A machine learning approach for identifying and classifying faults in wireless sensor networks

Ehsan Ullah Warriach; Marco Aiello; Kenji Tei

doi:10.1109/ICCSE.2012.90

A machine learning approach for identifying and classifying faults in wireless sensor networks

Ehsan Ullah Warriach^*, Marco Aiello, Kenji Tei

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

21 Citations (Scopus)

Abstract

Wireless Sensor Network (WSN) deployment experiences show that collected data is prone to be faulty. Faults are due to internal and external influences, such as calibration, low battery, environmental interference and sensor aging. However, only few solutions exist to deal with faulty sensory data in WSN. We develop a statistical approach to detect and identify faults in a WSN. In particular, we focus on the identification and classification of data and system fault types as it is essential to perform accurate recovery actions. Our method uses Hidden Markov Models (HMMs) to capture the fault-free dynamics of an environment and dynamics of faulty data. It then performs a structural analysis of these HMMs to determine the type of data and system faults affecting sensor measurements. The approach is validated using real data obtained from over one month of samples from motes deployed in an actual living lab.

Original language	English
Title of host publication	CSE 2012/EUC 2012
Subtitle of host publication	Proceedings of the 15th IEEE International Conference on Computational Science and Engineering and 10th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing
Place of Publication	Piscataway, NJ
Pages	618-625
Number of pages	8
DOIs	https://doi.org/10.1109/ICCSE.2012.90
Publication status	Published - 2012
Externally published	Yes
Event	15th IEEE International Conference on Computational Science and Engineering, CSE 2012 and 10th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, EUC 2012 - Paphos, Cyprus Duration: 5 Dec 2012 → 7 Dec 2012

Other

Other	15th IEEE International Conference on Computational Science and Engineering, CSE 2012 and 10th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, EUC 2012
Country/Territory	Cyprus
City	Paphos
Period	5/12/12 → 7/12/12

Access to Document

10.1109/ICCSE.2012.90

Cite this

Warriach, E. U., Aiello, M., & Tei, K. (2012). A machine learning approach for identifying and classifying faults in wireless sensor networks. In CSE 2012/EUC 2012: Proceedings of the 15th IEEE International Conference on Computational Science and Engineering and 10th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing (pp. 618-625). https://doi.org/10.1109/ICCSE.2012.90

Warriach, Ehsan Ullah ; Aiello, Marco ; Tei, Kenji. / A machine learning approach for identifying and classifying faults in wireless sensor networks. CSE 2012/EUC 2012: Proceedings of the 15th IEEE International Conference on Computational Science and Engineering and 10th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing. Piscataway, NJ, 2012. pp. 618-625

@inproceedings{3992c0db36f5434b8f774424292614a3,

title = "A machine learning approach for identifying and classifying faults in wireless sensor networks",

abstract = "Wireless Sensor Network (WSN) deployment experiences show that collected data is prone to be faulty. Faults are due to internal and external influences, such as calibration, low battery, environmental interference and sensor aging. However, only few solutions exist to deal with faulty sensory data in WSN. We develop a statistical approach to detect and identify faults in a WSN. In particular, we focus on the identification and classification of data and system fault types as it is essential to perform accurate recovery actions. Our method uses Hidden Markov Models (HMMs) to capture the fault-free dynamics of an environment and dynamics of faulty data. It then performs a structural analysis of these HMMs to determine the type of data and system faults affecting sensor measurements. The approach is validated using real data obtained from over one month of samples from motes deployed in an actual living lab.",

author = "Warriach, {Ehsan Ullah} and Marco Aiello and Kenji Tei",

year = "2012",

doi = "10.1109/ICCSE.2012.90",

language = "English",

isbn = "9780769549149",

pages = "618--625",

booktitle = "CSE 2012/EUC 2012",

note = "15th IEEE International Conference on Computational Science and Engineering, CSE 2012 and 10th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, EUC 2012 ; Conference date: 05-12-2012 Through 07-12-2012",

}

Warriach, EU, Aiello, M & Tei, K 2012, A machine learning approach for identifying and classifying faults in wireless sensor networks. in CSE 2012/EUC 2012: Proceedings of the 15th IEEE International Conference on Computational Science and Engineering and 10th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing. Piscataway, NJ, pp. 618-625, 15th IEEE International Conference on Computational Science and Engineering, CSE 2012 and 10th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, EUC 2012, Paphos, Cyprus, 5/12/12. https://doi.org/10.1109/ICCSE.2012.90

A machine learning approach for identifying and classifying faults in wireless sensor networks. / Warriach, Ehsan Ullah; Aiello, Marco; Tei, Kenji.
CSE 2012/EUC 2012: Proceedings of the 15th IEEE International Conference on Computational Science and Engineering and 10th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing. Piscataway, NJ, 2012. p. 618-625.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - A machine learning approach for identifying and classifying faults in wireless sensor networks

AU - Warriach, Ehsan Ullah

AU - Aiello, Marco

AU - Tei, Kenji

PY - 2012

Y1 - 2012

N2 - Wireless Sensor Network (WSN) deployment experiences show that collected data is prone to be faulty. Faults are due to internal and external influences, such as calibration, low battery, environmental interference and sensor aging. However, only few solutions exist to deal with faulty sensory data in WSN. We develop a statistical approach to detect and identify faults in a WSN. In particular, we focus on the identification and classification of data and system fault types as it is essential to perform accurate recovery actions. Our method uses Hidden Markov Models (HMMs) to capture the fault-free dynamics of an environment and dynamics of faulty data. It then performs a structural analysis of these HMMs to determine the type of data and system faults affecting sensor measurements. The approach is validated using real data obtained from over one month of samples from motes deployed in an actual living lab.

AB - Wireless Sensor Network (WSN) deployment experiences show that collected data is prone to be faulty. Faults are due to internal and external influences, such as calibration, low battery, environmental interference and sensor aging. However, only few solutions exist to deal with faulty sensory data in WSN. We develop a statistical approach to detect and identify faults in a WSN. In particular, we focus on the identification and classification of data and system fault types as it is essential to perform accurate recovery actions. Our method uses Hidden Markov Models (HMMs) to capture the fault-free dynamics of an environment and dynamics of faulty data. It then performs a structural analysis of these HMMs to determine the type of data and system faults affecting sensor measurements. The approach is validated using real data obtained from over one month of samples from motes deployed in an actual living lab.

UR - http://www.scopus.com/inward/record.url?scp=84874094695&partnerID=8YFLogxK

U2 - 10.1109/ICCSE.2012.90

DO - 10.1109/ICCSE.2012.90

M3 - Conference proceeding contribution

AN - SCOPUS:84874094695

SN - 9780769549149

SP - 618

EP - 625

BT - CSE 2012/EUC 2012

CY - Piscataway, NJ

T2 - 15th IEEE International Conference on Computational Science and Engineering, CSE 2012 and 10th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, EUC 2012

Y2 - 5 December 2012 through 7 December 2012

ER -

Warriach EU, Aiello M, Tei K. A machine learning approach for identifying and classifying faults in wireless sensor networks. In CSE 2012/EUC 2012: Proceedings of the 15th IEEE International Conference on Computational Science and Engineering and 10th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing. Piscataway, NJ. 2012. p. 618-625 doi: 10.1109/ICCSE.2012.90

A machine learning approach for identifying and classifying faults in wireless sensor networks

Abstract

Other

Access to Document

Other files and links

Fingerprint

Cite this