Seismic Anomaly Detection Using Symbolic Representation Methods

Vyron Christodoulou, Yaxin Bi, George Wilkie, Guoze Zhao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this work we investigate the use of symbolic represen- tation methods for Anomaly Detection in different elec- tromagnetic sequential time series datasets. An issue that is often overlooked regarding symbolic representa- tion and its performance in Anomaly Detection is the use of a quantitative accuracy metric. Until recently only vi- sual representations have been used to show the efficiency of an algorithm to detect anomalies. In this respect we propose an novel accuracy metric that takes into account the length of the sliding window of such symbolic rep- resentation algorithms and we present its utility. For the evaluation of the accuracy metric, HOT-SAX is used, a method that aggregates data points by use of sliding win- dows. A HOT-SAX variant, with the use of overlapping windows, is also introduced that achieves better results based on the newly defined accuracy metric. Both meth- ods are evaluated on ten different benchmark datasets and the Earth’s geomagnetic data gathered by the SWARM satellites and terrestrial sources around the epicenter of two seismic events in the Yunnan region of China.
LanguageEnglish
Title of host publicationUnknown Host Publication
Number of pages8
Publication statusPublished - 12 Sep 2016
EventDragon 3 symposium -
Duration: 12 Sep 2016 → …

Conference

ConferenceDragon 3 symposium
Period12/09/16 → …

Fingerprint

Time series
Earth (planet)
Satellites

Keywords

  • Seismic Anomaly Detection
  • Symbolic Rep- resentation of Time Series Data and Accuracy Measure.

Cite this

Christodoulou, V., Bi, Y., Wilkie, G., & Zhao, G. (2016). Seismic Anomaly Detection Using Symbolic Representation Methods. In Unknown Host Publication
Christodoulou, Vyron ; Bi, Yaxin ; Wilkie, George ; Zhao, Guoze. / Seismic Anomaly Detection Using Symbolic Representation Methods. Unknown Host Publication. 2016.
@inproceedings{8ab8de19597c41b8a607739c22d35f86,
title = "Seismic Anomaly Detection Using Symbolic Representation Methods",
abstract = "In this work we investigate the use of symbolic represen- tation methods for Anomaly Detection in different elec- tromagnetic sequential time series datasets. An issue that is often overlooked regarding symbolic representa- tion and its performance in Anomaly Detection is the use of a quantitative accuracy metric. Until recently only vi- sual representations have been used to show the efficiency of an algorithm to detect anomalies. In this respect we propose an novel accuracy metric that takes into account the length of the sliding window of such symbolic rep- resentation algorithms and we present its utility. For the evaluation of the accuracy metric, HOT-SAX is used, a method that aggregates data points by use of sliding win- dows. A HOT-SAX variant, with the use of overlapping windows, is also introduced that achieves better results based on the newly defined accuracy metric. Both meth- ods are evaluated on ten different benchmark datasets and the Earth’s geomagnetic data gathered by the SWARM satellites and terrestrial sources around the epicenter of two seismic events in the Yunnan region of China.",
keywords = "Seismic Anomaly Detection, Symbolic Rep- resentation of Time Series Data and Accuracy Measure.",
author = "Vyron Christodoulou and Yaxin Bi and George Wilkie and Guoze Zhao",
year = "2016",
month = "9",
day = "12",
language = "English",
isbn = "978-92-9221-304-6",
booktitle = "Unknown Host Publication",

}

Christodoulou, V, Bi, Y, Wilkie, G & Zhao, G 2016, Seismic Anomaly Detection Using Symbolic Representation Methods. in Unknown Host Publication. Dragon 3 symposium, 12/09/16.

Seismic Anomaly Detection Using Symbolic Representation Methods. / Christodoulou, Vyron; Bi, Yaxin; Wilkie, George; Zhao, Guoze.

Unknown Host Publication. 2016.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Seismic Anomaly Detection Using Symbolic Representation Methods

AU - Christodoulou, Vyron

AU - Bi, Yaxin

AU - Wilkie, George

AU - Zhao, Guoze

PY - 2016/9/12

Y1 - 2016/9/12

N2 - In this work we investigate the use of symbolic represen- tation methods for Anomaly Detection in different elec- tromagnetic sequential time series datasets. An issue that is often overlooked regarding symbolic representa- tion and its performance in Anomaly Detection is the use of a quantitative accuracy metric. Until recently only vi- sual representations have been used to show the efficiency of an algorithm to detect anomalies. In this respect we propose an novel accuracy metric that takes into account the length of the sliding window of such symbolic rep- resentation algorithms and we present its utility. For the evaluation of the accuracy metric, HOT-SAX is used, a method that aggregates data points by use of sliding win- dows. A HOT-SAX variant, with the use of overlapping windows, is also introduced that achieves better results based on the newly defined accuracy metric. Both meth- ods are evaluated on ten different benchmark datasets and the Earth’s geomagnetic data gathered by the SWARM satellites and terrestrial sources around the epicenter of two seismic events in the Yunnan region of China.

AB - In this work we investigate the use of symbolic represen- tation methods for Anomaly Detection in different elec- tromagnetic sequential time series datasets. An issue that is often overlooked regarding symbolic representa- tion and its performance in Anomaly Detection is the use of a quantitative accuracy metric. Until recently only vi- sual representations have been used to show the efficiency of an algorithm to detect anomalies. In this respect we propose an novel accuracy metric that takes into account the length of the sliding window of such symbolic rep- resentation algorithms and we present its utility. For the evaluation of the accuracy metric, HOT-SAX is used, a method that aggregates data points by use of sliding win- dows. A HOT-SAX variant, with the use of overlapping windows, is also introduced that achieves better results based on the newly defined accuracy metric. Both meth- ods are evaluated on ten different benchmark datasets and the Earth’s geomagnetic data gathered by the SWARM satellites and terrestrial sources around the epicenter of two seismic events in the Yunnan region of China.

KW - Seismic Anomaly Detection

KW - Symbolic Rep- resentation of Time Series Data and Accuracy Measure.

M3 - Conference contribution

SN - 978-92-9221-304-6

BT - Unknown Host Publication

ER -

Christodoulou V, Bi Y, Wilkie G, Zhao G. Seismic Anomaly Detection Using Symbolic Representation Methods. In Unknown Host Publication. 2016