Developing Ensemble Methods for Detecting Anomalies in Water Level Data

Khampuengson, Thakolpat, Bagnall, Tony and Wang, Wenjia (2020) Developing Ensemble Methods for Detecting Anomalies in Water Level Data. In: The 22nd International Conference on Big Data Analytics and Knowledge Discovery. Springer, SVK, pp. 145-151. ISBN 9783030637989

[img] PDF (Accepted_Manuscript) - Accepted Version
Restricted to Repository staff only until 8 December 2021.

Download (297kB) | Request a copy

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.

Item Type: Book Section
Uncontrolled Keywords: anomaly detection,ensemble methods,water level telemetry monitoring,theoretical computer science,computer science(all) ,/dk/atira/pure/subjectarea/asjc/2600/2614
Faculty \ School: Faculty of Science > School of Computing Sciences
Related URLs:
Depositing User: LivePure Connector
Date Deposited: 06 Feb 2021 00:34
Last Modified: 12 Jun 2021 00:19
URI: https://ueaeprints.uea.ac.uk/id/eprint/79173
DOI: 10.1007/978-3-030-63799-6_11

Actions (login required)

View Item View Item