Data anomaly detection in wireless sensor networks with application to an oil refinery

P. Gil; H. Martins; F. Januário; Amâncio Santos; L. Palma; A. Cardoso; J. Henriques

doi:10.1109/CONTROLO.2018.8514551

Data anomaly detection in wireless sensor networks with application to an oil refinery

P. Gil, H. Martins, F. Januário, Amâncio Santos, L. Palma, A. Cardoso, J. Henriques

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

1 Citation (Scopus)

Abstract

This paper presents a study concerning the online detection of outliers in non-stationary time-series collected over Wireless Sensor Networks on scenario implemented at an oil refinery. Two different approaches are under assessment. One based on the Least Squares Support Vector Machine and sliding window learning and standard Gaussian kernel. The other consists in a modification to the standard Gaussian kernel in order to improve the detection performance for non-stationary data streams. The implementability and effectiveness of these methods are evaluate on an oil refinery test-bed over a Wireless Sensor Network.

Original language	English
Title of host publication	13th APCA International Conference on Control and Soft Computing, CONTROLO 2018 - Proceedings
Editors	Cesar Teixeira, Jorge Henriques, Paulo Gil, Alberto Cardoso
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	425-429
Number of pages	5
ISBN (Electronic)	9781538653463
DOIs	https://doi.org/10.1109/CONTROLO.2018.8514551
Publication status	Published - 29 Oct 2018
Event	13th APCA International Conference on Control and Soft Computing, CONTROLO 2018 - Ponta Delgada, Sao Miguel Island, Azores, Portugal Duration: 4 Jun 2018 → 6 Jun 2018

Conference

Conference	13th APCA International Conference on Control and Soft Computing, CONTROLO 2018
Country/Territory	Portugal
City	Ponta Delgada, Sao Miguel Island, Azores
Period	4/06/18 → 6/06/18

Access to Document

10.1109/CONTROLO.2018.8514551

Cite this

Gil, P., Martins, H., Januário, F., Santos, A., Palma, L., Cardoso, A., & Henriques, J. (2018). Data anomaly detection in wireless sensor networks with application to an oil refinery. In C. Teixeira, J. Henriques, P. Gil, & A. Cardoso (Eds.), 13th APCA International Conference on Control and Soft Computing, CONTROLO 2018 - Proceedings (pp. 425-429). Article 8514551 Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/CONTROLO.2018.8514551

Gil, P. ; Martins, H. ; Januário, F. et al. / Data anomaly detection in wireless sensor networks with application to an oil refinery. 13th APCA International Conference on Control and Soft Computing, CONTROLO 2018 - Proceedings. editor / Cesar Teixeira ; Jorge Henriques ; Paulo Gil ; Alberto Cardoso. Institute of Electrical and Electronics Engineers (IEEE), 2018. pp. 425-429

@inproceedings{c699726131a44a3aa70181c78f186d00,

title = "Data anomaly detection in wireless sensor networks with application to an oil refinery",

abstract = "This paper presents a study concerning the online detection of outliers in non-stationary time-series collected over Wireless Sensor Networks on scenario implemented at an oil refinery. Two different approaches are under assessment. One based on the Least Squares Support Vector Machine and sliding window learning and standard Gaussian kernel. The other consists in a modification to the standard Gaussian kernel in order to improve the detection performance for non-stationary data streams. The implementability and effectiveness of these methods are evaluate on an oil refinery test-bed over a Wireless Sensor Network.",

author = "P. Gil and H. Martins and F. Janu{\'a}rio and Am{\^a}ncio Santos and L. Palma and A. Cardoso and J. Henriques",

note = "info:eu-repo/grantAgreement/FCT/5876/147324/PT# info:eu-repo/grantAgreement/FCT/5876/147281/PT# ; 13th APCA International Conference on Control and Soft Computing, CONTROLO 2018 ; Conference date: 04-06-2018 Through 06-06-2018",

year = "2018",

month = oct,

day = "29",

doi = "10.1109/CONTROLO.2018.8514551",

language = "English",

pages = "425--429",

editor = "Cesar Teixeira and Jorge Henriques and Paulo Gil and Alberto Cardoso",

booktitle = "13th APCA International Conference on Control and Soft Computing, CONTROLO 2018 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

