Detecting anomalies in time series data via a deep learning algorithm combining wavelets, neural networks and Hilbert transform
- Submitting institution
-
Coventry University
- Unit of assessment
- 12 - Engineering
- Output identifier
- 13660035
- Type
- D - Journal article
- DOI
-
10.1016/j.eswa.2017.04.028
- Title of journal
- Expert Systems with Applications
- Article number
- -
- First page
- 292
- Volume
- 85
- Issue
- -
- ISSN
- 0957-4174
- Open access status
- Compliant
- Month of publication
- April
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- In this paper, we present a novel anomaly detection algorithm that combines the analytic power of wavelets with the modelling flexibility of cascaded Deep Neural Networks. It is an interpretable and transferable algorithm that requires minimum tuning; applied in a range of real-world problems from Seismic Electrical Signals for the prediction of earthquakes to vibrations for the detection of road anomalies. The method has been tested successfully on a variety of real-world engineering datasets (https://doi.org/10.1016/j.eswa.2017.04.028), DOI: 10.1109/TITS.2018.2797943). Last but not least, the paper has been cited by a number of authors until now (https://www.sciencedirect.com/science/article/abs/pii/S0957417417302737).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -