Abstract
The problem of data analytics in real world electromagnetic (EM) applications poses a lot of algorithmic constraints. The process of big datasets, the requirement of prior knowledge, unknown location of anomalies and variable length patterns are all issues that need to be addressed. In this application we address those issues by proposing a Fuzzy Symbolic Representational method with anomaly detection (AD). This method is evaluated against twelve benchmark datasets of different kinds of anomalies and provides promising results based on the use of a new performance metric that takes into account the distance between predicted and actual anomalies. Real-world EM data from the Earth’s magnetic field are provided by the SWARM satellite constellation using regions in China, Greece and Peru. The seismic events that occurred in those regions are compared against the SWARM data. Moreover, three other methods: GrammarViz, HOT-SAX and CUSUM-EWMA are also applied to further investigate the possible linkeages of EM anomalies with seismic events. The findings further our understanding of real-world data analytics in EM data and seismicity. Some proposals regarding the limitations of available data for the real-world datasets are also presented.
Original language | English |
---|---|
Pages (from-to) | 3366-3379 |
Number of pages | 14 |
Journal | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Volume | 11 |
Issue number | 9 |
Early online date | 29 Jul 2018 |
DOIs | |
Publication status | Published (in print/issue) - 7 Sept 2018 |
Keywords
- Anomaly Detection
- Symbolic Representation
- Fuzzy Logic
- Electromagnetic Data
- SWARM Satellites
Fingerprint
Dive into the research topics of 'A Fuzzy Shape-Based Anomaly Detection and its Application to Electromagnetic Data'. Together they form a unique fingerprint.Student theses
-
Development and Application of Collective Anomaly Detection methods to Electromagnetic Satellite Data
Christodoulou, V. (Author), Wilkie, G. (Supervisor) & Bi, Y. (Supervisor), Sept 2020Student thesis: Doctoral Thesis
File