Gil, P , Martins, H , Januário, F, Santos, A, Palma, L, Cardoso, A & Henriques, J 2018, Data anomaly detection in wireless sensor networks with application to an oil refinery. in C Teixeira, J Henriques, P Gil & A Cardoso (eds), 13th APCA International Conference on Control and Soft Computing, CONTROLO 2018 - Proceedings., 8514551, Institute of Electrical and Electronics Engineers (IEEE), pp. 425-429, 13th APCA International Conference on Control and Soft Computing, CONTROLO 2018, Ponta Delgada, Sao Miguel Island, Azores, Portugal, 4/06/18. https://doi.org/10.1109/CONTROLO.2018.8514551

Data anomaly detection in wireless sensor networks with application to an oil refinery. / Gil, P.; Martins, H.; Januário, F. et al.
13th APCA International Conference on Control and Soft Computing, CONTROLO 2018 - Proceedings. ed. / Cesar Teixeira; Jorge Henriques; Paulo Gil; Alberto Cardoso. Institute of Electrical and Electronics Engineers (IEEE), 2018. p. 425-429 8514551.

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

TY - GEN

T1 - Data anomaly detection in wireless sensor networks with application to an oil refinery

AU - Gil, P.

AU - Martins, H.

AU - Januário, F.

AU - Santos, Amâncio

AU - Palma, L.

AU - Cardoso, A.

AU - Henriques, J.

N1 - info:eu-repo/grantAgreement/FCT/5876/147324/PT# info:eu-repo/grantAgreement/FCT/5876/147281/PT#

PY - 2018/10/29

Y1 - 2018/10/29

N2 - This paper presents a study concerning the online detection of outliers in non-stationary time-series collected over Wireless Sensor Networks on scenario implemented at an oil refinery. Two different approaches are under assessment. One based on the Least Squares Support Vector Machine and sliding window learning and standard Gaussian kernel. The other consists in a modification to the standard Gaussian kernel in order to improve the detection performance for non-stationary data streams. The implementability and effectiveness of these methods are evaluate on an oil refinery test-bed over a Wireless Sensor Network.

AB - This paper presents a study concerning the online detection of outliers in non-stationary time-series collected over Wireless Sensor Networks on scenario implemented at an oil refinery. Two different approaches are under assessment. One based on the Least Squares Support Vector Machine and sliding window learning and standard Gaussian kernel. The other consists in a modification to the standard Gaussian kernel in order to improve the detection performance for non-stationary data streams. The implementability and effectiveness of these methods are evaluate on an oil refinery test-bed over a Wireless Sensor Network.

UR - http://www.scopus.com/inward/record.url?scp=85057307815&partnerID=8YFLogxK

U2 - 10.1109/CONTROLO.2018.8514551

DO - 10.1109/CONTROLO.2018.8514551

M3 - Conference contribution

AN - SCOPUS:85057307815

SP - 425

EP - 429

BT - 13th APCA International Conference on Control and Soft Computing, CONTROLO 2018 - Proceedings

A2 - Teixeira, Cesar

A2 - Henriques, Jorge

A2 - Gil, Paulo

A2 - Cardoso, Alberto

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 13th APCA International Conference on Control and Soft Computing, CONTROLO 2018

Y2 - 4 June 2018 through 6 June 2018

ER -

Gil P , Martins H , Januário F, Santos A, Palma L, Cardoso A et al. Data anomaly detection in wireless sensor networks with application to an oil refinery. In Teixeira C, Henriques J, Gil P, Cardoso A, editors, 13th APCA International Conference on Control and Soft Computing, CONTROLO 2018 - Proceedings. Institute of Electrical and Electronics Engineers (IEEE). 2018. p. 425-429. 8514551 doi: 10.1109/CONTROLO.2018.8514551

Data anomaly detection in wireless sensor networks with application to an oil refinery

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this