Handling outliers and concept drift in online mass flow prediction in CFB boilers

J. Bakker; M. Pechenizkiy; I. Zliobaite; A. Ivannikov; T. Kärkkäinen

doi:10.1145/1601966.1601972

Handling outliers and concept drift in online mass flow prediction in CFB boilers

J. Bakker, M. Pechenizkiy, I. Zliobaite, A. Ivannikov, T. Kärkkäinen

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

7 Citations (Scopus)

Abstract

In this paper we consider an application of data mining technology to the analysis of time series data from a pilot circulating fluidized bed (CFB) reactor. We focus on the problem of the online mass prediction in CFB boilers. We present a framework based on switching regression models depending on perceived changes in the data. We analyze three alternatives for change detection. Additionally, a noise canceling and a state determination and windowing mechanisms are used for improving the robustness of online prediction. We validate our ideas on real data collected from the pilot CFB boiler.

Original language	English
Title of host publication	Proceedings of the Third International Workshop on Knowledge Discovery from Sensor Data (KDD 2009, Paris, France, June 28, 2009)
Editors	O.A. Omitaomu, A.R. Ganguly, J. Gama, R.R. Vatsavai, N.V. Chawla, M.M. Gaber
Place of Publication	New York
Publisher	Association for Computing Machinery, Inc
Pages	13-22
ISBN (Print)	978-1-60558-668-7
DOIs	https://doi.org/10.1145/1601966.1601972
Publication status	Published - 2009

Access to Document

10.1145/1601966.1601972

Fingerprint Dive into the research topics of 'Handling outliers and concept drift in online mass flow prediction in CFB boilers'. Together they form a unique fingerprint.

Cite this

Bakker, J., Pechenizkiy, M., Zliobaite, I., Ivannikov, A., & Kärkkäinen, T. (2009). Handling outliers and concept drift in online mass flow prediction in CFB boilers. In O. A. Omitaomu, A. R. Ganguly, J. Gama, R. R. Vatsavai, N. V. Chawla, & M. M. Gaber (Eds.), Proceedings of the Third International Workshop on Knowledge Discovery from Sensor Data (KDD 2009, Paris, France, June 28, 2009) (pp. 13-22). Association for Computing Machinery, Inc. https://doi.org/10.1145/1601966.1601972

Bakker, J. ; Pechenizkiy, M. ; Zliobaite, I. ; Ivannikov, A. ; Kärkkäinen, T. / Handling outliers and concept drift in online mass flow prediction in CFB boilers. Proceedings of the Third International Workshop on Knowledge Discovery from Sensor Data (KDD 2009, Paris, France, June 28, 2009). editor / O.A. Omitaomu ; A.R. Ganguly ; J. Gama ; R.R. Vatsavai ; N.V. Chawla ; M.M. Gaber. New York : Association for Computing Machinery, Inc, 2009. pp. 13-22

@inproceedings{3bb043f04da1400ab1bb046fb166cd3f,

title = "Handling outliers and concept drift in online mass flow prediction in CFB boilers",

abstract = "In this paper we consider an application of data mining technology to the analysis of time series data from a pilot circulating fluidized bed (CFB) reactor. We focus on the problem of the online mass prediction in CFB boilers. We present a framework based on switching regression models depending on perceived changes in the data. We analyze three alternatives for change detection. Additionally, a noise canceling and a state determination and windowing mechanisms are used for improving the robustness of online prediction. We validate our ideas on real data collected from the pilot CFB boiler.",

author = "J. Bakker and M. Pechenizkiy and I. Zliobaite and A. Ivannikov and T. K{\"a}rkk{\"a}inen",

year = "2009",

doi = "10.1145/1601966.1601972",

language = "English",

isbn = "978-1-60558-668-7",

pages = "13--22",

editor = "O.A. Omitaomu and A.R. Ganguly and J. Gama and R.R. Vatsavai and N.V. Chawla and M.M. Gaber",

booktitle = "Proceedings of the Third International Workshop on Knowledge Discovery from Sensor Data (KDD 2009, Paris, France, June 28, 2009)",

publisher = "Association for Computing Machinery, Inc",

address = "United States",

}

Bakker, J, Pechenizkiy, M, Zliobaite, I, Ivannikov, A & Kärkkäinen, T 2009, Handling outliers and concept drift in online mass flow prediction in CFB boilers. in OA Omitaomu, AR Ganguly, J Gama, RR Vatsavai, NV Chawla & MM Gaber (eds), Proceedings of the Third International Workshop on Knowledge Discovery from Sensor Data (KDD 2009, Paris, France, June 28, 2009). Association for Computing Machinery, Inc, New York, pp. 13-22. https://doi.org/10.1145/1601966.1601972

Handling outliers and concept drift in online mass flow prediction in CFB boilers. / Bakker, J.; Pechenizkiy, M.; Zliobaite, I.; Ivannikov, A.; Kärkkäinen, T.

Proceedings of the Third International Workshop on Knowledge Discovery from Sensor Data (KDD 2009, Paris, France, June 28, 2009). ed. / O.A. Omitaomu; A.R. Ganguly; J. Gama; R.R. Vatsavai; N.V. Chawla; M.M. Gaber. New York : Association for Computing Machinery, Inc, 2009. p. 13-22.

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

TY - GEN

T1 - Handling outliers and concept drift in online mass flow prediction in CFB boilers

AU - Bakker, J.

AU - Pechenizkiy, M.

AU - Zliobaite, I.

AU - Ivannikov, A.

AU - Kärkkäinen, T.

PY - 2009

Y1 - 2009

N2 - In this paper we consider an application of data mining technology to the analysis of time series data from a pilot circulating fluidized bed (CFB) reactor. We focus on the problem of the online mass prediction in CFB boilers. We present a framework based on switching regression models depending on perceived changes in the data. We analyze three alternatives for change detection. Additionally, a noise canceling and a state determination and windowing mechanisms are used for improving the robustness of online prediction. We validate our ideas on real data collected from the pilot CFB boiler.

AB - In this paper we consider an application of data mining technology to the analysis of time series data from a pilot circulating fluidized bed (CFB) reactor. We focus on the problem of the online mass prediction in CFB boilers. We present a framework based on switching regression models depending on perceived changes in the data. We analyze three alternatives for change detection. Additionally, a noise canceling and a state determination and windowing mechanisms are used for improving the robustness of online prediction. We validate our ideas on real data collected from the pilot CFB boiler.

U2 - 10.1145/1601966.1601972

DO - 10.1145/1601966.1601972

M3 - Conference contribution

SN - 978-1-60558-668-7

SP - 13

EP - 22

BT - Proceedings of the Third International Workshop on Knowledge Discovery from Sensor Data (KDD 2009, Paris, France, June 28, 2009)

A2 - Omitaomu, O.A.

A2 - Ganguly, A.R.

A2 - Gama, J.

A2 - Vatsavai, R.R.

A2 - Chawla, N.V.

A2 - Gaber, M.M.

PB - Association for Computing Machinery, Inc

CY - New York

ER -

Bakker J, Pechenizkiy M, Zliobaite I, Ivannikov A, Kärkkäinen T. Handling outliers and concept drift in online mass flow prediction in CFB boilers. In Omitaomu OA, Ganguly AR, Gama J, Vatsavai RR, Chawla NV, Gaber MM, editors, Proceedings of the Third International Workshop on Knowledge Discovery from Sensor Data (KDD 2009, Paris, France, June 28, 2009). New York: Association for Computing Machinery, Inc. 2009. p. 13-22 https://doi.org/10.1145/1601966.1601972