Imaging time series for the classification of EMI discharge sources
- Submitting institution
-
Glasgow Caledonian University
- Unit of assessment
- 12 - Engineering
- Output identifier
- 33575229
- Type
- D - Journal article
- DOI
-
10.3390/s18093098
- Title of journal
- Sensors
- Article number
- 3098
- First page
- -
- Volume
- 18
- Issue
- 9
- ISSN
- 1424-8220
- Open access status
- Compliant
- Month of publication
- September
- Year of publication
- 2018
- 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
-
5
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper achieved for the first-time classification of a wider range of EMI discharge sources collected from various plant sites across multiple assets, which is considered a challenging classification task. A feature extraction and data dimension reduction algorithm called the Gramian Angular Field was exploited, which maps the measured EMI time signals to an image, from which the significant information is extracted while removing redundancy. The image of each discharge type contains a unique fingerprint and its features are implemented into a Random Forest classifier. This method demonstrates higher performance when compared to previous developed methods in this field.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -