information Processing

ER -