Developing Ensemble Methods for Detecting Anomalies in Water Level Data

Thakolpat Khampuengson; Tony Bagnall; Wenjia Wang

doi:10.1007/978-3-030-63799-6_11

Developing Ensemble Methods for Detecting Anomalies in Water Level Data

Thakolpat Khampuengson, Tony Bagnall, Wenjia Wang

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

1 Citation (Scopus)

23 Downloads (Pure)

Abstract

Telemetry is an automatic system for monitoring environments in a remote or inaccessible area and transmitting data via various media. Data from telemetry stations can be used to produce early warning or decision supports in risky situations. However, sometimes a device in a telemetry system may not work properly and generates some errors in the data, which lead to false alarms or miss true alarms for disasters. We then developed two types of ensembles: (1) simple and (2) complex ensembles for automatically detecting the anomaly data. The ensembles were tested on the data collected from 9 telemetry water level stations and the results clearly show that the complex ensembles are the most accurate and also reliable in detecting anomalies.

Original language	English
Title of host publication	The 22nd International Conference on Big Data Analytics and Knowledge Discovery
Editors	Max Bramer, Richard Ellis
Publisher	Springer
Pages	145-151
Number of pages	7
ISBN (Print)	9783030637989
DOIs	https://doi.org/10.1007/978-3-030-63799-6_11
Publication status	Published - 8 Dec 2020
Event	22nd International Conference on Big Data Analytics and Knowledge Discovery - Bratislava, Slovakia Duration: 14 Sep 2020 → 17 Sep 2020 http://www.dexa.org/dawak2020

Conference

Conference	22nd International Conference on Big Data Analytics and Knowledge Discovery
Country/Territory	Slovakia
City	Bratislava
Period	14/09/20 → 17/09/20
Internet address	http://www.dexa.org/dawak2020

Keywords

Anomaly detection
Ensemble methods
Water level telemetry monitoring

Access to Document

10.1007/978-3-030-63799-6_11

Accepted_ManuscriptAccepted author manuscript, 291 KB

Cite this

@inproceedings{c865366f42e64edc9324adb207be8aaf,

title = "Developing Ensemble Methods for Detecting Anomalies in Water Level Data",

abstract = "Telemetry is an automatic system for monitoring environments in a remote or inaccessible area and transmitting data via various media. Data from telemetry stations can be used to produce early warning or decision supports in risky situations. However, sometimes a device in a telemetry system may not work properly and generates some errors in the data, which lead to false alarms or miss true alarms for disasters. We then developed two types of ensembles: (1) simple and (2) complex ensembles for automatically detecting the anomaly data. The ensembles were tested on the data collected from 9 telemetry water level stations and the results clearly show that the complex ensembles are the most accurate and also reliable in detecting anomalies.",

keywords = "Anomaly detection, Ensemble methods, Water level telemetry monitoring",

author = "Thakolpat Khampuengson and Tony Bagnall and Wenjia Wang",

year = "2020",

month = dec,

day = "8",

doi = "10.1007/978-3-030-63799-6_11",

language = "English",

isbn = "9783030637989",

pages = "145--151",

editor = "Max Bramer and Richard Ellis",

booktitle = "The 22nd International Conference on Big Data Analytics and Knowledge Discovery",

publisher = "Springer",

address = "Germany",

note = "22nd International Conference on Big Data Analytics and Knowledge Discovery ; Conference date: 14-09-2020 Through 17-09-2020",

url = "http://www.dexa.org/dawak2020",

}

Khampuengson, T, Bagnall, T & Wang, W 2020, Developing Ensemble Methods for Detecting Anomalies in Water Level Data. in M Bramer & R Ellis (eds), The 22nd International Conference on Big Data Analytics and Knowledge Discovery. Springer, pp. 145-151, 22nd International Conference on Big Data Analytics and Knowledge Discovery, Bratislava, Slovakia, 14/09/20. https://doi.org/10.1007/978-3-030-63799-6_11

TY - GEN

T1 - Developing Ensemble Methods for Detecting Anomalies in Water Level Data

AU - Khampuengson, Thakolpat

AU - Bagnall, Tony

AU - Wang, Wenjia

PY - 2020/12/8

Y1 - 2020/12/8

N2 - Telemetry is an automatic system for monitoring environments in a remote or inaccessible area and transmitting data via various media. Data from telemetry stations can be used to produce early warning or decision supports in risky situations. However, sometimes a device in a telemetry system may not work properly and generates some errors in the data, which lead to false alarms or miss true alarms for disasters. We then developed two types of ensembles: (1) simple and (2) complex ensembles for automatically detecting the anomaly data. The ensembles were tested on the data collected from 9 telemetry water level stations and the results clearly show that the complex ensembles are the most accurate and also reliable in detecting anomalies.

AB - Telemetry is an automatic system for monitoring environments in a remote or inaccessible area and transmitting data via various media. Data from telemetry stations can be used to produce early warning or decision supports in risky situations. However, sometimes a device in a telemetry system may not work properly and generates some errors in the data, which lead to false alarms or miss true alarms for disasters. We then developed two types of ensembles: (1) simple and (2) complex ensembles for automatically detecting the anomaly data. The ensembles were tested on the data collected from 9 telemetry water level stations and the results clearly show that the complex ensembles are the most accurate and also reliable in detecting anomalies.

KW - Anomaly detection

KW - Ensemble methods

KW - Water level telemetry monitoring

UR - http://www.scopus.com/inward/record.url?scp=85098268519&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-63799-6_11

DO - 10.1007/978-3-030-63799-6_11

M3 - Conference contribution

SN - 9783030637989

SP - 145

EP - 151

BT - The 22nd International Conference on Big Data Analytics and Knowledge Discovery

A2 - Bramer, Max

A2 - Ellis, Richard

PB - Springer

T2 - 22nd International Conference on Big Data Analytics and Knowledge Discovery

Y2 - 14 September 2020 through 17 September 2020

ER -

Developing Ensemble Methods for Detecting Anomalies in Water Level Data

Abstract

Conference

Keywords

Access to Document

Other files and links

Profiles

Tony Bagnall

Wenjia Wang

Cite this