Quantile index for gradual and abrupt change detection from CFB boiler sensor data in online settings

A. Maslov; M. Pechenizkiy; T. Kärkkäinen; Matti Tähtinen

doi:10.1145/2350182.2350185

Quantile index for gradual and abrupt change detection from CFB boiler sensor data in online settings

A. Maslov, M. Pechenizkiy, T. Kärkkäinen, Matti Tähtinen

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

2 Citations (Scopus)

Abstract

In this paper we consider the problem of online detection of gradual and abrupt changes in sensor data having high levels of noise and outliers. We propose a simple heuristic method based on the Quantile Index (QI) and study how robust this method is for detecting both gradual and abrupt changes with such data. We evaluate the performance of our method on the artificially generated and real datasets that represent different operational settings of a pilot circulating fluidized bed (CFB) reactor and CFB cold model. Our experiments suggest that QI can be used for designing very simple yet effective methods for gradual change detection in the noisy sensor data. It can be also used for detecting abrupt changes in the data unless they occur too often one after another

Original language	English
Title of host publication	Proceedings of the Sixth International Workshop on Knowledge Discovery from Sensor Data
Subtitle of host publication	SensorKDD 2012
Place of Publication	New York, NY, USA
Publisher	Association for Computing Machinery ACM
Pages	25-33
ISBN (Print)	978-1-4503-1554-8
DOIs	https://doi.org/10.1145/2350182.2350185
Publication status	Published - 2012
MoE publication type	Not Eligible
Event	6th International Workshop on Knowledge Discovery from Sensor Data, SensorKDD'12 - Held in Conjunction with the 18th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2012 - Beijing, China Duration: 12 Aug 2012 → …

Conference

Conference	6th International Workshop on Knowledge Discovery from Sensor Data, SensorKDD'12 - Held in Conjunction with the 18th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2012
Abbreviated title	SensorKDD 2012
Country/Territory	China
City	Beijing
Period	12/08/12 → …

Access to Document

10.1145/2350182.2350185

Cite this

Maslov, A., Pechenizkiy, M., Kärkkäinen, T., & Tähtinen, M. (2012). Quantile index for gradual and abrupt change detection from CFB boiler sensor data in online settings. In Proceedings of the Sixth International Workshop on Knowledge Discovery from Sensor Data: SensorKDD 2012 (pp. 25-33). Association for Computing Machinery ACM. https://doi.org/10.1145/2350182.2350185

@inproceedings{6415625857aa46acbe735a0bb0bdbcbb,

title = "Quantile index for gradual and abrupt change detection from CFB boiler sensor data in online settings",

abstract = "In this paper we consider the problem of online detection of gradual and abrupt changes in sensor data having high levels of noise and outliers. We propose a simple heuristic method based on the Quantile Index (QI) and study how robust this method is for detecting both gradual and abrupt changes with such data. We evaluate the performance of our method on the artificially generated and real datasets that represent different operational settings of a pilot circulating fluidized bed (CFB) reactor and CFB cold model. Our experiments suggest that QI can be used for designing very simple yet effective methods for gradual change detection in the noisy sensor data. It can be also used for detecting abrupt changes in the data unless they occur too often one after another",

author = "A. Maslov and M. Pechenizkiy and T. K{\"a}rkk{\"a}inen and Matti T{\"a}htinen",

year = "2012",

doi = "10.1145/2350182.2350185",

language = "English",

isbn = "978-1-4503-1554-8",

pages = "25--33",

booktitle = "Proceedings of the Sixth International Workshop on Knowledge Discovery from Sensor Data",

publisher = "Association for Computing Machinery ACM",

address = "United States",

note = "6th International Workshop on Knowledge Discovery from Sensor Data, SensorKDD'12 - Held in Conjunction with the 18th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2012, SensorKDD 2012 ; Conference date: 12-08-2012",

}

Maslov, A, Pechenizkiy, M, Kärkkäinen, T & Tähtinen, M 2012, Quantile index for gradual and abrupt change detection from CFB boiler sensor data in online settings. in Proceedings of the Sixth International Workshop on Knowledge Discovery from Sensor Data: SensorKDD 2012. Association for Computing Machinery ACM, New York, NY, USA, pp. 25-33, 6th International Workshop on Knowledge Discovery from Sensor Data, SensorKDD'12 - Held in Conjunction with the 18th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2012, Beijing, China, 12/08/12. https://doi.org/10.1145/2350182.2350185

Quantile index for gradual and abrupt change detection from CFB boiler sensor data in online settings. / Maslov, A.; Pechenizkiy, M.; Kärkkäinen, T. et al.

Proceedings of the Sixth International Workshop on Knowledge Discovery from Sensor Data: SensorKDD 2012. New York, NY, USA : Association for Computing Machinery ACM, 2012. p. 25-33.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Quantile index for gradual and abrupt change detection from CFB boiler sensor data in online settings

AU - Maslov, A.

AU - Pechenizkiy, M.

AU - Kärkkäinen, T.

AU - Tähtinen, Matti

PY - 2012

Y1 - 2012

N2 - In this paper we consider the problem of online detection of gradual and abrupt changes in sensor data having high levels of noise and outliers. We propose a simple heuristic method based on the Quantile Index (QI) and study how robust this method is for detecting both gradual and abrupt changes with such data. We evaluate the performance of our method on the artificially generated and real datasets that represent different operational settings of a pilot circulating fluidized bed (CFB) reactor and CFB cold model. Our experiments suggest that QI can be used for designing very simple yet effective methods for gradual change detection in the noisy sensor data. It can be also used for detecting abrupt changes in the data unless they occur too often one after another

AB - In this paper we consider the problem of online detection of gradual and abrupt changes in sensor data having high levels of noise and outliers. We propose a simple heuristic method based on the Quantile Index (QI) and study how robust this method is for detecting both gradual and abrupt changes with such data. We evaluate the performance of our method on the artificially generated and real datasets that represent different operational settings of a pilot circulating fluidized bed (CFB) reactor and CFB cold model. Our experiments suggest that QI can be used for designing very simple yet effective methods for gradual change detection in the noisy sensor data. It can be also used for detecting abrupt changes in the data unless they occur too often one after another

U2 - 10.1145/2350182.2350185

DO - 10.1145/2350182.2350185

M3 - Conference article in proceedings

SN - 978-1-4503-1554-8

SP - 25

EP - 33

BT - Proceedings of the Sixth International Workshop on Knowledge Discovery from Sensor Data

PB - Association for Computing Machinery ACM

CY - New York, NY, USA

T2 - 6th International Workshop on Knowledge Discovery from Sensor Data, SensorKDD'12 - Held in Conjunction with the 18th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2012

Y2 - 12 August 2012

ER -

Quantile index for gradual and abrupt change detection from CFB boiler sensor data in online settings

Abstract

Conference

Access to Document

Fingerprint

Cite this